]*>)()', html_string))
24 | assert len(cell_nodes) == len(img['html']['cells']), 'Number of cells defined in tags does not match the length of cells'
25 | cells = [''.join(c['tokens']) for c in img['html']['cells']]
26 | offset = 0
27 | for n, cell in zip(cell_nodes, cells):
28 | html_string = html_string[:n.end(1) + offset] + cell + html_string[n.start(2) + offset:]
29 | offset += len(cell)
30 | # prettify the html
31 | soup = bs(html_string)
32 | html_string = soup.prettify()
33 | return html_string
34 |
35 |
36 | if __name__ == '__main__':
37 | import json
38 | import sys
39 | f = sys.argv[1]
40 | with open(f, 'r') as fp:
41 | annotations = json.load(fp)
42 | for img in annotations['images']:
43 | html_string = format_html(img)
44 | print(html_string)
45 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | *.egg-info/
24 | .installed.cfg
25 | *.egg
26 | MANIFEST
27 |
28 | # PyInstaller
29 | # Usually these files are written by a python script from a template
30 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
31 | *.manifest
32 | *.spec
33 |
34 | # Installer logs
35 | pip-log.txt
36 | pip-delete-this-directory.txt
37 |
38 | # Unit test / coverage reports
39 | htmlcov/
40 | .tox/
41 | .coverage
42 | .coverage.*
43 | .cache
44 | nosetests.xml
45 | coverage.xml
46 | *.cover
47 | .hypothesis/
48 | .pytest_cache/
49 |
50 | # Translations
51 | *.mo
52 | *.pot
53 |
54 | # Django stuff:
55 | *.log
56 | local_settings.py
57 | db.sqlite3
58 |
59 | # Flask stuff:
60 | instance/
61 | .webassets-cache
62 |
63 | # Scrapy stuff:
64 | .scrapy
65 |
66 | # Sphinx documentation
67 | docs/_build/
68 |
69 | # PyBuilder
70 | target/
71 |
72 | # Jupyter Notebook
73 | .ipynb_checkpoints
74 |
75 | # pyenv
76 | .python-version
77 |
78 | # celery beat schedule file
79 | celerybeat-schedule
80 |
81 | # SageMath parsed files
82 | *.sage.py
83 |
84 | # Environments
85 | .env
86 | .venv
87 | env/
88 | venv/
89 | ENV/
90 | env.bak/
91 | venv.bak/
92 |
93 | # Spyder project settings
94 | .spyderproject
95 | .spyproject
96 |
97 | # Rope project settings
98 | .ropeproject
99 |
100 | # mkdocs documentation
101 | /site
102 |
103 | # mypy
104 | .mypy_cache/
105 | .DS_Store
106 | examples.tar.gz
107 | ._examples
108 |
--------------------------------------------------------------------------------
/src/parallel.py:
--------------------------------------------------------------------------------
1 | from tqdm import tqdm
2 | from concurrent.futures import ProcessPoolExecutor, as_completed
3 |
4 | def parallel_process(array, function, n_jobs=16, use_kwargs=False, front_num=0):
5 | """
6 | A parallel version of the map function with a progress bar.
7 |
8 | Args:
9 | array (array-like): An array to iterate over.
10 | function (function): A python function to apply to the elements of array
11 | n_jobs (int, default=16): The number of cores to use
12 | use_kwargs (boolean, default=False): Whether to consider the elements of array as dictionaries of
13 | keyword arguments to function
14 | front_num (int, default=3): The number of iterations to run serially before kicking off the parallel job.
15 | Useful for catching bugs
16 | Returns:
17 | [function(array[0]), function(array[1]), ...]
18 | """
19 | # We run the first few iterations serially to catch bugs
20 | if front_num > 0:
21 | front = [function(**a) if use_kwargs else function(a) for a in array[:front_num]]
22 | else:
23 | front = []
24 | # If we set n_jobs to 1, just run a list comprehension. This is useful for benchmarking and debugging.
25 | if n_jobs == 1:
26 | return front + [function(**a) if use_kwargs else function(a) for a in tqdm(array[front_num:])]
27 | # Assemble the workers
28 | with ProcessPoolExecutor(max_workers=n_jobs) as pool:
29 | # Pass the elements of array into function
30 | if use_kwargs:
31 | futures = [pool.submit(function, **a) for a in array[front_num:]]
32 | else:
33 | futures = [pool.submit(function, a) for a in array[front_num:]]
34 | kwargs = {
35 | 'total': len(futures),
36 | 'unit': 'it',
37 | 'unit_scale': True,
38 | 'leave': True
39 | }
40 | # Print out the progress as tasks complete
41 | for f in tqdm(as_completed(futures), **kwargs):
42 | pass
43 | out = []
44 | # Get the results from the futures.
45 | for i, future in tqdm(enumerate(futures)):
46 | try:
47 | out.append(future.result())
48 | except Exception as e:
49 | out.append(e)
50 | return front + out
51 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # PubTabNet
2 |
3 | PubTabNet is a large dataset for image-based table recognition, containing 568k+ images of tabular data annotated with the corresponding HTML representation of the tables. The table images are extracted from the scientific publications included in the [PubMed Central Open Access Subset (commercial use collection)](https://www.ncbi.nlm.nih.gov/pmc/tools/openftlist/). Table regions are identified by matching the PDF format and the XML format of the articles in the PubMed Central Open Access Subset. More details are available in our paper ["Image-based table recognition: data, model, and evaluation"](https://arxiv.org/abs/1911.10683).
4 |
5 | ## Headlines
6 |
7 | `07/Mar/2022` - Test set and ground truth for the ICDAR 2021 Scientific Literature Parsing competition available [here](https://github.com/ajjimeno/icdar-task-b).
8 |
9 | `04/May/2021` - Report for the ICDAR 2021 Scientific Literature Parsing competition available [here](https://github.com/ibm-aur-nlp/PubLayNet/blob/master/ICDAR_SLR_competition/ICDAR_2021_Scientific_Literature_Parsing.pdf).
10 |
11 | `21/July/2020` - PubTabNet 2.0.0 is released, where the position (bounding box) of non-empty cells is added into the annotation. The annotation file is also changed from `json` format to `jsonl` format to reduce the requirement on large RAM.
12 |
13 | `20/Jul/2020` - PubTabNet is used in [ICDAR 2021 Competition on Scientific Literature Parsing](https://github.com/IBM/ICDAR2021-SLP) ([Task B on Table Recognition](https://aieval.draco.res.ibm.com/challenge/40/overview))
14 |
15 | `03/July/2020` - `Image-based table recognition: data, model, and evaluation` is accepted by ECCV20.
16 |
17 | `01/July/2020` - Code of **T**ree-**Edit**-**D**istance-based **S**imilarity (TEDS) metric is [released](src).
18 |
19 | ## Updates in progress
20 |
21 | ### Encoder-dual-decoder model
22 |
23 | In our paper, we proposed a new encoder-dual-decoder architecture, which was trained on PubTabNet and can accurately reconstruct the HTML representation of complex tables solely relying on image input. Due to legal constraints, the source code of the model will not be released.
24 |
25 | ### Ground truth of test set
26 |
27 | The ground truth of test will not be release, as we want to keep it for a competition in the future. We will offer a service for people to submit and evaluate their results soon.
28 |
29 | ## Getting data
30 |
31 | PubTabNet is available from: [ajimeno/PubTabNet](https://huggingface.co/datasets/ajimeno/PubTabNet)
32 |
33 | Test set and ground truth for the ICDAR 2021 Scientific Literature Parsing competition available [here](https://github.com/ajjimeno/icdar-task-b).
34 |
35 | ## Annotation structure
36 |
37 | The annotation is in the jsonl (jsonlines) format, where each line contains the annotations on a given sample in the following format:
38 | The structure of the annotation jsonl file is:
39 |
40 | ```
41 | {
42 | 'filename': str,
43 | 'split': str,
44 | 'imgid': int,
45 | 'html': {
46 | 'structure': {'tokens': [str]},
47 | 'cell': [
48 | {
49 | 'tokens': [str],
50 | 'bbox': [x0, y0, x1, y1] # only non-empty cells have this attribute
51 | }
52 | ]
53 | }
54 | }
55 | ```
56 |
57 | ## Cite us
58 |
59 | ```
60 | @article{zhong2019image,
61 | title={Image-based table recognition: data, model, and evaluation},
62 | author={Zhong, Xu and ShafieiBavani, Elaheh and Yepes, Antonio Jimeno},
63 | journal={arXiv preprint arXiv:1911.10683},
64 | year={2019}
65 | }
66 | ```
67 |
68 | ## Examples
69 |
70 | A [Jupyter notebook](./exploring_PubTabNet_dataset.ipynb) is provided to inspect the annotations of 20 sample tables.
71 |
72 |
73 | ## Related links
74 |
75 | [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) is a large dataset of document images, of which the layout is annotated with both bounding boxes and polygonal segmentations. The source of the documents is [PubMed Central Open Access Subset (commercial use collection)](https://www.ncbi.nlm.nih.gov/pmc/tools/openftlist/). The annotations are automatically generated by matching the PDF format and the XML format of the articles in the PubMed Central Open Access Subset. More details are available in our paper ["PubLayNet: largest dataset ever for document layout analysis."](https://arxiv.org/abs/1908.07836), which was awarded the [best paper at ICDAR 2019](http://icdar2019.org/award/)!
76 |
--------------------------------------------------------------------------------
/src/demo.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "metadata": {},
6 | "source": [
7 | "## Evaluate a single prediction agains ground truth"
8 | ]
9 | },
10 | {
11 | "cell_type": "code",
12 | "execution_count": 5,
13 | "metadata": {},
14 | "outputs": [],
15 | "source": [
16 | "# Sample HTML code\n",
17 | "pred = '| Name of algori | Notablefeatures |
| MACS [23] | Uses both a control library and local statistics to minimize bias |
| SICER [15] | Designed for detecting diffusely enriched regions; for example, histone modification |
| PeakSEQ [24] | Corrects for reference genome mappability and local statistics |
| SISSRs [25] | High resolution, precise identification of binding-site location |
| F-seq [26] | Uses kernel density estimation |
'\n",
18 | "true = '| Name of algorithm | Notable features |
| MACS [23] | Uses both a control library and local statistics to minimize bias |
| SICER [14] | Designed for detecting diffusely enriched regions; for example, histone modification |
| PeakSeq [24] | Corrects for reference genome mappability and local statistics |
| SISSRs [25] | High resolution, precise identification of binding-site location |
| F-seq [26] | Uses kernel density estimation |
'"
19 | ]
20 | },
21 | {
22 | "cell_type": "code",
23 | "execution_count": 10,
24 | "metadata": {},
25 | "outputs": [
26 | {
27 | "name": "stdout",
28 | "output_type": "stream",
29 | "text": [
30 | "TEDS score: 0.9781765018607124\n"
31 | ]
32 | }
33 | ],
34 | "source": [
35 | "from metric import TEDS\n",
36 | "# Initialize TEDS object\n",
37 | "teds = TEDS()\n",
38 | "# Evaluate\n",
39 | "score = teds.evaluate(pred, true)\n",
40 | "print('TEDS score:', score)"
41 | ]
42 | },
43 | {
44 | "cell_type": "markdown",
45 | "metadata": {},
46 | "source": [
47 | "## Batch evaluation with parallel threads"
48 | ]
49 | },
50 | {
51 | "cell_type": "code",
52 | "execution_count": 7,
53 | "metadata": {},
54 | "outputs": [],
55 | "source": [
56 | "import json\n",
57 | "import pprint\n",
58 | "from metric import TEDS"
59 | ]
60 | },
61 | {
62 | "cell_type": "code",
63 | "execution_count": 8,
64 | "metadata": {},
65 | "outputs": [],
66 | "source": [
67 | "# Load sample ground truth and predictions\n",
68 | "with open('sample_pred.json') as fp:\n",
69 | " pred_json = json.load(fp)\n",
70 | "with open('sample_gt.json') as fp:\n",
71 | " true_json = json.load(fp)"
72 | ]
73 | },
74 | {
75 | "cell_type": "code",
76 | "execution_count": 9,
77 | "metadata": {},
78 | "outputs": [
79 | {
80 | "name": "stderr",
81 | "output_type": "stream",
82 | "text": [
83 | "100%|██████████| 19.0/19.0 [00:10<00:00, 1.50s/it]\n",
84 | "19it [00:00, 112400.25it/s]"
85 | ]
86 | },
87 | {
88 | "name": "stdout",
89 | "output_type": "stream",
90 | "text": [
91 | "{'PMC2094709_004_00.png': 1.0,\n",
92 | " 'PMC2871264_002_00.png': 1.0,\n",
93 | " 'PMC2915972_003_00.png': 0.9298260149130074,\n",
94 | " 'PMC3160368_005_00.png': 0.994615695248351,\n",
95 | " 'PMC3568059_003_00.png': 0.9609420535891124,\n",
96 | " 'PMC3707453_006_00.png': 0.8538903625110521,\n",
97 | " 'PMC3765162_003_01.png': 0.9867342100509474,\n",
98 | " 'PMC3872294_001_00.png': 0.9863636363636363,\n",
99 | " 'PMC4196076_004_00.png': 0.9958653089334908,\n",
100 | " 'PMC4219599_004_00.png': 0.6029978075326913,\n",
101 | " 'PMC4297392_007_00.png': 0.8070175438596492,\n",
102 | " 'PMC4311460_007_00.png': 0.6576923076923077,\n",
103 | " 'PMC4357206_002_00.png': 0.9295181638546892,\n",
104 | " 'PMC4445578_009_01.png': 0.6754965084868096,\n",
105 | " 'PMC4969833_016_01.png': 1.0,\n",
106 | " 'PMC5303243_003_00.png': 0.6494374120956399,\n",
107 | " 'PMC5451934_004_00.png': 0.9978213507625272,\n",
108 | " 'PMC5755158_010_01.png': 1.0,\n",
109 | " 'PMC5849724_006_00.png': 0.9653439200120101,\n",
110 | " 'PMC6022086_007_00.png': 1.0}\n"
111 | ]
112 | },
113 | {
114 | "name": "stderr",
115 | "output_type": "stream",
116 | "text": [
117 | "\n"
118 | ]
119 | }
120 | ],
121 | "source": [
122 | "# Initialize TEDS object, using 4 parallel threads\n",
123 | "teds = TEDS(n_jobs=4)\n",
124 | "# Evaluate\n",
125 | "scores = teds.batch_evaluate(pred_json, true_json)\n",
126 | "# Print results\n",
127 | "pp = pprint.PrettyPrinter()\n",
128 | "pp.pprint(scores)"
129 | ]
130 | }
131 | ],
132 | "metadata": {
133 | "kernelspec": {
134 | "display_name": "Python 3",
135 | "language": "python",
136 | "name": "python3"
137 | },
138 | "language_info": {
139 | "codemirror_mode": {
140 | "name": "ipython",
141 | "version": 3
142 | },
143 | "file_extension": ".py",
144 | "mimetype": "text/x-python",
145 | "name": "python",
146 | "nbconvert_exporter": "python",
147 | "pygments_lexer": "ipython3",
148 | "version": "3.6.8"
149 | }
150 | },
151 | "nbformat": 4,
152 | "nbformat_minor": 2
153 | }
154 |
--------------------------------------------------------------------------------
/src/metric.py:
--------------------------------------------------------------------------------
1 | # Copyright 2020 IBM
2 | # Author: peter.zhong@au1.ibm.com
3 | #
4 | # This is free software; you can redistribute it and/or modify
5 | # it under the terms of the Apache 2.0 License.
6 | #
7 | # This software is distributed in the hope that it will be useful,
8 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
9 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
10 | # Apache 2.0 License for more details.
11 |
12 | import distance
13 | from apted import APTED, Config
14 | from apted.helpers import Tree
15 | from lxml import etree, html
16 | from collections import deque
17 | from parallel import parallel_process
18 | from tqdm import tqdm
19 |
20 | class TableTree(Tree):
21 | def __init__(self, tag, colspan=None, rowspan=None, content=None, *children):
22 | self.tag = tag
23 | self.colspan = colspan
24 | self.rowspan = rowspan
25 | self.content = content
26 | self.children = list(children)
27 |
28 | def bracket(self):
29 | """Show tree using brackets notation"""
30 | if self.tag == 'td':
31 | result = '"tag": %s, "colspan": %d, "rowspan": %d, "text": %s' % \
32 | (self.tag, self.colspan, self.rowspan, self.content)
33 | else:
34 | result = '"tag": %s' % self.tag
35 | for child in self.children:
36 | result += child.bracket()
37 | return "{{{}}}".format(result)
38 |
39 |
40 | class CustomConfig(Config):
41 | @staticmethod
42 | def maximum(*sequences):
43 | """Get maximum possible value
44 | """
45 | return max(map(len, sequences))
46 |
47 | def normalized_distance(self, *sequences):
48 | """Get distance from 0 to 1
49 | """
50 | return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
51 |
52 | def rename(self, node1, node2):
53 | """Compares attributes of trees"""
54 | if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan):
55 | return 1.
56 | if node1.tag == 'td':
57 | if node1.content or node2.content:
58 | return self.normalized_distance(node1.content, node2.content)
59 | return 0.
60 |
61 |
62 | class TEDS(object):
63 | ''' Tree Edit Distance basead Similarity
64 | '''
65 | def __init__(self, structure_only=False, n_jobs=1, ignore_nodes=None):
66 | assert isinstance(n_jobs, int) and (n_jobs >= 1), 'n_jobs must be an integer greather than 1'
67 | self.structure_only = structure_only
68 | self.n_jobs = n_jobs
69 | self.ignore_nodes = ignore_nodes
70 | self.__tokens__ = []
71 |
72 | def tokenize(self, node):
73 | ''' Tokenizes table cells
74 | '''
75 | self.__tokens__.append('<%s>' % node.tag)
76 | if node.text is not None:
77 | self.__tokens__ += list(node.text)
78 | for n in node.getchildren():
79 | self.tokenize(n)
80 | if node.tag != 'unk':
81 | self.__tokens__.append('' % node.tag)
82 | if node.tag != 'td' and node.tail is not None:
83 | self.__tokens__ += list(node.tail)
84 |
85 | def load_html_tree(self, node, parent=None):
86 | ''' Converts HTML tree to the format required by apted
87 | '''
88 | global __tokens__
89 | if node.tag == 'td':
90 | if self.structure_only:
91 | cell = []
92 | else:
93 | self.__tokens__ = []
94 | self.tokenize(node)
95 | cell = self.__tokens__[1:-1].copy()
96 | new_node = TableTree(node.tag,
97 | int(node.attrib.get('colspan', '1')),
98 | int(node.attrib.get('rowspan', '1')),
99 | cell, *deque())
100 | else:
101 | new_node = TableTree(node.tag, None, None, None, *deque())
102 | if parent is not None:
103 | parent.children.append(new_node)
104 | if node.tag != 'td':
105 | for n in node.getchildren():
106 | self.load_html_tree(n, new_node)
107 | if parent is None:
108 | return new_node
109 |
110 | def evaluate(self, pred, true):
111 | ''' Computes TEDS score between the prediction and the ground truth of a
112 | given sample
113 | '''
114 | if (not pred) or (not true):
115 | return 0.0
116 | parser = html.HTMLParser(remove_comments=True, encoding='utf-8')
117 | pred = html.fromstring(pred, parser=parser)
118 | true = html.fromstring(true, parser=parser)
119 | if pred.xpath('body/table') and true.xpath('body/table'):
120 | pred = pred.xpath('body/table')[0]
121 | true = true.xpath('body/table')[0]
122 | if self.ignore_nodes:
123 | etree.strip_tags(pred, *self.ignore_nodes)
124 | etree.strip_tags(true, *self.ignore_nodes)
125 | n_nodes_pred = len(pred.xpath(".//*"))
126 | n_nodes_true = len(true.xpath(".//*"))
127 | n_nodes = max(n_nodes_pred, n_nodes_true)
128 | tree_pred = self.load_html_tree(pred)
129 | tree_true = self.load_html_tree(true)
130 | distance = APTED(tree_pred, tree_true, CustomConfig()).compute_edit_distance()
131 | return 1.0 - (float(distance) / n_nodes)
132 | else:
133 | return 0.0
134 |
135 | def batch_evaluate(self, pred_json, true_json):
136 | ''' Computes TEDS score between the prediction and the ground truth of
137 | a batch of samples
138 | @params pred_json: {'FILENAME': 'HTML CODE', ...}
139 | @params true_json: {'FILENAME': {'html': 'HTML CODE'}, ...}
140 | @output: {'FILENAME': 'TEDS SCORE', ...}
141 | '''
142 | samples = true_json.keys()
143 | if self.n_jobs == 1:
144 | scores = [self.evaluate(pred_json.get(filename, ''), true_json[filename]['html']) for filename in tqdm(samples)]
145 | else:
146 | inputs = [{'pred': pred_json.get(filename, ''), 'true': true_json[filename]['html']} for filename in samples]
147 | scores = parallel_process(inputs, self.evaluate, use_kwargs=True, n_jobs=self.n_jobs, front_num=1)
148 | scores = dict(zip(samples, scores))
149 | return scores
150 |
151 |
152 | if __name__ == '__main__':
153 | import json
154 | import pprint
155 | with open('sample_pred.json') as fp:
156 | pred_json = json.load(fp)
157 | with open('sample_gt.json') as fp:
158 | true_json = json.load(fp)
159 | teds = TEDS(n_jobs=4)
160 | scores = teds.batch_evaluate(pred_json, true_json)
161 | pp = pprint.PrettyPrinter()
162 | pp.pprint(scores)
163 |
--------------------------------------------------------------------------------
/src/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/src/sample_gt.json:
--------------------------------------------------------------------------------
1 | {"PMC5755158_010_01.png": {"html": " | Weaning | Week 15 | Off-test |
| Weaning | \u2013 | \u2013 | \u2013 |
| Week 15 | \u2013 | 0.17 \u00b1 0.08 | 0.16 \u00b1 0.03 |
| Off-test | \u2013 | 0.80 \u00b1 0.24 | 0.19 \u00b1 0.09 |
", "tag_len": 44, "cell_len_max": 11, "width": 238, "height": 59, "type": "simple"}, "PMC4445578_009_01.png": {"html": "| Reactive astrogliois | Changes in astrocytes morphology | Changes in molecules expression |
| Upregulated molecules | Upregulated or downregulated molecules |
| Mild to moderate astrogliosis | \u2022 Hypertrophy of cell body | \u2022 Structural elements: GFAP, nestin, vimentin | \u2022 Inflammatory cell regulators: cytokines, growth factors, glutathione |
| \u2022 Astrocytes processes are are numerous and thicker | \u2022 Transcriptional regulators: STAT3, NF\u03baB, Rheb-m TOR, cAMP, Olig2, SOX9 [61\u201365]. | \u2022 Transporters and pumps: AQP4 and Na+/K+ transporters [61, 66\u201369] |
| \u2022 Glutamate transporter [70\u201373] |
| \u2022 The non-overlapping domains of individual astrocytes are preserved | | \u2022 Vascular regulators: PGE, NO [74, 75] |
| \u2022 Energy provision: lactate [76] |
| \u2022 Molecules implicated in synapse formation and |
| Severe astrogliosis and glial scar | \u2022 Intense hypertrophy of cell body | | \u2022 Remodeling: thrombospondin and Complement C1q [77, 78] |
| \u2022 Significant extension of processes | | \u2022 Molecules implicated in oxidative stress and providing protection from oxidative stress: NO, NOS, SOD, Glutathione [67, 68, 79] |
| \u2022 Proliferation | | |
| \u2022 Overlapping of individual domains | | |
| \u2022 Substantial reorganization of tissue architecture [60] | | |
", "tag_len": 116, "cell_len_max": 129, "width": 486, "height": 248, "type": "complex"}, "PMC2871264_002_00.png": {"html": "| Name of algorithm | Notable features |
| MACS [23] | Uses both a control library and local statistics to minimize bias |
| SICER [14] | Designed for detecting diffusely enriched regions; for example, histone modification |
| PeakSeq [24] | Corrects for reference genome mappability and local statistics |
| SISSRs [25] | High resolution, precise identification of binding-site location |
| F-seq [26] | Uses kernel density estimation |
", "tag_len": 40, "cell_len_max": 84, "width": 238, "height": 124, "type": "simple"}, "PMC3872294_001_00.png": {"html": " | HC (N = 20) | FASD (N = 15) |
| Age (years) | 16.3 (2.1) | 15.3 (2.1) |
| IQ | 108 (15)* | 80 (15)* |
| Male/female (%male) | 12/8 (60%) | 10/5 (67%) |
| FASD sub diagnosis | \u2013 | 8 FAS, 7 ARND |
", "tag_len": 44, "cell_len_max": 19, "width": 251, "height": 88, "type": "simple"}, "PMC2915972_003_00.png": {"html": " | No of patients |
| Gender: | |
| Men | 24 |
| Women | 26 |
| Age (years): | |
| 30-39 | 2 |
| 40-49 | 8 |
| 50-59 | 15 |
| 60-69 | 16 |
| 70-79 | 6 |
| \u2265 80 | 3 |
| Tumor site: | |
| Bladder | 4 |
| Breast | 10 |
| Colorectal | 4 |
| Esophageal | 9 |
| Gynecological | 7 |
| Lung | 6 |
| Prostate | 10 |
| Length of interval between baseline and follow-up interview |
| (median) | |
| < 50 days | 22 |
| \u2265 50 days | 28 |
", "tag_len": 142, "cell_len_max": 59, "width": 238, "height": 287, "type": "complex"}, "PMC4196076_004_00.png": {"html": "| miRNA | Change relative to controls | Direction of regulation | Chromosome | miRNA | Change relative to controls | Direction of regulation | Chromosome |
| hsa-miR-1181 | 2.13 | Up | 19 | hsa-miR-874 | 2.97 | Up | 5 |
| hsa-miR-125a-5p | 5.04 | Up | 19 | hsa-miR-890 | 2.83 | Up | X |
| hsa-miR-21-3p | 2.82 | Up | 17 | hsa-miR-939 | 2.59 | Up | 8 |
| hsa-miR-29b-1-5p | 3.12 | Up | 7 | hsa-miR-1290 | \u22127.56 | Down | 1 |
| hsa-miR-3663-3p | 2.19 | Up | 10 | hsa-miR-1915-3p | \u22122.63 | Down | 10 |
| hsa-miR-3127-5p | 2.01 | Up | 2 | hsa-miR-2861 | \u22123.31 | Down | 9 |
| hsa-miR-3663-3p | 2.03 | Up | 10 | hsa-miR-3665 | \u22122.37 | Down | 13 |
| hsa-miR-371a-5p | 3.14 | Up | 19 | hsa-miR-4257 | \u22123.62 | Down | 1 |
| hsa-miR-4327 | 2.95 | Up | 21 | hsa-miR-452-5p | \u22122.54 | Down | X |
| hsa-miR-584-5p | 2.31 | Up | 5 | hsa-miR-513a-5p | \u22123.15 | Down | X |
| hsa-miR-602 | 5.74 | Up | 9 | hsa-miR-572 | \u22125.80 | Down | 4 |
| hsa-miR-629-3p | 2.71 | Up | 15 | hsa-miR-629-3p | \u22123.03 | Down | 15 |
| hsa-miR-642b-3p | 2.10 | Up | 19 | hsa-miR-765 | \u22127.18 | Down | 1 |
| hsa-miR-651 | 3.91 | Up | X | hsa-miR-875-5p | \u22123.91 | Down | 8 |
| hsa-miR-762 | 2.84 | Up | 16 | hsa-miR-940 | \u22122.31 | Down | 16 |
", "tag_len": 292, "cell_len_max": 29, "width": 486, "height": 236, "type": "simple"}, "PMC3160368_005_00.png": {"html": "| Methods (n-mers used) | Average Sensitivity of 5-fold cross validation (%) | Average Specificity of 5-fold cross validation (%) |
| FDAFSA(hexamers) | 84* | 86* |
| PromMachine(tetramers) | 86+ | 81+ |
", "tag_len": 28, "cell_len_max": 52, "width": 238, "height": 71, "type": "simple"}, "PMC3707453_006_00.png": {"html": "| TFC Layer Thickness [\u03bcm] | Star Magnitude 1 | Star Magnitude 6 | Saturation Charge [e-] | Capacitance Linearity [%] |
| Signal @ 0.1s integr. [e-] | Noise @ 0.1s integr. [e-] | S/N at 10 bit A/D [dB] | Signal @ 0.1s integr. [e-] | Noise @ 0.1s integr. [e-] | S/N at 10 bit A/D [dB] |
| 0.5 | 121200 | 498 | 47 | 1882 | 358 | 10 | 500000 | 99.2 |
| 1.0 | 143960 | 426 | 50 | 1610 | 199 | 13 | 272232 | 98.6 |
| 1.5 | 155220 | 418 | 50 | 1713 | 147 | 19 | 197109 | 98.1 |
| 1.8 | 159950 | 418 | 50 | 1759 | 130 | 19 | 172018 | 97.8 |
| 2.0 | 162400 | 419 | 50 | 1784 | 122 | 19 | 159575 | 97.6 |
| 2.2 | 164550 | 420 | 50 | 1807 | 115 | 19 | 149254 | 97.5 |
", "tag_len": 160, "cell_len_max": 30, "width": 446, "height": 184, "type": "complex"}, "PMC4311460_007_00.png": {"html": " | | | | Number | | Patients | |
| Category | Type | | | CHP | % | (N = 4,560) | % |
| I | Inflammation | | 6,987 | 11.3 | 3,537 | 77.6 |
| II | Infection | | | 3,629 | 5.9 | 2,451 | 53.8 |
| III | Injury | | | 5,556 | 9.0 | 3,401 | 74.6 |
| IV | Specific conditions | | 32,016 | 51.9 | n.c. | |
| V | Neoplasms | | 3,592 | 5.8 | 2,461# | 54 |
| | Maligne | 1,444 | | | | 1,219 (27%) |
| | Other-benign | 2,148 | | | | 1,758 (39%) |
| VI | Congenital | | 490 | 0.8 | n.c. | |
| VII | Otherwise | | 9,383 | 15.2 | n.c. | |
| Total | ALL-types | | 61,653 | 100 | | |
", "tag_len": 220, "cell_len_max": 19, "width": 486, "height": 170, "type": "complex"}, "PMC5451934_004_00.png": {"html": "| Condition | Pre Well-Being | Post Well-Being | Pre-Post Change |
| TP (handler & dog interaction) | 46.33 \u00b1 7.41 1 | 48.69 \u00b1 7.22 | +2.36 |
| DO (dog only interaction) | 49.78 \u00b1 7.91 | 51.56 \u00b1 6.99 | +1.78 ** |
| HO (handler only interaction) | 47.37 \u00b1 7.57 | 46.43 \u00b1 8.03 | \u22120.94 ** |
", "tag_len": 44, "cell_len_max": 30, "width": 389, "height": 56, "type": "simple"}, "PMC5849724_006_00.png": {"html": "| Analytes | GC\u2013HRMS | GC\u2013MS/MS | GC\u2013MS |
| LOQ, (ng/CFPa) | Estimated LOQ, (ng/cig) | LOQ, (ng/CFPa) | Estimated LOQ, (ng/cig) | LOQ, (ng/CFPa) | Estimated LOQ, (ng/cig) |
| Naphthalene | 0.51 | 0.026 | 1178.71 | 58.94 | 108.17 | 5.41 |
| Benzo[c]phenanthrene | 0.04 | 0.002 | ND | ND | 66.80 | 3.34 |
| Benzo[a]anthracene | 0.03 | 0.002 | 38.57 | 1.93 | 38.11 | 1.91 |
| Chrysene | 0.04 | 0.002 | 50.13 | 2.51 | 49.61 | 2.48 |
| Cyclopenta[c,d]pyrene | 0.02 | 0.001 | 48.84 | 2.44 | 60.04 | 3.00 |
| 5-Methylchrysene | 0.04 | 0.002 | ND | ND | 2.48 | 0.12 |
| Benzo[b]fluoranthene | 0.04 | 0.002 | 11.44 | 0.57 | 5.08 | 0.25 |
| Benzo[k]fluoranthene | 0.05 | 0.003 | 12.41 | 0.62 | 5.07 | 0.25 |
| Benzo[j]aceanthrylene | 0.09 | 0.005 | ND | ND | ND | ND |
| Benzo[a]pyrene | 0.04 | 0.002 | 5.01 | 0.25 | 3.03 | 0.15 |
| Indeno[1,2,3-c,d]pyrene | 0.02 | 0.001 | 5.46 | 0.27 | 1.54 | 0.08 |
| Dibenzo[a,h]anthracene | 0.07 | 0.004 | 0.83 | 0.04 | 1.48 | 0.07 |
| Dibenzo[a,l]pyrene | 0.05 | 0.003 | ND | ND | ND | ND |
| Dibenzo[a,e]pyrene | 0.04 | 0.002 | 0.80 | 0.04 | 0.28 | 0.01 |
| Dibenzo[a,i]pyrene | 0.06 | 0.003 | 1.33 | 0.07 | ND | ND |
| Dibenzo[a,h]pyrene | 0.07 | 0.004 | 2.99 | 0.15 | ND | ND |
", "tag_len": 292, "cell_len_max": 27, "width": 486, "height": 253, "type": "complex"}, "PMC6022086_007_00.png": {"html": "| Method | Data Type | Mean (m) | RMSE (m) | P90% (m) | PGSD (%) |
| Improved FCM | Gaofen-3 | 5.77 | 5.89 | 10.07 | 94.37 |
| Sentinel-1 | 6.30 | 5.83 | 14.03 | 80.00 |
| Original FCM | Gaofen-3 | 6.97 | 7.66 | 13.87 | 90.70 |
| Sentinel-1 | 8.53 | 4.81 | 13.14 | 90.00 |
", "tag_len": 74, "cell_len_max": 12, "width": 409, "height": 77, "type": "complex"}, "PMC4297392_007_00.png": {"html": "| Treatment phase | Adverse event | No. of patients |
| T1 | Swelling | 1 |
| Itching | 1 |
| Fever | 4 |
| Throat infection | 1 |
| Chest Congestion | 2 |
| Total | 9 |
| T2 | Diarrhea | 1 |
| Body Pain | 1 |
| Total | 2 |
| T3 | Diarrhea | 1 |
| Total | 1 |
| T4 | Nil | - |
", "tag_len": 98, "cell_len_max": 17, "width": 238, "height": 185, "type": "complex"}, "PMC2094709_004_00.png": {"html": "| Week | Duration (min) | Intensity (% HRR) | Intensity (RPE) |
| 1 | 20 | 50 \u2013 60 | 9 \u2013 11 |
| 2 | 20 | 50 \u2013 60 | 9 \u2013 11 |
| 3 \u2013 5 | 25 | 60 \u2013 70 | 11 |
| 6 \u2013 8 | 30 | 60 \u2013 70 | 11 |
| 9 \u2013 11 | 30 | 70 \u2013 80 | 11 \u2013 13 |
| 12 \u2013 14 | 35 | 70 \u2013 80 | 11 \u2013 13 |
| 15 & 16 | 40 | 75 \u2013 85 | 13 \u2013 15 |
", "tag_len": 84, "cell_len_max": 19, "width": 503, "height": 107, "type": "simple"}, "PMC3568059_003_00.png": {"html": "| | Participants during the period; |
| | 0 to 3 months | 3 to 6 months | 6 to 12 months |
| Characteristics | n=72 | n=71 | n=65 |
| Age, years, median (range) | 73 (50\u201394) | 73 (47\u201392) | 73 (47\u201390) |
| Patients, n (%) | | | |
| Female | 33 (46) | 27 (38) | 26 (40) |
| Male | 39 (54) | 44 (62) | 39 (60) |
| Stroke classification (TOAST), n (%) | | | |
| Large vessel disease | 17 (24) | 18 (25) | 17 (26) |
| Small vessel disease | 21 (29) | 21 (30) | 17 (26) |
| Cardioembolic stroke | 15 (21) | 11 (15) | 11 (17) |
| Cryptogenic stroke | 13 (18) | 14 (20) | 12 (19) |
| Intracerebral haemorrhage | 6 (8) | 7 (10) | 8 (12) |
| Side of lesion, n (%) | | | |
| Right side lesion | 35 (49) | 32 (45) | 28 (43) |
| Left side lesion | 37 (51) | 39 (55) | 37 (57) |
| Hypertension | 47 (65) | 44 (62) | 41 (63) |
| Diabetes mellitus | 17 (24) | 18 (25) | 17 (26) |
| Results from clinical scales 1\u20137 days after stroke onset |
| BBS median (range) (n) | 35 (0\u201356) (n=71) | 41 (0\u201356) (n=70) | 41 (0\u201356) (n=64) |
| M-MAS UAS-95 median (range) | 45 (12\u201355) (n=65) | 47 (12\u201355) (n=65) | 50 (16\u201355) (n=59) |
", "tag_len": 208, "cell_len_max": 56, "width": 486, "height": 296, "type": "complex"}, "PMC4357206_002_00.png": {"html": " | N = 121 |
| Demographics | |
| Age (yr) - median (IQR) | 62 (56-73) |
| Female sex (%) | 46 (38) |
| White race (%) | 112 (93) |
| Comorbidities (%) | |
| Hypertension | 64 (53) |
| Chronic lung disease | 37 (31) |
| Active malignancy | 34 (28) |
| Diabetes mellitus | 29 (24) |
| Chronic kidney disease | 7 (6) |
| Congestive heart failure | 4 (3) |
| Chronic liver disease | 2 (2) |
| Severity of illness | |
| APACHE II score - median (IQR)* | 14 (10-16) |
| Charlson Comorbidity Index - median (IQR)\u2020 | 2 (1-4) |
| ICU type | |
| Surgical | 102 (84) |
| SICU | 66 (54) |
| TICU | 36 (30) |
| Nonsurgical | 19 (16) |
| CCU | 11 (9) |
| MICU | 8 (7) |
| Status of procedure (for surgical patients) (%) | |
| Elective | 41 (34) |
| Urgent | 57 (47) |
| Days in hospital prior to enrollment \u2013 median (IQR) | 1 (1-3) |
", "tag_len": 166, "cell_len_max": 51, "width": 238, "height": 381, "type": "simple"}, "PMC4219599_004_00.png": {"html": "| | ORP (n = 9) | RALP (n = 24) | Total (n = 33) |
| Anthropometric data | | | |
| Age (yr) | 60 (7) | 63 (6) | 62 (6) |
| Height (m) | 1.76 (0.07) | 1.75 (0.05) | 1.75 (0.06) |
| Weight (kg) | 92 (12) | 83 (10) | 86 (11) |
| BMI (kg.m-2) | 29.6 (4.5) | 27.3 (3.0) | 27.9 (3.6) |
| Preoperative factors | | | |
| PSA (ng/mL) | 5.8 (4.2) | 5.0 (2.1) | 5.2 (2.8) |
| Preoperative Gleason score | | | |
| 3 + 3 | 1 (11%) | 5 (21%) | 6 (18%) |
| 3 + 4 | 5 (56%) | 16 (67%) | 21 (64%) |
| 4 + 3 | 3 (33%) | 2 (9%) | 5 (15%) |
| 4 + 4 | 0 (0%) | 1 (4%) | 1 (3%) |
| Clinical tumour stage | | | |
| cT1 | 4 (44%) | 13 (54%) | 17 (52%) |
| cT2 | 5 (56%) | 11 (46%) | 16 (48%) |
| cT3 | 0 (0%) | 0 (0%) | 0 (0%) |
| cT4 | 0 (0%) | 0 (0%) | 0 (0%) |
| Prostate volume (cc) | 40.2 (13.4) | 41.2 (12.5) | 40.9 (12.6) |
| Intraoperative factors | | | |
| Nerve sparing | | | |
| None | 3 (33%) | 3 (13%) | 6 (18%) |
| One bundle | 2 (22%) | 2 (9%) | 4 (12%) |
| Two bundles | 4 (44%) | 19 (79%) | 23 (70%) |
| Pelvic lymph node dissection | 7 (78%) | 2 (9%)a | 9 (27%) |
| Bladder neck preservation | 0 (0%) | 23 (96%)a | 23 (70%) |
| Postoperative factors | | | |
| Postoperative Gleason score | | | |
| 3 + 3 | 1 (11%) | 3 (13%) | 4 (12%) |
| 3 + 4 | 6 (67%) | 16 (67%) | 22 (67%) |
| 4 + 3 | 2 (22%) | 5 (21%) | 7 (21%) |
| 4 + 4 | 0 (0%) | 0 (0%) | 0 (0%) |
| Pathological tumour stage | | | |
| pT2 | 6 (67%) | 18 (75%) | 24 (73%) |
| pT3 | 3 (33%) | 6 (25%) | 9 (27%) |
| pT4 | 0 (0%) | 0 (0%) | 0 (0%) |
| Positive lymph nodes | 1/7 (14%) | 0/2 (0%) | 1/9 (11%) |
| Positive margins | 2 (22%) | 2 (9%) | 4 (12%) |
| Duration of postoperative hospital stay (d) | 2.9 (0.3) | 2.0 (0.2)a | 2.3 (0.5) |
| Duration of postoperative catheterization (d) | 10.2 (3.0) | 8.4 (1.6) | 8.9 (2.2) |
| Anastomic structure | 0 (0%) | 1 (4%) | 1 (3%) |
", "tag_len": 414, "cell_len_max": 45, "width": 486, "height": 577, "type": "simple"}, "PMC3765162_003_01.png": {"html": "| | Men (n = 359) | Women (n = 412) |
| | Metabolic syndrome | Metabolic syndrome |
| Baseline characteristics | Yes (n = 163) | No (n = 196) | P value | Yes (n = 96) | No (n = 316) | P value |
| Age (years)* | 61.86 (\u00b10.83) | 60.32 (\u00b10.77) | 0.17 | 64.96 (\u00b10.88) | 58.52 (\u00b10.55) | <0.001 |
| Sitting Systolic BP (mmHg)* | 141.34 (\u00b11.27) | 132.26 (\u00b11.15) | <0.001 | 151.82 (\u00b11.16) | 137.49 (\u00b10.96) | <0.001 |
| Sitting Diastolic BP (mmHg)* | 85.69 (\u00b10.77) | 80.79 (\u00b10.73) | <0.001 | 89.27 (\u00b10.92) | 82.67 (\u00b10.51) | <0.001 |
| Antihypertensive Therapy (%) | 50.9% | 28.4% | <0.001 | 60.4% | 29.4% | <0.001 |
| Total Cholesterol (mmol/L)* | 5.61 (\u00b10.08) | 5.70 (\u00b10.08) | 0.56 | 6.04 (\u00b10.1) | 5.99 (\u00b10.06) | 0.67 |
| LDL cholesterol (mmol/L)* | 3.44 (\u00b10.06) | 3.49 (\u00b10.06) | 0.52 | 3.58 (\u00b1 0.06) | 3.54 (\u00b1 0.04) | 0.66 |
| HDL cholesterol (mmol/L)* | 1.03 (\u00b10.63) | 1.27 (\u00b10.02) | <0.001 | 1.20 (\u00b1 0.02) | 1.48 (\u00b10.016) | <0.001 |
| Triglycerides (mmol/L)\u2020 | 2.10 (1.63; 2.64) | 1.32 (0.98; 1.57) | <0.001 | 2.15 (1.78; 2.83) | 1.24 (0.97; 1.56) | <0.001 |
| Diabetes mellitus (%) | 30.7% | 6.3% | <0.001 | 33.3% | 2.3% | <0.001 |
| BMI (kg/m2)* | 29.88 (\u00b10.35) | 26.06 (\u00b10.2) | <0.001 | 32.39 (\u00b10.47) | 26.95 (\u00b10.25) | <0.001 |
| ApoA1 (g/L)* | 1.29 (\u00b10.013) | 1.40 (\u00b10.017) | <0.001 | 1.44 (\u00b10.02) | 1.55 (\u00b10.001) | <0.001 |
| ApoB (g/L)* | 1.21 (\u00b10.02) | 1.19 (\u00b10.02) | 0.48 | 1.23 (\u00b10.02) | 1.18 (\u00b10.014) | 0.044 |
| Homa index\u2020 | 2.25(1.15; 4.18) | 0.94(0.51; 1.8) | <0.001 | 2.51 (1.67; 3.86) | 1.14 (0.72; 1.7) | <0.001 |
| IMTccMean (mm)* | 0.79 (\u00b10.15) | 0.76 (\u00b10.12) | 0.084 | 0.77 (\u00b10.16) | 0.69 (\u00b10.13) | <0.001 |
| Sum of total plaque area (mm2)\u2020 | 53 (25; 103) | 42 (10;72) | 0.002 | 16 (1; 44) | 8 (1;32) | 0.01 |
| Sum of plaque area carotids (mm2)\u2020 | 22 (1; 39) | 12 (1; 27.5) | 0.011 | 8.75 (1;25.75) | 1 (1; 19) | 0.013 |
| Sum of plaque area femoral (mm2)\u2020 | 33(10; 62) | 23(1; 49) | 0.011 | 1(1; 17.75) | 1(1; 6) | 0.012 |
", "tag_len": 316, "cell_len_max": 42, "width": 486, "height": 282, "type": "complex"}, "PMC5303243_003_00.png": {"html": "| Characteristics | Total (N = 613) | MSSA(N = 508) | MRSA (N = 105) | OR (95%CI) | P-value |
| Age (years)(median, quartiles) | 72 (66;79) | 75 (67;81) | 72 (65;78) | N/A | 0.0048 |
| Gender: | Female | 322 (100.0) | 214 (82.3) | 57 (17.7) | 1.4 (0.93\u20132.16) | 0.5909 |
| Male | 291 (100.0) | 255 (83.5) | 48 (16.5) |
| Step aging n (%) | 0,0849 |
| Young Old | 311 (100.0) | 267 (85.9) | 44 (14.1) | 1.5 (1.00\u20132.35) |
| Old Old | 272 (100.0) | 219 (80.5) | 53 (19.5) | 0.7 (0.49\u20131.13) |
| Longevity | 30 (100.0) | 22 (73.3) | 8 (26.7) | 0.6 (0.24\u20131.27) |
| Disease n (%) | <0.0001 |
| PNU | 47 (100.0) | 28 (59.6) | 19 (40.4) | 0.3 (0.14\u20130.49) |
| BSI | 37 (100.0) | 27 (73.0) | 10 (27.0) | 0.5 (0.25\u20131.14) |
| SSTI | 416 (100.0) | 350 (84.1) | 66 (15.9) | 1.3 (0.85\u20132.03) |
| EI | 62 (100.0) | 56 (90.3) | 6 (9.7) | 1.7 (0.72\u20134.06) |
| Others | 51 (100.0) | 47 (92.2) | 4 (7.8) | 2.6 (0.91\u20137.31) |
| Place of the treatment infections n (%) | 0.0033 |
| INPATIENTS | 430 (100.0) | 352 (81.4) | 78 (18.1) | 0.8 (0.49\u20131.26) |
| LTCF | 16 (100.0) | 9 (56.3) | 7 (43.8) | 0.3 (0.09\u20130.69) |
| OUTPATIENTS | 167 (100.0) | 147 (88.0) | 20 (12.0) | 1.7 (1.03\u20132.92) |
| Infections treated in hospitals (INPATIENTS N = 430, n (%)) |
| ICU | 19 (100.0) | 12 (63.2) | 7 (36.8) | 2.8 (1.06\u20137.34) | 0.014 |
| non-ICU | 411 (100.0) | 340 (82.7) | 71 (17.3) |
", "tag_len": 290, "cell_len_max": 63, "width": 486, "height": 316, "type": "complex"}, "PMC4969833_016_01.png": {"html": " | Horizontal | Normal | Vertical | Total Object |
| Horizontal | 38 | 3 | 5 | 46 (83%) |
| Normal | 1 | 54 | 7 | 62 (87%) |
| Vertical | 2 | 21 | 1140 | 1163 (98%) |
", "tag_len": 52, "cell_len_max": 14, "width": 264, "height": 58, "type": "simple"}}
--------------------------------------------------------------------------------
/src/sample_pred.json:
--------------------------------------------------------------------------------
1 | {"PMC2094709_004_00.png": "\n \n \n \n \n \n \n | Week | Duration (min) | Intensity (% HRR) | Intensity (RPE) |
| 1 | 20 | 50 \u2013 60 | 9 \u2013 11 |
| 2 | 20 | 50 \u2013 60 | 9 \u2013 11 |
| 3 \u2013 5 | 25 | 60 \u2013 70 | 11 |
| 6 \u2013 8 | 30 | 60 \u2013 70 | 11 |
| 9 \u2013 11 | 30 | 70 \u2013 80 | 11 \u2013 13 |
| 12 \u2013 14 | 35 | 70 \u2013 80 | 11 \u2013 13 |
| 15 & 16 | 40 | 75 \u2013 85 | 13 \u2013 15 |
\n
\n \n ", "PMC2871264_002_00.png": "\n \n \n \n \n \n \n | Name of algorithm | Notable features |
| MACS [23] | Uses both a control library and local statistics to minimize bias |
| SICER [14] | Designed for detecting diffusely enriched regions; for example, histone modification |
| PeakSeq [24] | Corrects for reference genome mappability and local statistics |
| SISSRs [25] | High resolution, precise identification of binding-site location |
| F-seq [26] | Uses kernel density estimation |
\n
\n \n ", "PMC2915972_003_00.png": "\n \n \n \n \n \n \n | | No of patients |
| Gender: | |
| Men | 24 |
| Women | 26 |
| Age (years): | |
| 30-39 | 2 |
| 40-49 | 8 |
| 50-59 | 15 |
| 60-69 | 16 |
| 70-79 | 6 |
| \u2265 80 | 3 |
| Tumor site: | |
| Bladder | 4 |
| Breast | 10 |
| Colorectal | 4 |
| Exophageal | 9 |
| Gynecological | 7 |
| Lung | 6 |
| Prostate | 10 |
| Length of interval between baseline and follow-up interview (median) | |
| < 50 days | 22 |
| \u2265 50 days | 28 |
\n
\n \n ", "PMC3160368_005_00.png": "\n \n \n \n \n \n \n | Methods (n-mers used) | Average Sensitivity of 5-fold cross validation (%) | Average Specificity of 5-fold cross validation (%) |
| FDAFSA (hexamers) | 84* | 86* |
| PromMachine (tetramers) | 86+ | 81+ |
\n
\n \n ", "PMC3568059_003_00.png": "\n \n \n \n \n \n \n | | Participants during the period; |
| | 0 to 3 months | 3 to 6 months | 6 to 12 months |
| Characteristics | n=72 | n=71 | n=65 |
| Age, years, median (range) | 73 (50\u201394) | 73 (47\u201392) | 73 (47\u201390) |
| Patients, n (%) | | | |
| Female | 33 (46) | 27 (38) | 26 (40) |
| Male | 39 (54) | 44 (62) | 39 (60) |
| Stroke classification (TOAST), n (%) | | | |
| Large vessel disease | 17 (24) | 18 (25) | 17 (26) |
| Small vessel disease | 21 (29) | 21 (30) | 17 (26) |
| Cardioembolic stroke | 15 (21) | 11 (15) | 11 (17) |
| Cryptogenic stroke | 13 (18) | 14 (20) | 12 (19) |
| Intracerebral haemorrhage | 6 (8) | 7 (10) | 8 (12) |
| Side of feision, n (%) | | | |
| Right side lesion | 35 (49) | 32 (45) | 28 (43) |
| Left side lesion | 37 (51) | 39 (53) | 37 (57) |
| Hypertension | 47 (65) | 44 (62) | 41 (63) |
| Diabetes mellitus | 17 (24) | 18 (25) | 17 (26) |
| Results from clinical scales 1\u20137 days after stroke onset | | | |
| BBS median (range) (n) | 35 (0\u201356) (n=71) | 41 (0\u201356) (n=70) | 41 (0\u201356) (n=46) |
| M-MAS UAS-IS median (range) | 45 (12\u201355) (n=65) | 47 (12\u201355) (n=65) | 50 (16\u201355) (n=56) |
\n
\n \n ", "PMC3707453_006_00.png": "\n \n \n \n \n \n \n | Star Magnitude 1 | Star Magnitude 6 | Saturation Charge [%] | Capacitanc e Linearity [%] |
| Noise (g) | SN at 10 | Signal (g) | Noise (g) | SN at 10 No AD [d] |
| 121200 | 498 | 47 | 1882 | 358 | 10 | 50000 | 99.2 |
| 143960 | 426 | 50 | 1610 | 199 | 13 | 272232 | 98.6 |
| 155220 | 418 | 50 | 1713 | 147 | 19 | 197109 | 98.1 |
| 159950 | 418 | 50 | 1759 | 130 | 19 | 172018 | 97.8 |
| 162400 | 419 | 50 | 1784 | 122 | 19 | 159575 | 97.6 |
| 164550 | 420 | 50 | 180 | 115 | 19 | 149254 | 97.5 |
\n
\n \n ", "PMC3765162_003_01.png": "\n \n \n \n \n \n \n | | Men (n = 359) | Women (n = 412) |
| | Metabolic syndrome | Metabolic syndrome |
| Baseline characteristics | Yes (n = 163) | No (n = 196) | P-value | Yes (n = 96) | No (n = 316) | P value |
| Age (years)* | 61.86 (\u00b10.83) | 60.32 (\u00b10.77) | 0.17 | 64.96 (\u00b10.88) | 58.52 (\u00b10.55) | <0.001 |
| Sitting Systolic BP (mmHg)* | 141.34 (\u00b11.27) | 132.26 (\u00b11.15) | <0.001 | 151.82 (\u00b11.16) | 137.4( (\u00b10.96) | <0.001 |
| Stitting Diastolic BP (mmHg)* | 85.69 (\u00b10.77) | 80.79 (\u00b10.73) | <0.001 | 89.27 (\u00b10.92) | 82.67 (\u00b10.51) | <0.001 |
| Antitypertensive Therapy (%) | 50.9% | 28.4% | <0.001 | 60.4% | 29.4% | <0.001 |
| Total Cholesterol (mmol/L)* | 5.61 (\u00b10.08) | 5.70 (\u00b10.08) | 0.56 | 6.04 (\u00b10.1) | 5.99 (\u00b10.06) | 0.67 |
| LDL cholesterol (mmol/L)* | 3.44 (\u00b10.06) | 3.49 (\u00b10.06) | 0.52 | 3.58 (\u00b1 0.06) | 3.54 (\u00b1 0.04) | 0.66 |
| HDL cholesterol (mmol/L)* | 1.03 (\u00b10.63) | 1.27 (\u00b10.02) | <0.001 | 1.20 (\u00b1 0.02) | 1.48 (\u00b10.016) | <0.001 |
| Triglycerides (mmol/L)* | 2.10 (1.63; 2.64) | 1.32 (0.98; 1.57) | <0.001 | 2.15 (1.78; 2.83) | 1.24 (0.97; 1.56) | <0.001 |
| Diabetes mellitus (%) | 30.7% | 6.3% | <0.001 | 33.3% | 2.3% | <0.001 |
| BMI (kg/m2)* | 29.88 (\u00b10.35) | 26.06 (\u00b10.2) | <0.001 | 22.39 (\u00b10.47) | 26.95 (\u00b10.25) | <0.001 |
| ApoA1 Ig/L* | 1.29 (\u00b10.013) | 1.40 (\u00b10.017) | <0.001 | 1.44 (\u00b10.02) | 1.55 (\u00b10.001) | <0.001 |
| ApoB (g/L)* | 1.21 (\u00b10.02) | 1.19 (\u00b10.02) | 0.48 | 1.23 (\u00b10.02) | 1.18 (\u00b10.014) | 0.044 |
| Homa index* | 2.25(1.15; 4.18) | 0.94(0.51; 1.8) | <0.001 | 2.51 (1.67, 3.86) | 1.14 (0.72; 1.7) | <0.001 |
| MITCoffean (mm)* | 0.79 (\u00b10.15) | 0.76 (\u00b10.12) | 0.084 | 0.77 (\u00b10.16) | 0.69 (\u00b10.13) | <0.001 |
| Sum of total plaque area (mm2)* | 53 (25; 100) | 42 (10/27) | 0.002 | 16 (1; 44) | 8 (1;32) | 0.01 |
| Sum of plaque area carotids (mm2)* | 22 (1; 39) | 12 (1; 27.5) | 0.011 | 8.75 (1.25.75) | 1 (1; 19) | 0.013 |
| Sum of plaque area femoral (mm3)* | 33(10 6,0) | 23(1, 49) | 0.011 | 10 (-17.75) | 1(1; 6) | 0.012 |
\n
\n \n ", "PMC3872294_001_00.png": "\n \n \n \n \n \n \n | HC (N = 20) | FASD (N = 15) |
| Age (years) | 16.3 (2.1) | 15.3 (2.1) |
| IQ | 108 (15)* | 80 (15)* |
| Male/female (%male) | 12/8 (60%) | 10/5 (67%) |
| FASD sub diagnosis | \u2013 | 8 FAS, 7 ARND |
\n
\n \n ", "PMC4196076_004_00.png": "\n \n \n \n \n \n \n | miRNA | Change relative to controls | Direction of regulation | Chromosome | miRNA | Change relative to controls | Direction of regulation | Chromosome |
| hsa-miR-1181 | 2.13 | Up | 19 | hsa-miR-874 | 2.97 | Up | 5 |
| hsa-miR-125a-5p | 5.04 | Up | 19 | hsa-miR-890 | 2.83 | Up | X |
| hsa-miR-21-3p | 2.82 | Up | 17 | hsa-miR-939 | 2.59 | Up | 8 |
| hsa-miR-29b-1-pp | 3.12 | Up | 7 | hsa-miR-1290 | \u22127.56 | Down | 1 |
| hsa-miR-3665-3p | 2.19 | Up | 10 | hsa-miR-191-3-p | \u22122.63 | Down | 10 |
| hsa-miR-1327-5p | 2.01 | Up | 2 | hsa-miR-2861 | \u22123.31 | Down | 9 |
| hsa-miR-3665-3p | 2.03 | Up | 10 | hsa-miR-3665 | \u22122.37 | Down | 13 |
| hsa-miR-371a-5p | 3.14 | Up | 19 | hsa-miR-4357 | \u22123.62 | Down | 1 |
| hsa-miR-4327 | 2.95 | Up | 21 | hsa-miR-452-5p | \u22122.54 | Down | X |
| hsa-miR-584-5p | 2.31 | Up | 5 | hsa-miR-513a-5p | \u22123.15 | Down | X |
| hsa-miR-602 | 5.74 | Up | 9 | hsa-miR-572 | \u22125.80 | Down | 4 |
| hsa-miR-629-3p | 2.71 | Up | 15 | hsa-miR-629-3p | \u22123.03 | Down | 15 |
| hsa-miR-642b-3p | 2.10 | Up | 19 | hsa-miR-165 | \u22127.18 | Down | 1 |
| hsa-miR-651 | 3.91 | Up | X | hsa-miR-875-5p | \u22123.91 | Down | 8 |
| hsa-miR-762 | 2.84 | Up | 16 | hsa-miR-940 | \u22122.31 | Down | 16 |
\n
\n \n ", "PMC4219599_004_00.png": "\n \n \n \n \n \n \n | SBE (n = 24) | MEA 7n = 24 | Evele N = 24 |
| Ethnopositive data |
| Age (yrs) | 0.1 (0) | 0.1 (0) | 43.9 (8) |
| Male (%) | 0.3 (0.0) | 0.1 (0.0) | 8.1 (10%) |
| Married | 0.1 (0.9) | 0.9 (0%) | 8.9 (11) |
| Married | 29.6 (4.3) | 27.0 (0.0) | 27.9 (161) |
| Preventions Fathers |
| 1 + 1 | 1.0 (1%) | 5 (21%) | 5.2 (2.8) |
| 1 + 1 | 5 (5.9%) | 1 (1.9%) | 8 (18%) |
| 4 + 1 | 5 (5.9%) | 11 (5%) | 21 (69%) |
| 4 + 1 | 3 (33%) | 1 (4%) | 3 (19%) |
| 41 + 1 | 0 (0%) | 1 (4%) | 1 (1%) |
| Others increase stage |
| CT1 | 4 (6.4%) | 11 (54%) | 11 (52%) |
| -71 | 5 (5%) | 0 (0%) | 0 (0%) |
| CT2 | 5 (5%) | 0 (0%) | 0 (0%) |
| Private wound with schools | 0 (0%) | 0 (0%) | 0 (0%) |
| Non-sensitive factors | 40.2 (11.4) | 41.2 (13.3) | 45.0 (12.0) |
| Non-sensitive factors |
| None | 1 (11%) | 1 (13%) | 6 (18%) |
| None | 2 (2.9%) | 2 (9%) | 4 (1.7%) |
| None | 2 (2.9%) | 0 (0%) | 4 (1.9%) |
| Total survivor | 0 (0%) | 0 (0%) | 0 (0%) |
| Primary experience | 8 (9%) | 23 (80%)* | 0.0 (0%) |
| Postoperative followsors |
| 1 + 0 | 1 (11%) | 1 (13%) | 4 (12%) |
| 1 + 0 | 6 (6.7%) | 15 (57%) | 21 (61%) |
| 4 + 1 | 2 (2%) | 5 (37%) | 2 (2%) |
| 4 + 1 | 8 (29%) | 8 (29%) | 0 (0%) |
| Pathological survour stage |
| PT3 | 8 (37%) | 16 (39%) | 24 (17%) |
| PT3 | 8 (37%) | 6 (3%) | 5 (17%) |
| PT3 | 0 (0%) | 6 (3%) | 4 (3%) |
| Positive | 17 (14%) | 6 (3%) | 1 (0.1%) |
| Positive nempl nodes | 17 (14%) | 0.9 (0%) | 1.0 (1%) |
| Positive reference in complete hospital stay (n) | 2.0 (0.4) | 2.0 (0.2) | 2.2 (0.3) |
| Position of pressoreation compression (%) | 10.5 (10) | 4.4 (14) | 8.9 (2.2) |
| Duration of pressoreation collectivation (%) | 10.5 (10) | 8.4 (14) | 8.9 (9.2) |
\n
\n \n ", "PMC4297392_007_00.png": "\n \n \n \n \n \n \n | Treatment phase | Adverse event | No. of patients |
| T1 | Swelling | 1 |
| | Itching | 1 |
| | Fever | 4 |
| | Throat infection | 1 |
| | Chest Congestion | 2 |
| | Total | 9 |
| T2 | Diarrhea | 1 |
| | Body Pain | 1 |
| | Total | 2 |
| T3 | Diarrhea | 1 |
| | Total | 1 |
| T4 | Nil | - |
\n
\n \n ", "PMC4311460_007_00.png": "\n \n \n \n \n \n \n | | | | Number | | Patients | Patients |
| Category | Type | | CHP | % | (N = 4,560) | % |
| I | Inflammation | | 6,987 | 11.3 | 3,537 | 77.6 |
| II | Infection | | 3,629 | 5.9 | 2,451 | 53.8 |
| III | Injury | | 5,556 | 9.0 | 3,401 | 74.6 |
| IV | Specific conditions | | 32,016 | 51.9 | n.c. | |
| V | Neoplasms | | 3,592 | 5.8 | 2,461# | 54 |
| | | Maligne | | | | 1,219 (27%) |
| | | O,ther-benign | 2,148 | | | 1,758 (39%) |
| VI | Congenital | | 490 | 0.8 | n.c. | |
| VII | Otherwise | | 9,383 | 15.2 | n.c. | |
| Total | ALL-types | | | 100 | | |
\n
\n \n ", "PMC4357206_002_00.png": "\n \n \n \n \n \n \n | | N = 121 |
| Demographics | |
| Age (yr) - median (IQR) | 62 (56-73) |
| Female sex (%) | 46 (38) |
| White race (%) | 112 (93) |
| Comorbidities (%) | |
| Hypertension | 64 (53) |
| Chronic lung disease | 37 (31) |
| Active malignancy | 34 (28) |
| Diabetes mellitus | 29 (24) |
| Chronic kidney disease | 7 (6) |
| Congestive heart failure | 4 (3) |
| Chronic liver disease | 2 (2) |
| Severity of illness | |
| APACHE II score - median (IQR)* | 14 (10-16) |
| Chanlson Comorbidity Index - median (IQR)\u2020 | 2 (1-4) |
| ICU type | |
| Surgical | 102 (84) |
| SICU | 66 (54) |
| TICU | 36 (30) |
| Nonsurgical | 19 (16) |
| CCU | 11 (9) |
| MICU | 8 (7) |
| Status of procedure (for surgical patients) (%) | |
| Elective | 41 (34) |
| Urgent | 57 (47) |
| Dops in hospital prior to enrollment \u2013 median (IQR) | 1 (1-3) |
\n
\n \n ", "PMC4445578_009_01.png": "\n \n \n \n \n \n \n | Reactive astroglioss | Changes in astrocytes morphology | Changes in molecules expression |
| Upregulated molecules | Upregulated or downregulated molecules |
| Mild to moderate astroglosis | \u2022 Hypertrophy of cell body | \u2022 Structural elements GFAP, nestin, virenetin | \u2022 Inflammatory cell regulators, cytokines, growth factors, glutathione |
| \u2022 Astrocytes processes are are numeroca and thicker | \u2022 Transcriptional regulators STAT3, NFASI (Pechem 1076, cAnP6 Chiga, SOX9 [61-65]. | Trassopteres and purprs; AQP4 and No YK+ transporters [26,64-69] |
| | | \u2022 Glutamate transporter [76-73] |
| \u2022 The non-overlapping domains of individual astrocytes are preserved | | \u2022 Vascular regulators: PGE, NO [74,75] |
| | | \u2022 Energy provision: lactate [76] |
| | | \u2022 Molecules implicated in synapse formation and |
| | | \u2022 Remodeling thrombospondin and Complement C1q [77,78] |
| - Significant extension of processes | | \u2022 Molecules implicated in ovidative stress, and providing protection from oxidative stress: NO, NOS, SOX, Glutathione [67,68,79] |
| \u2022 Proliferation | | |
| \u2022 Overlapping of individual domains | | |
| \u2022 Substantial reorganization of tissue activitecute [50] | | |
\n
\n \n ", "PMC4969833_016_01.png": "\n \n \n \n \n \n \n | Horizontal | Normal | Vertical | Total Object |
| Horizontal | 38 | 3 | 5 | 46 (83%) |
| Normal | 1 | 54 | 7 | 62 (87%) |
| Vertical | 2 | 21 | 1140 | 1163 (98%) |
\n
\n \n ", "PMC5303243_003_00.png": "\n \n \n \n \n \n \n | Characteristics | Total (N = 613) | MSSA (N = 508) | MRSA (N = 105) | OR (95%CI) | P-value |
| Age (years) (median, quartiles) | 72 (66,79) | 75 (6731) | 72 (67,78) | N/A | 0.0048 |
| Gender | 322 (100.0) | 214 (82.3) | 57 (17.7) | 1.4 (0.93\u20132.16) | 0.5909 |
| Male | 291 (100.0) | 255 (83.5) | 48 (16.5) | | |
| Step aging n (%) | | | | | 0,0849 |
| Young Old | 311 (100.0) | 267 (85.9) | 44 (14.1) | 1.5 (1.00\u20132.35) | |
| O6: O& | 272 (100.0) | 219 (80.5) | 53 (19.5) | 0.7 (0.49\u20131.13) | |
| Longevity | 30 (100.0) | 22 (73.3) | 8 (26.7) | 0.6 (0.24\u20131.27) | |
| Disease n (%) | | | | | <0.0001 |
| PNU | 47 (100.0) | 28 (59.6) | 19 (40.4) | 0.3 (0.14\u20130.49) | |
| BSI | 37 (100.0) | 27 (73.0) | 10 (27.0) | 0.5 (0.25\u20131.14) | |
| SSTI | 416 (100.0) | 350 (84.1) | 66 (15.9) | 1.3 (0.85\u20132.03) | |
| EI | 62 (100.0) | 56 (90.3) | 6 (9.7) | 1.7 (0.72\u20134.06) | |
| Others | 51 (100.0) | 47 (92.2) | 4 (7.8) | 2.6 (0.91\u20137.31) | |
| Place of the treatment infections n (%) | | | | | 0.0033 |
| INPATBENTS | 430 (100.0) | 352 (81.4) | 78 (18.1) | 0.8 (0.49\u20131.26) | |
| LTCF | 16 (100.0) | 9 (56.3) | 7 (43.8) | 0.3 (0.09\u20130.69) | |
| OUTPATIENTS | 167 (100.0) | 147 (88.0) | 20 (12.0) | 1.7 (1.03\u20132.92) | |
| Infections treated in hospitals (NPATIENTS N = 430, n (%)) |
| ICU | 19 (100.0) | 12 (63.2) | 7 (36.8) | 2.8 (1.06\u20137.34) | 0.014 |
| non-ICU | 411 (100.0) | 340 (82.7) | 71 (17.3) | | |
\n
\n \n ", "PMC5451934_004_00.png": "\n \n \n \n \n \n \n | Condition | Pre Well-Being | Post Well-Being | Pre-Post-Change |
| TP (handler & dog interaction) | 46.33 \u00b1 7.41 1 | 48.69 \u00b1 7.22 | +2.36 |
| DO (dog only interaction) | 49.78 \u00b1 7.91 | 51.56 \u00b1 6.99 | +1.78 ** |
| HO (handler only interaction) | 47.37 \u00b1 7.57 | 46.43 \u00b1 8.03 | \u22120.94 ** |
\n
\n \n ", "PMC5755158_010_01.png": "\n \n \n \n \n \n \n | Weaning | Week 15 | Off-test |
| Weaning | \u2013 | \u2013 | \u2013 |
| Week 15 | \u2013 | 0.17 \u00b1 0.08 | 0.16 \u00b1 0.03 |
| Off-test | \u2013 | 0.80 \u00b1 0.24 | 0.19 \u00b1 0.09 |
\n
\n \n ", "PMC5849724_006_00.png": "\n \n \n \n \n \n \n | Analytes | GC-HRMS | GC-MS/MS | GC-MS |
| LOQ (ng/CIPP) | Estimated LOQ, (ng/cig) | LOQ, (ng/CPP) | Estimated LOQ, (ng/cig) | LOQ (ng/CIPP) | Estimated LOQ, (ng/cig) |
| Naphthalene | 0.51 | 0.026 | 1178.71 | 58.94 | 108.17 | 5.41 |
| Benzolylphenamthene | 0.04 | 0.002 | ND | ND | 66.80 | 3.34 |
| Benzolylanthracene | 0.03 | 0.002 | 38.57 | 1.93 | 38.11 | 1.91 |
| Chrysene | 0.04 | 0.002 | 50.13 | 2.51 | 49.61 | 2.48 |
| Cyclopentid,culysyner | 0.02 | 0.001 | 48.84 | 2.44 | 60.04 | 3.00 |
| S-Methylchrysene | 0.04 | 0.002 | ND | ND | 2.48 | 0.12 |
| Benzo[p]Iluonarthene | 0.04 | 0.002 | 11.44 | 0.57 | 5.08 | 0.25 |
| Benzol[Illicuranthene | 0.05 | 0.003 | 12.41 | 0.62 | 5.07 | 0.25 |
| Benzo[[aceanthrylene] | 0.09 | 0.005 | ND | ND | ND | ND |
| Benzoliglyreene | 0.04 | 0.002 | 5.01 | 0.25 | 3.03 | 0.15 |
| Indeno(1,2,1-cultypnee | 0.02 | 0.001 | 5.46 | 0.27 | 1.54 | 0.08 |
| Dibenodju/lipinthe cere | 0.07 | 0.004 | 0.83 | 0.04 | 1.48 | 0.07 |
| Dibenzolip/lyprene | 0.05 | 0.003 | ND | ND | ND | ND |
| Dibenzolyadyprene | 0.04 | 0.002 | 0.80 | 0.04 | 0.28 | 0.01 |
| Dibenzolyuloyene | 0.06 | 0.003 | 1.33 | 0.07 | ND | ND |
| Dibenzolya/hyperene | 0.07 | 0.004 | 2.99 | 0.15 | ND | ND |
\n
\n \n ", "PMC6022086_007_00.png": "\n \n \n \n \n \n \n | Method | Data Type | Mean (m) | RMSE (m) | P90% (m) | PGSD (%) |
| Improved FCM | Gaofen-3 | 5.77 | 5.89 | 10.07 | 94.37 |
| Sentinel-1 | 6.30 | 5.83 | 14.03 | 80.00 |
| Original FCM | Gaofen-3 | 6.97 | 7.66 | 13.87 | 90.70 |
| Sentinel-1 | 8.53 | 4.81 | 13.14 | 90.00 |
\n
\n \n "}
--------------------------------------------------------------------------------
/exploring_PubTabNet_dataset.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "metadata": {
6 | "collapsed": true
7 | },
8 | "source": [
9 | "# PubTabNet Dataset\n",
10 | "\n",
11 | "PubTabNet is a large dataset for image-based table recognition, containing 568k+ images of tabular data annotated with the corresponding HTML representation of the tables.\n",
12 | " \n",
13 | "The dataset is open sourced by IBM Research Australia and is [available to download freely](https://developer.ibm.com/exchanges/data/all/pubtabnet/) on the IBM Developer [Data Asset Exchange](http://ibm.biz/data-exchange). \n",
14 | "\n",
15 | "This notebook can be found on [GitHub](https://github.com/ibm-aur-nlp/PubTabNet) and [Watson Studio](https://dataplatform.cloud.ibm.com/analytics/notebooks/v2/0aa641b0-af25-4470-b9e1-6b33d6b5b66a/view?access_token=b7d5880bb60c253457a72e3ec76f9ab40ccc42c607331acdcbbbe21be4c46bc8)."
16 | ]
17 | },
18 | {
19 | "cell_type": "code",
20 | "execution_count": 25,
21 | "metadata": {},
22 | "outputs": [],
23 | "source": [
24 | "# importing prerequisites\n",
25 | "import sys\n",
26 | "import requests\n",
27 | "import tarfile\n",
28 | "import jsonlines\n",
29 | "import numpy as np\n",
30 | "from os import path\n",
31 | "from PIL import Image\n",
32 | "from PIL import ImageFont, ImageDraw\n",
33 | "from glob import glob\n",
34 | "from matplotlib import pyplot as plt\n",
35 | "%matplotlib inline"
36 | ]
37 | },
38 | {
39 | "cell_type": "markdown",
40 | "metadata": {},
41 | "source": [
42 | "## Download and Extract the Dataset\n",
43 | "\n",
44 | "Since the dataset is large (~12GB), here we will be downloading a small subset of the data and extract it. "
45 | ]
46 | },
47 | {
48 | "cell_type": "code",
49 | "execution_count": 26,
50 | "metadata": {},
51 | "outputs": [
52 | {
53 | "data": {
54 | "text/plain": [
55 | "376695"
56 | ]
57 | },
58 | "execution_count": 26,
59 | "metadata": {},
60 | "output_type": "execute_result"
61 | }
62 | ],
63 | "source": [
64 | "fname = 'examples.tar.gz'\n",
65 | "url = 'https://dax-cdn.cdn.appdomain.cloud/dax-pubtabnet/2.0.0/' + fname\n",
66 | "r = requests.get(url)\n",
67 | "open(fname , 'wb').write(r.content)"
68 | ]
69 | },
70 | {
71 | "cell_type": "code",
72 | "execution_count": 27,
73 | "metadata": {},
74 | "outputs": [],
75 | "source": [
76 | "# Extracting the dataset\n",
77 | "tar = tarfile.open(fname)\n",
78 | "tar.extractall()\n",
79 | "tar.close()"
80 | ]
81 | },
82 | {
83 | "cell_type": "code",
84 | "execution_count": 28,
85 | "metadata": {},
86 | "outputs": [
87 | {
88 | "data": {
89 | "text/plain": [
90 | "True"
91 | ]
92 | },
93 | "execution_count": 28,
94 | "metadata": {},
95 | "output_type": "execute_result"
96 | }
97 | ],
98 | "source": [
99 | "# Verifying the file was extracted properly\n",
100 | "data_path = \"examples/\"\n",
101 | "path.exists(data_path)"
102 | ]
103 | },
104 | {
105 | "cell_type": "markdown",
106 | "metadata": {},
107 | "source": [
108 | "## Visualizing the Data\n",
109 | "\n",
110 | "In this section, we visualize the raw image and extract it's HTML annotation from the JSON file. \n",
111 | "We further render the table using Jupyter notebook's inbuilt HTML capabilities. "
112 | ]
113 | },
114 | {
115 | "cell_type": "code",
116 | "execution_count": 29,
117 | "metadata": {},
118 | "outputs": [],
119 | "source": [
120 | "# Helper function to read in tables from the annotations\n",
121 | "from bs4 import BeautifulSoup as bs\n",
122 | "from html import escape\n",
123 | "\n",
124 | "def format_html(img):\n",
125 | " ''' Formats HTML code from tokenized annotation of img\n",
126 | " '''\n",
127 | " html_code = img['html']['structure']['tokens'].copy()\n",
128 | " to_insert = [i for i, tag in enumerate(html_code) if tag in ('', '>')]\n",
129 | " for i, cell in zip(to_insert[::-1], img['html']['cells'][::-1]):\n",
130 | " if cell['tokens']:\n",
131 | " cell = [escape(token) if len(token) == 1 else token for token in cell['tokens']]\n",
132 | " cell = ''.join(cell)\n",
133 | " html_code.insert(i + 1, cell)\n",
134 | " html_code = ''.join(html_code)\n",
135 | " html_code = '''\n",
136 | " \n",
137 | " \n",
138 | " \n",
144 | " \n",
145 | " \n",
146 | " \n",
147 | " %s\n",
148 | " \n",
149 | " \n",
150 | " ''' % html_code\n",
151 | "\n",
152 | " # prettify the html\n",
153 | " soup = bs(html_code)\n",
154 | " html_code = soup.prettify()\n",
155 | " return html_code"
156 | ]
157 | },
158 | {
159 | "cell_type": "code",
160 | "execution_count": 40,
161 | "metadata": {
162 | "scrolled": true
163 | },
164 | "outputs": [],
165 | "source": [
166 | "# Loading an example annotation\n",
167 | "with jsonlines.open('examples/PubTabNet_Examples.jsonl', 'r') as reader:\n",
168 | " img = list(reader)[0]"
169 | ]
170 | },
171 | {
172 | "cell_type": "code",
173 | "execution_count": 41,
174 | "metadata": {},
175 | "outputs": [
176 | {
177 | "data": {
178 | "image/png": "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\n",
179 | "text/plain": [
180 | ""
181 | ]
182 | },
183 | "execution_count": 41,
184 | "metadata": {},
185 | "output_type": "execute_result"
186 | }
187 | ],
188 | "source": [
189 | "# Showing the raw image\n",
190 | "from IPython.display import Image as displayImage\n",
191 | "filename = img['filename']\n",
192 | "displayImage(\"examples/\"+filename)"
193 | ]
194 | },
195 | {
196 | "cell_type": "code",
197 | "execution_count": 42,
198 | "metadata": {},
199 | "outputs": [
200 | {
201 | "name": "stdout",
202 | "output_type": "stream",
203 | "text": [
204 | "\n",
205 | " \n",
206 | " \n",
207 | " \n",
213 | " \n",
214 | " \n",
215 | " \n",
216 | " \n",
217 | " \n",
218 | " | \n",
219 | " \n",
220 | " Variable\n",
221 | " \n",
222 | " | \n",
223 | " \n",
224 | " \n",
225 | " Hazard ratio\n",
226 | " \n",
227 | " | \n",
228 | " \n",
229 | " \n",
230 | " 95 % CI\n",
231 | " \n",
232 | " | \n",
233 | " \n",
234 | " \n",
235 | " \n",
236 | " p\n",
237 | " \n",
238 | " value*\n",
239 | " \n",
240 | " | \n",
241 | " \n",
242 | " \n",
243 | " \n",
244 | " \n",
245 | " | \n",
246 | " Age (median)\n",
247 | " | \n",
248 | " \n",
249 | " | \n",
250 | " \n",
251 | " | \n",
252 | " \n",
253 | " 0.716\n",
254 | " | \n",
255 | " \n",
256 | " \n",
257 | " | \n",
258 | " ≤69\n",
259 | " | \n",
260 | " \n",
261 | " 1.000\n",
262 | " | \n",
263 | " \n",
264 | " | \n",
265 | " \n",
266 | " | \n",
267 | " \n",
268 | " \n",
269 | " | \n",
270 | " >69\n",
271 | " | \n",
272 | " \n",
273 | " 0.839\n",
274 | " | \n",
275 | " \n",
276 | " 0.310–2.268\n",
277 | " | \n",
278 | " \n",
279 | " | \n",
280 | " \n",
281 | " \n",
282 | " | \n",
283 | " Gender\n",
284 | " | \n",
285 | " \n",
286 | " | \n",
287 | " \n",
288 | " | \n",
289 | " \n",
290 | " 0.142\n",
291 | " | \n",
292 | " \n",
293 | " \n",
294 | " | \n",
295 | " Male\n",
296 | " | \n",
297 | " \n",
298 | " 1.000\n",
299 | " | \n",
300 | " \n",
301 | " | \n",
302 | " \n",
303 | " | \n",
304 | " \n",
305 | " \n",
306 | " | \n",
307 | " Female\n",
308 | " | \n",
309 | " \n",
310 | " 0.426\n",
311 | " | \n",
312 | " \n",
313 | " 0.152–1.190\n",
314 | " | \n",
315 | " \n",
316 | " | \n",
317 | " \n",
318 | " \n",
319 | " | \n",
320 | " Type of surgery\n",
321 | " | \n",
322 | " \n",
323 | " | \n",
324 | " \n",
325 | " | \n",
326 | " \n",
327 | " 0.010\n",
328 | " | \n",
329 | " \n",
330 | " \n",
331 | " | \n",
332 | " Low anterior resection\n",
333 | " | \n",
334 | " \n",
335 | " 1.000\n",
336 | " | \n",
337 | " \n",
338 | " | \n",
339 | " \n",
340 | " | \n",
341 | " \n",
342 | " \n",
343 | " | \n",
344 | " Abdominoperineal resection\n",
345 | " | \n",
346 | " \n",
347 | " 3.140\n",
348 | " | \n",
349 | " \n",
350 | " 0.919–10.725\n",
351 | " | \n",
352 | " \n",
353 | " | \n",
354 | " \n",
355 | " \n",
356 | " | \n",
357 | " Tumor location\n",
358 | " | \n",
359 | " \n",
360 | " | \n",
361 | " \n",
362 | " | \n",
363 | " \n",
364 | " 0.710\n",
365 | " | \n",
366 | " \n",
367 | " \n",
368 | " | \n",
369 | " Upper rectum\n",
370 | " | \n",
371 | " \n",
372 | " 1.000\n",
373 | " | \n",
374 | " \n",
375 | " | \n",
376 | " \n",
377 | " | \n",
378 | " \n",
379 | " \n",
380 | " | \n",
381 | " Middle rectum\n",
382 | " | \n",
383 | " \n",
384 | " 1.267\n",
385 | " | \n",
386 | " \n",
387 | " 0.381–4.213\n",
388 | " | \n",
389 | " \n",
390 | " | \n",
391 | " \n",
392 | " \n",
393 | " | \n",
394 | " Low rectum\n",
395 | " | \n",
396 | " \n",
397 | " 1.716\n",
398 | " | \n",
399 | " \n",
400 | " 0.419–7.026\n",
401 | " | \n",
402 | " \n",
403 | " | \n",
404 | " \n",
405 | " \n",
406 | " | \n",
407 | " Grade of differentiation\n",
408 | " | \n",
409 | " \n",
410 | " | \n",
411 | " \n",
412 | " | \n",
413 | " \n",
414 | " 0.936\n",
415 | " | \n",
416 | " \n",
417 | " \n",
418 | " | \n",
419 | " G1\n",
420 | " | \n",
421 | " \n",
422 | " 1.000\n",
423 | " | \n",
424 | " \n",
425 | " | \n",
426 | " \n",
427 | " | \n",
428 | " \n",
429 | " \n",
430 | " | \n",
431 | " G2\n",
432 | " | \n",
433 | " \n",
434 | " 1.933\n",
435 | " | \n",
436 | " \n",
437 | " 0.416–3.423\n",
438 | " | \n",
439 | " \n",
440 | " | \n",
441 | " \n",
442 | " \n",
443 | " | \n",
444 | " G3\n",
445 | " | \n",
446 | " \n",
447 | " 1.119\n",
448 | " | \n",
449 | " \n",
450 | " 0.137–9.137\n",
451 | " | \n",
452 | " \n",
453 | " | \n",
454 | " \n",
455 | " \n",
456 | " | \n",
457 | " Histologic type\n",
458 | " | \n",
459 | " \n",
460 | " | \n",
461 | " \n",
462 | " | \n",
463 | " \n",
464 | " 0.299\n",
465 | " | \n",
466 | " \n",
467 | " \n",
468 | " | \n",
469 | " Adenocarcinoma\n",
470 | " | \n",
471 | " \n",
472 | " 1.000\n",
473 | " | \n",
474 | " \n",
475 | " | \n",
476 | " \n",
477 | " | \n",
478 | " \n",
479 | " \n",
480 | " | \n",
481 | " Adenocarcinoma with mucinous features\n",
482 | " | \n",
483 | " \n",
484 | " 0.381\n",
485 | " | \n",
486 | " \n",
487 | " 0.096–1.514\n",
488 | " | \n",
489 | " \n",
490 | " | \n",
491 | " \n",
492 | " \n",
493 | " | \n",
494 | " Depth of tumor invasion\n",
495 | " | \n",
496 | " \n",
497 | " | \n",
498 | " \n",
499 | " | \n",
500 | " \n",
501 | " 0.925\n",
502 | " | \n",
503 | " \n",
504 | " \n",
505 | " | \n",
506 | " T3\n",
507 | " | \n",
508 | " \n",
509 | " 1.000\n",
510 | " | \n",
511 | " \n",
512 | " | \n",
513 | " \n",
514 | " | \n",
515 | " \n",
516 | " \n",
517 | " | \n",
518 | " T4a\n",
519 | " | \n",
520 | " \n",
521 | " 0.919\n",
522 | " | \n",
523 | " \n",
524 | " 0.316–2.673\n",
525 | " | \n",
526 | " \n",
527 | " | \n",
528 | " \n",
529 | " \n",
530 | " | \n",
531 | " T4b\n",
532 | " | \n",
533 | " \n",
534 | " 0.745\n",
535 | " | \n",
536 | " \n",
537 | " 0.172–3.223\n",
538 | " | \n",
539 | " \n",
540 | " | \n",
541 | " \n",
542 | " \n",
543 | " | \n",
544 | " Tumor size\n",
545 | " | \n",
546 | " \n",
547 | " | \n",
548 | " \n",
549 | " | \n",
550 | " \n",
551 | " 0.329\n",
552 | " | \n",
553 | " \n",
554 | " \n",
555 | " | \n",
556 | " ≤4 cm\n",
557 | " | \n",
558 | " \n",
559 | " 1.000\n",
560 | " | \n",
561 | " \n",
562 | " | \n",
563 | " \n",
564 | " | \n",
565 | " \n",
566 | " \n",
567 | " | \n",
568 | " >4 cm\n",
569 | " | \n",
570 | " \n",
571 | " 0.594\n",
572 | " | \n",
573 | " \n",
574 | " 0.214–1.651\n",
575 | " | \n",
576 | " \n",
577 | " | \n",
578 | " \n",
579 | " \n",
580 | " \n",
581 | " \n",
582 | "\n"
583 | ]
584 | }
585 | ],
586 | "source": [
587 | "# Extracting the HTML for the table from the annotation\n",
588 | "html_string = format_html(img)\n",
589 | "print(html_string)"
590 | ]
591 | },
592 | {
593 | "cell_type": "code",
594 | "execution_count": 43,
595 | "metadata": {},
596 | "outputs": [
597 | {
598 | "data": {
599 | "text/html": [
600 | "\n",
601 | " \n",
602 | " \n",
603 | " \n",
609 | " \n",
610 | " \n",
611 | " \n",
612 | " \n",
613 | " \n",
614 | " | \n",
615 | " \n",
616 | " Variable\n",
617 | " \n",
618 | " | \n",
619 | " \n",
620 | " \n",
621 | " Hazard ratio\n",
622 | " \n",
623 | " | \n",
624 | " \n",
625 | " \n",
626 | " 95 % CI\n",
627 | " \n",
628 | " | \n",
629 | " \n",
630 | " \n",
631 | " \n",
632 | " p\n",
633 | " \n",
634 | " value*\n",
635 | " \n",
636 | " | \n",
637 | " \n",
638 | " \n",
639 | " \n",
640 | " \n",
641 | " | \n",
642 | " Age (median)\n",
643 | " | \n",
644 | " \n",
645 | " | \n",
646 | " \n",
647 | " | \n",
648 | " \n",
649 | " 0.716\n",
650 | " | \n",
651 | " \n",
652 | " \n",
653 | " | \n",
654 | " ≤69\n",
655 | " | \n",
656 | " \n",
657 | " 1.000\n",
658 | " | \n",
659 | " \n",
660 | " | \n",
661 | " \n",
662 | " | \n",
663 | " \n",
664 | " \n",
665 | " | \n",
666 | " >69\n",
667 | " | \n",
668 | " \n",
669 | " 0.839\n",
670 | " | \n",
671 | " \n",
672 | " 0.310–2.268\n",
673 | " | \n",
674 | " \n",
675 | " | \n",
676 | " \n",
677 | " \n",
678 | " | \n",
679 | " Gender\n",
680 | " | \n",
681 | " \n",
682 | " | \n",
683 | " \n",
684 | " | \n",
685 | " \n",
686 | " 0.142\n",
687 | " | \n",
688 | " \n",
689 | " \n",
690 | " | \n",
691 | " Male\n",
692 | " | \n",
693 | " \n",
694 | " 1.000\n",
695 | " | \n",
696 | " \n",
697 | " | \n",
698 | " \n",
699 | " | \n",
700 | " \n",
701 | " \n",
702 | " | \n",
703 | " Female\n",
704 | " | \n",
705 | " \n",
706 | " 0.426\n",
707 | " | \n",
708 | " \n",
709 | " 0.152–1.190\n",
710 | " | \n",
711 | " \n",
712 | " | \n",
713 | " \n",
714 | " \n",
715 | " | \n",
716 | " Type of surgery\n",
717 | " | \n",
718 | " \n",
719 | " | \n",
720 | " \n",
721 | " | \n",
722 | " \n",
723 | " 0.010\n",
724 | " | \n",
725 | " \n",
726 | " \n",
727 | " | \n",
728 | " Low anterior resection\n",
729 | " | \n",
730 | " \n",
731 | " 1.000\n",
732 | " | \n",
733 | " \n",
734 | " | \n",
735 | " \n",
736 | " | \n",
737 | " \n",
738 | " \n",
739 | " | \n",
740 | " Abdominoperineal resection\n",
741 | " | \n",
742 | " \n",
743 | " 3.140\n",
744 | " | \n",
745 | " \n",
746 | " 0.919–10.725\n",
747 | " | \n",
748 | " \n",
749 | " | \n",
750 | " \n",
751 | " \n",
752 | " | \n",
753 | " Tumor location\n",
754 | " | \n",
755 | " \n",
756 | " | \n",
757 | " \n",
758 | " | \n",
759 | " \n",
760 | " 0.710\n",
761 | " | \n",
762 | " \n",
763 | " \n",
764 | " | \n",
765 | " Upper rectum\n",
766 | " | \n",
767 | " \n",
768 | " 1.000\n",
769 | " | \n",
770 | " \n",
771 | " | \n",
772 | " \n",
773 | " | \n",
774 | " \n",
775 | " \n",
776 | " | \n",
777 | " Middle rectum\n",
778 | " | \n",
779 | " \n",
780 | " 1.267\n",
781 | " | \n",
782 | " \n",
783 | " 0.381–4.213\n",
784 | " | \n",
785 | " \n",
786 | " | \n",
787 | " \n",
788 | " \n",
789 | " | \n",
790 | " Low rectum\n",
791 | " | \n",
792 | " \n",
793 | " 1.716\n",
794 | " | \n",
795 | " \n",
796 | " 0.419–7.026\n",
797 | " | \n",
798 | " \n",
799 | " | \n",
800 | " \n",
801 | " \n",
802 | " | \n",
803 | " Grade of differentiation\n",
804 | " | \n",
805 | " \n",
806 | " | \n",
807 | " \n",
808 | " | \n",
809 | " \n",
810 | " 0.936\n",
811 | " | \n",
812 | " \n",
813 | " \n",
814 | " | \n",
815 | " G1\n",
816 | " | \n",
817 | " \n",
818 | " 1.000\n",
819 | " | \n",
820 | " \n",
821 | " | \n",
822 | " \n",
823 | " | \n",
824 | " \n",
825 | " \n",
826 | " | \n",
827 | " G2\n",
828 | " | \n",
829 | " \n",
830 | " 1.933\n",
831 | " | \n",
832 | " \n",
833 | " 0.416–3.423\n",
834 | " | \n",
835 | " \n",
836 | " | \n",
837 | " \n",
838 | " \n",
839 | " | \n",
840 | " G3\n",
841 | " | \n",
842 | " \n",
843 | " 1.119\n",
844 | " | \n",
845 | " \n",
846 | " 0.137–9.137\n",
847 | " | \n",
848 | " \n",
849 | " | \n",
850 | " \n",
851 | " \n",
852 | " | \n",
853 | " Histologic type\n",
854 | " | \n",
855 | " \n",
856 | " | \n",
857 | " \n",
858 | " | \n",
859 | " \n",
860 | " 0.299\n",
861 | " | \n",
862 | " \n",
863 | " \n",
864 | " | \n",
865 | " Adenocarcinoma\n",
866 | " | \n",
867 | " \n",
868 | " 1.000\n",
869 | " | \n",
870 | " \n",
871 | " | \n",
872 | " \n",
873 | " | \n",
874 | " \n",
875 | " \n",
876 | " | \n",
877 | " Adenocarcinoma with mucinous features\n",
878 | " | \n",
879 | " \n",
880 | " 0.381\n",
881 | " | \n",
882 | " \n",
883 | " 0.096–1.514\n",
884 | " | \n",
885 | " \n",
886 | " | \n",
887 | " \n",
888 | " \n",
889 | " | \n",
890 | " Depth of tumor invasion\n",
891 | " | \n",
892 | " \n",
893 | " | \n",
894 | " \n",
895 | " | \n",
896 | " \n",
897 | " 0.925\n",
898 | " | \n",
899 | " \n",
900 | " \n",
901 | " | \n",
902 | " T3\n",
903 | " | \n",
904 | " \n",
905 | " 1.000\n",
906 | " | \n",
907 | " \n",
908 | " | \n",
909 | " \n",
910 | " | \n",
911 | " \n",
912 | " \n",
913 | " | \n",
914 | " T4a\n",
915 | " | \n",
916 | " \n",
917 | " 0.919\n",
918 | " | \n",
919 | " \n",
920 | " 0.316–2.673\n",
921 | " | \n",
922 | " \n",
923 | " | \n",
924 | " \n",
925 | " \n",
926 | " | \n",
927 | " T4b\n",
928 | " | \n",
929 | " \n",
930 | " 0.745\n",
931 | " | \n",
932 | " \n",
933 | " 0.172–3.223\n",
934 | " | \n",
935 | " \n",
936 | " | \n",
937 | " \n",
938 | " \n",
939 | " | \n",
940 | " Tumor size\n",
941 | " | \n",
942 | " \n",
943 | " | \n",
944 | " \n",
945 | " | \n",
946 | " \n",
947 | " 0.329\n",
948 | " | \n",
949 | " \n",
950 | " \n",
951 | " | \n",
952 | " ≤4 cm\n",
953 | " | \n",
954 | " \n",
955 | " 1.000\n",
956 | " | \n",
957 | " \n",
958 | " | \n",
959 | " \n",
960 | " | \n",
961 | " \n",
962 | " \n",
963 | " | \n",
964 | " >4 cm\n",
965 | " | \n",
966 | " \n",
967 | " 0.594\n",
968 | " | \n",
969 | " \n",
970 | " 0.214–1.651\n",
971 | " | \n",
972 | " \n",
973 | " | \n",
974 | " \n",
975 | " \n",
976 | " \n",
977 | " \n",
978 | ""
979 | ],
980 | "text/plain": [
981 | ""
982 | ]
983 | },
984 | "metadata": {},
985 | "output_type": "display_data"
986 | }
987 | ],
988 | "source": [
989 | "# Rendering the above HTML in Jupyter Notebook for a more readable format\n",
990 | "from IPython.core.display import display, HTML\n",
991 | "display(HTML(html_string))"
992 | ]
993 | }
994 | ],
995 | "metadata": {
996 | "kernelspec": {
997 | "display_name": "Python 3",
998 | "language": "python",
999 | "name": "python3"
1000 | },
1001 | "language_info": {
1002 | "codemirror_mode": {
1003 | "name": "ipython",
1004 | "version": 3
1005 | },
1006 | "file_extension": ".py",
1007 | "mimetype": "text/x-python",
1008 | "name": "python",
1009 | "nbconvert_exporter": "python",
1010 | "pygments_lexer": "ipython3",
1011 | "version": "3.6.8"
1012 | }
1013 | },
1014 | "nbformat": 4,
1015 | "nbformat_minor": 1
1016 | }
1017 |
--------------------------------------------------------------------------------
|