├── Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset.pdf
├── Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset SI.pdf
├── README.md
└── Params.yaml


/Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kwahid/Radiomic-Prediction-of-Tumor-Grade-and-Overall-Survival-from-the-BraTS-Glioma-Dataset/HEAD/Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset.pdf


--------------------------------------------------------------------------------
/Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset SI.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kwahid/Radiomic-Prediction-of-Tumor-Grade-and-Overall-Survival-from-the-BraTS-Glioma-Dataset/HEAD/Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset SI.pdf


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Radiomic-Prediction-of-Tumor-Grade-and-Overall-Survival-from-the-BraTS-Glioma-Dataset
 2 | Folder corresponding to 2017 summer project at MD Anderson Cancer Center. Correspondance: kareem.a.wahid@uth.tmc.edu.
 3 | 
 4 | ## This repo contains the following files: 
 5 | PDF of project report (Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset.pdf). <br><br>
 6 | PDF of supplementary information (Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset SI.pdf). <br><br>
 7 | Folder containing csv files neccessary for running notebook (input files). <br><br>
 8 | Jupyter notebook of code implementation (Radiomic Prediction of Tumor Grade and Overall Survival from the BraTS Glioma Dataset.ipynb). <br><br>
 9 | HTML copy of Jupyter notebook (Radiomic+Prediction+of+Tumor+Grade+and+Overall+Survival+from+the+BraTS+Glioma+Dataset).<br><br>
10 | Parameter file used in radiomic feature extaction (Params.yaml). <br><br>
11 | 
12 | ## Utilized the following python libraries in project: 
13 | pyradiomics to generate features of dataset. http://pyradiomics.readthedocs.io/en/latest/ <br><br>
14 | pandas for data manipulation.<br><br>
15 | sklearn for machine learning.<br><br>
16 | imblearn for upsampling. <br><br>
17 | matplotlib for graphing.<br><br>
18 | seaborn for data visualizations. <br><br>
19 | statsmodels for ANOVA statistical test. <br><br>
20 | 


--------------------------------------------------------------------------------
/Params.yaml:
--------------------------------------------------------------------------------
 1 | # This is an example of a parameters file
 2 | # It is written according to the YAML-convention (www.yaml.org) and is checked by the code for consistency.
 3 | # Three types of settings are possible and reflected in the structure of the document:
 4 | #
 5 | # Setting Type:
 6 | #   Setting Name: <value>
 7 | #
 8 | # The three setting types are:
 9 | # - setting: Setting to use for preprocessing and class specific settings. if no <value> is specified, the value for
10 | #   this setting is set to None.
11 | # - featureClass: Feature class to enable, <value> is list of strings representing enabled features. If no <value> is
12 | #   specified or <value> is an empty list ('[]'), all features for this class are enabled.
13 | # - inputImage: input image to calculate features on. <value> is custom kwarg settings (dictionary). if <value> is an
14 | #   empty dictionary ('{}'), no custom settings are added for this input image.
15 | #
16 | # Some settings have a limited list of possible values. Where this is the case, possible values are listed in the
17 | # package documentation
18 | 
19 | # Settings to use, possible settings are mentioned in the documentation at the start of the modules.
20 | setting:
21 |   normalize: True
22 |   #normalizeScale: 256 
23 |   removeOutliers: 3
24 |   binWidth: 0.1
25 |   label: 1
26 |   interpolator: 'sitkBSpline' # This is an enumerated value, here None is not allowed
27 |   resampledPixelSpacing: # This disables resampling, as it is interpreted as None, to enable it, specify spacing in x, y, z as [x, y , z]
28 |   weightingNorm: # If no value is specified, it is interpreted as None
29 | 
30 | # Input images to use: original for unfiltered image and/or any other filters, see documentation of featureextractor.py
31 | # for possible values
32 | inputImage:
33 |   Original: {} # for dictionaries / mappings, None values are not allowed, '{}' is interpreted as an empty dictionary
34 |   #LoG: {'sigma': [2.0]}
35 |   Wavelet: {}
36 | 
37 | # Featureclasses, from which features must be calculated. If a featureclass is not mentioned, no features are calculated
38 | # for that class. Otherwise, the specified features are calculated, or, if none are specified, all are calculated.
39 | featureClass:
40 |   shape: # Only enable these shape descriptors (disables redundant Compactness 1 and Compactness 2)
41 |   firstorder: [] # specifying an empty list has the same effect as specifying nothing.
42 |   glcm: # for lists none values are allowed, in this case, all features are enabled
43 |   glrlm:
44 |   glszm:
45 | 


--------------------------------------------------------------------------------