├── LICENSE ├── README.md ├── code ├── compound_loss.py └── edcnn_model.py └── figs ├── aapm_mayo_dataset.png ├── denoising_results.png └── model_structure.png /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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising 2 | 3 | By [Tengfei Liang](https://github.com/workingcoder), [Yi Jin](https://scholar.google.com/citations?user=NQAenU0AAAAJ&hl=en&oi=sra), [Yidong Li](https://scholar.google.com/citations?hl=en&user=3PagRQEAAAAJ), [Tao Wang](https://scholar.google.com/citations?user=F3C5oAcAAAAJ&hl=en&oi=sra). 4 | 5 | This repository is an official implementation of the paper [EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising](https://arxiv.org/abs/2011.00139). [`ArXiv`](https://arxiv.org/abs/2011.00139) [`IEEEXplore`](https://ieeexplore.ieee.org/document/9320928) 6 | 7 | *Notes:* 8 | 9 | This repository provides [model and loss implementation code](./code), which can be easily integrated into the user's project. 10 | 11 | 12 | ## Introduction 13 | 14 | EDCNN is a new end-to-end Low-Dose CT Denoiser. Designed as the FCN structure, it can effectively realize the low-dose CT image denoising in the way of post-processing. With the noval edge enhancement module, densely connection and compound loss, the model has a good performance in preserving details and suppressing noise in this denoising task. (For more details, please refer to [the original paper](https://arxiv.org/abs/2011.00139)) 15 | 16 |
17 |
18 | 19 | 20 | Fig. 1: Overall architecture of the proposed EDCNN model. 21 |
22 | 23 | 24 | ## Denoised results 25 | 26 | For fairness, we choose the [REDCNN](https://arxiv.org/abs/1702.00288), [WGAN](https://arxiv.org/abs/1708.00961) and [CPCE](https://arxiv.org/abs/1802.05656) for comparison, because of their design of the single model, which is the same as our [EDCNN](https://arxiv.org/abs/2011.00139) model. All these models adopt the structure of convolutional neural networks. 27 | 28 |
29 |
30 | 31 | 32 | Fig. 2: Comparison with existing Models on the AAPM-Mayo Dataset. 33 |
34 | 35 | 36 | 37 | ## AAPM-Mayo dataset 38 | 39 | In the experiment of our study, we utilize the dataset of the [2016 NIH AAPM-Mayo Clinic Low-Dose CT Grand Challenge](https://www.aapm.org/grandchallenge/lowdosect/), which is used by current mainstream methods in the field of low-dose CT image denoising. It contains the paired normal-dose CT (NDCT) images and synthetic quarter-dose CT images (LDCT) with a size of 512x512 pixels, collected from 10 patients. So there are LDCT images for inputs of the model and NDCT images as targets, which can support the supervised training process. [`Download`](https://www.dropbox.com/sh/txplswleuxgrdue/AABD_1W7-SKdXuZD4myvC2Hqa?dl=0) 40 | 41 |
42 |
43 | 44 |
45 | 46 | 47 | ## Citing EDCNN 48 | If you find EDCNN useful in your research, please consider citing: 49 | ```bibtex 50 | @article{Liang_2020, 51 | title={EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising}, 52 | ISBN={9781728144801}, 53 | url={http://dx.doi.org/10.1109/ICSP48669.2020.9320928}, 54 | DOI={10.1109/icsp48669.2020.9320928}, 55 | journal={2020 15th IEEE International Conference on Signal Processing (ICSP)}, 56 | publisher={IEEE}, 57 | author={Liang, Tengfei and Jin, Yi and Li, Yidong and Wang, Tao}, 58 | year={2020}, 59 | month={Dec} 60 | } 61 | ``` 62 | 63 | 64 | ## License 65 | 66 | This repository is released under the Apache 2.0 license. Please see the [LICENSE](./LICENSE) file for more information. 67 | -------------------------------------------------------------------------------- /code/compound_loss.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | from torch.nn.modules.loss import _Loss 4 | from torchvision import models 5 | 6 | 7 | class ResNet50FeatureExtractor(nn.Module): 8 | 9 | def __init__(self, blocks=[1, 2, 3, 4], pretrained=False, progress=True, **kwargs): 10 | super(ResNet50FeatureExtractor, self).__init__() 11 | self.model = models.resnet50(pretrained, progress, **kwargs) 12 | del self.model.avgpool 13 | del self.model.fc 14 | self.blocks = blocks 15 | 16 | def forward(self, x): 17 | feats = list() 18 | 19 | x = self.model.conv1(x) 20 | x = self.model.bn1(x) 21 | x = self.model.relu(x) 22 | x = self.model.maxpool(x) 23 | 24 | x = self.model.layer1(x) 25 | if 1 in self.blocks: 26 | feats.append(x) 27 | 28 | x = self.model.layer2(x) 29 | if 2 in self.blocks: 30 | feats.append(x) 31 | 32 | x = self.model.layer3(x) 33 | if 3 in self.blocks: 34 | feats.append(x) 35 | 36 | x = self.model.layer4(x) 37 | if 4 in self.blocks: 38 | feats.append(x) 39 | 40 | return feats 41 | 42 | 43 | class CompoundLoss(_Loss): 44 | 45 | def __init__(self, blocks=[1, 2, 3, 4], mse_weight=1, resnet_weight=0.01): 46 | super(CompoundLoss, self).__init__() 47 | 48 | self.mse_weight = mse_weight 49 | self.resnet_weight = resnet_weight 50 | 51 | self.blocks = blocks 52 | self.model = ResNet50FeatureExtractor(pretrained=True) 53 | 54 | if torch.cuda.is_available(): 55 | self.model = self.model.cuda() 56 | self.model.eval() 57 | 58 | self.criterion = nn.MSELoss() 59 | 60 | def forward(self, input, target): 61 | loss_value = 0 62 | 63 | input_feats = self.model(torch.cat([input, input, input], dim=1)) 64 | target_feats = self.model(torch.cat([target, target, target], dim=1)) 65 | 66 | feats_num = len(self.blocks) 67 | for idx in range(feats_num): 68 | loss_value += self.criterion(input_feats[idx], target_feats[idx]) 69 | loss_value /= feats_num 70 | 71 | loss = self.mse_weight * self.criterion(input, target) + self.resnet_weight * loss_value 72 | 73 | return loss 74 | -------------------------------------------------------------------------------- /code/edcnn_model.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | import torch.nn.functional as F 4 | 5 | 6 | class SobelConv2d(nn.Module): 7 | 8 | def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, 9 | padding=0, dilation=1, groups=1, bias=True, requires_grad=True): 10 | assert kernel_size % 2 == 1, 'SobelConv2d\'s kernel_size must be odd.' 11 | assert out_channels % 4 == 0, 'SobelConv2d\'s out_channels must be a multiple of 4.' 12 | assert out_channels % groups == 0, 'SobelConv2d\'s out_channels must be a multiple of groups.' 13 | 14 | super(SobelConv2d, self).__init__() 15 | 16 | self.in_channels = in_channels 17 | self.out_channels = out_channels 18 | self.kernel_size = kernel_size 19 | self.stride = stride 20 | self.padding = padding 21 | self.dilation = dilation 22 | self.groups = groups 23 | 24 | # In non-trainable case, it turns into normal Sobel operator with fixed weight and no bias. 25 | self.bias = bias if requires_grad else False 26 | 27 | if self.bias: 28 | self.bias = nn.Parameter(torch.zeros(size=(out_channels,), dtype=torch.float32), requires_grad=True) 29 | else: 30 | self.bias = None 31 | 32 | self.sobel_weight = nn.Parameter(torch.zeros( 33 | size=(out_channels, int(in_channels / groups), kernel_size, kernel_size)), requires_grad=False) 34 | 35 | # Initialize the Sobel kernal 36 | kernel_mid = kernel_size // 2 37 | for idx in range(out_channels): 38 | if idx % 4 == 0: 39 | self.sobel_weight[idx, :, 0, :] = -1 40 | self.sobel_weight[idx, :, 0, kernel_mid] = -2 41 | self.sobel_weight[idx, :, -1, :] = 1 42 | self.sobel_weight[idx, :, -1, kernel_mid] = 2 43 | elif idx % 4 == 1: 44 | self.sobel_weight[idx, :, :, 0] = -1 45 | self.sobel_weight[idx, :, kernel_mid, 0] = -2 46 | self.sobel_weight[idx, :, :, -1] = 1 47 | self.sobel_weight[idx, :, kernel_mid, -1] = 2 48 | elif idx % 4 == 2: 49 | self.sobel_weight[idx, :, 0, 0] = -2 50 | for i in range(0, kernel_mid + 1): 51 | self.sobel_weight[idx, :, kernel_mid - i, i] = -1 52 | self.sobel_weight[idx, :, kernel_size - 1 - i, kernel_mid + i] = 1 53 | self.sobel_weight[idx, :, -1, -1] = 2 54 | else: 55 | self.sobel_weight[idx, :, -1, 0] = -2 56 | for i in range(0, kernel_mid + 1): 57 | self.sobel_weight[idx, :, kernel_mid + i, i] = -1 58 | self.sobel_weight[idx, :, i, kernel_mid + i] = 1 59 | self.sobel_weight[idx, :, 0, -1] = 2 60 | 61 | # Define the trainable sobel factor 62 | if requires_grad: 63 | self.sobel_factor = nn.Parameter(torch.ones(size=(out_channels, 1, 1, 1), dtype=torch.float32), 64 | requires_grad=True) 65 | else: 66 | self.sobel_factor = nn.Parameter(torch.ones(size=(out_channels, 1, 1, 1), dtype=torch.float32), 67 | requires_grad=False) 68 | 69 | def forward(self, x): 70 | if torch.cuda.is_available(): 71 | self.sobel_factor = self.sobel_factor.cuda() 72 | if isinstance(self.bias, nn.Parameter): 73 | self.bias = self.bias.cuda() 74 | 75 | sobel_weight = self.sobel_weight * self.sobel_factor 76 | 77 | if torch.cuda.is_available(): 78 | sobel_weight = sobel_weight.cuda() 79 | 80 | out = F.conv2d(x, sobel_weight, self.bias, self.stride, self.padding, self.dilation, self.groups) 81 | 82 | return out 83 | 84 | 85 | class EDCNN(nn.Module): 86 | 87 | def __init__(self, in_ch=1, out_ch=32, sobel_ch=32): 88 | super(EDCNN, self).__init__() 89 | 90 | self.conv_sobel = SobelConv2d(in_ch, sobel_ch, kernel_size=3, stride=1, padding=1, bias=True) 91 | 92 | self.conv_p1 = nn.Conv2d(in_ch + sobel_ch, out_ch, kernel_size=1, stride=1, padding=0) 93 | self.conv_f1 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 94 | 95 | self.conv_p2 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 96 | self.conv_f2 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 97 | 98 | self.conv_p3 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 99 | self.conv_f3 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 100 | 101 | self.conv_p4 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 102 | self.conv_f4 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 103 | 104 | self.conv_p5 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 105 | self.conv_f5 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 106 | 107 | self.conv_p6 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 108 | self.conv_f6 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 109 | 110 | self.conv_p7 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 111 | self.conv_f7 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) 112 | 113 | self.conv_p8 = nn.Conv2d(in_ch + sobel_ch + out_ch, out_ch, kernel_size=1, stride=1, padding=0) 114 | self.conv_f8 = nn.Conv2d(out_ch, in_ch, kernel_size=3, stride=1, padding=1) 115 | 116 | self.relu = nn.LeakyReLU() 117 | 118 | def forward(self, x): 119 | out_0 = self.conv_sobel(x) 120 | out_0 = torch.cat((x, out_0), dim=-3) 121 | 122 | out_1 = self.relu(self.conv_p1(out_0)) 123 | out_1 = self.relu(self.conv_f1(out_1)) 124 | out_1 = torch.cat((out_0, out_1), dim=-3) 125 | 126 | out_2 = self.relu(self.conv_p2(out_1)) 127 | out_2 = self.relu(self.conv_f2(out_2)) 128 | out_2 = torch.cat((out_0, out_2), dim=-3) 129 | 130 | out_3 = self.relu(self.conv_p3(out_2)) 131 | out_3 = self.relu(self.conv_f3(out_3)) 132 | out_3 = torch.cat((out_0, out_3), dim=-3) 133 | 134 | out_4 = self.relu(self.conv_p4(out_3)) 135 | out_4 = self.relu(self.conv_f4(out_4)) 136 | out_4 = torch.cat((out_0, out_4), dim=-3) 137 | 138 | out_5 = self.relu(self.conv_p5(out_4)) 139 | out_5 = self.relu(self.conv_f5(out_5)) 140 | out_5 = torch.cat((out_0, out_5), dim=-3) 141 | 142 | out_6 = self.relu(self.conv_p6(out_5)) 143 | out_6 = self.relu(self.conv_f6(out_6)) 144 | out_6 = torch.cat((out_0, out_6), dim=-3) 145 | 146 | out_7 = self.relu(self.conv_p7(out_6)) 147 | out_7 = self.relu(self.conv_f7(out_7)) 148 | out_7 = torch.cat((out_0, out_7), dim=-3) 149 | 150 | out_8 = self.relu(self.conv_p8(out_7)) 151 | out_8 = self.conv_f8(out_8) 152 | 153 | out = self.relu(x + out_8) 154 | 155 | return out 156 | -------------------------------------------------------------------------------- /figs/aapm_mayo_dataset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/workingcoder/EDCNN/68305f465d2b731b60ce78bd0c95c7742d9f52d1/figs/aapm_mayo_dataset.png -------------------------------------------------------------------------------- /figs/denoising_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/workingcoder/EDCNN/68305f465d2b731b60ce78bd0c95c7742d9f52d1/figs/denoising_results.png -------------------------------------------------------------------------------- /figs/model_structure.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/workingcoder/EDCNN/68305f465d2b731b60ce78bd0c95c7742d9f52d1/figs/model_structure.png --------------------------------------------------------------------------------