A super-resolution network using channel attention retention for pathology images
Image super-resolution (SR) significantly improves the quality of low-resolution images, and is widely used for image reconstruction in various fields. Although the existing SR methods have achieved distinguished results in objective metrics, most methods focus on real-world images and employ large...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1196.pdf |
| _version_ | 1828058457841860608 |
|---|---|
| author | Feiyang Jia Li Tan Ge Wang Caiyan Jia Zhineng Chen |
| author_facet | Feiyang Jia Li Tan Ge Wang Caiyan Jia Zhineng Chen |
| author_sort | Feiyang Jia |
| collection | DOAJ |
| description | Image super-resolution (SR) significantly improves the quality of low-resolution images, and is widely used for image reconstruction in various fields. Although the existing SR methods have achieved distinguished results in objective metrics, most methods focus on real-world images and employ large and complex network structures, which are inefficient for medical diagnosis scenarios. To address the aforementioned issues, the distinction between pathology images and real-world images was investigated, and an SR Network with a wider and deeper attention module called Channel Attention Retention is proposed to obtain SR images with enhanced high-frequency features. This network captures contextual information within and across blocks via residual skips and balances the performance and efficiency by controlling the number of blocks. Meanwhile, a new linear loss was introduced to optimize the network. To evaluate the work and compare multiple SR works, a benchmark dataset bcSR was created, which forces a model training on wider and more critical regions. The results show that the proposed model outperforms state-of-the-art methods in both performance and efficiency, and the newly created dataset significantly improves the reconstruction quality of all compared models. Moreover, image classification experiments demonstrate that the suggested network improves the performance of downstream tasks in medical diagnosis scenarios. The proposed network and dataset provide effective priors for the SR task of pathology images, which significantly improves the diagnosis of relevant medical staff. The source code and the dataset are available on https://github.com/MoyangSensei/CARN-Pytorch. |
| first_indexed | 2024-04-10T21:28:48Z |
| format | Article |
| id | doaj.art-bf99e82f2d804d50a2fad3d43b52132d |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-04-10T21:28:48Z |
| publishDate | 2023-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-bf99e82f2d804d50a2fad3d43b52132d2023-01-19T15:05:09ZengPeerJ Inc.PeerJ Computer Science2376-59922023-01-019e119610.7717/peerj-cs.1196A super-resolution network using channel attention retention for pathology imagesFeiyang Jia0Li Tan1Ge Wang2Caiyan Jia3Zhineng Chen4Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing, ChinaBeijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing, ChinaBeijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing, ChinaSchool of Computer and Information Technology, Beijing Jiaotong University, Beijing, ChinaSchool of Computer Science, Fudan University, Shanghai, ChinaImage super-resolution (SR) significantly improves the quality of low-resolution images, and is widely used for image reconstruction in various fields. Although the existing SR methods have achieved distinguished results in objective metrics, most methods focus on real-world images and employ large and complex network structures, which are inefficient for medical diagnosis scenarios. To address the aforementioned issues, the distinction between pathology images and real-world images was investigated, and an SR Network with a wider and deeper attention module called Channel Attention Retention is proposed to obtain SR images with enhanced high-frequency features. This network captures contextual information within and across blocks via residual skips and balances the performance and efficiency by controlling the number of blocks. Meanwhile, a new linear loss was introduced to optimize the network. To evaluate the work and compare multiple SR works, a benchmark dataset bcSR was created, which forces a model training on wider and more critical regions. The results show that the proposed model outperforms state-of-the-art methods in both performance and efficiency, and the newly created dataset significantly improves the reconstruction quality of all compared models. Moreover, image classification experiments demonstrate that the suggested network improves the performance of downstream tasks in medical diagnosis scenarios. The proposed network and dataset provide effective priors for the SR task of pathology images, which significantly improves the diagnosis of relevant medical staff. The source code and the dataset are available on https://github.com/MoyangSensei/CARN-Pytorch.https://peerj.com/articles/cs-1196.pdfBreast cancerPathology imagesSuper-resolutionResidual networkChannel attention |
| spellingShingle | Feiyang Jia Li Tan Ge Wang Caiyan Jia Zhineng Chen A super-resolution network using channel attention retention for pathology images PeerJ Computer Science Breast cancer Pathology images Super-resolution Residual network Channel attention |
| title | A super-resolution network using channel attention retention for pathology images |
| title_full | A super-resolution network using channel attention retention for pathology images |
| title_fullStr | A super-resolution network using channel attention retention for pathology images |
| title_full_unstemmed | A super-resolution network using channel attention retention for pathology images |
| title_short | A super-resolution network using channel attention retention for pathology images |
| title_sort | super resolution network using channel attention retention for pathology images |
| topic | Breast cancer Pathology images Super-resolution Residual network Channel attention |
| url | https://peerj.com/articles/cs-1196.pdf |
| work_keys_str_mv | AT feiyangjia asuperresolutionnetworkusingchannelattentionretentionforpathologyimages AT litan asuperresolutionnetworkusingchannelattentionretentionforpathologyimages AT gewang asuperresolutionnetworkusingchannelattentionretentionforpathologyimages AT caiyanjia asuperresolutionnetworkusingchannelattentionretentionforpathologyimages AT zhinengchen asuperresolutionnetworkusingchannelattentionretentionforpathologyimages AT feiyangjia superresolutionnetworkusingchannelattentionretentionforpathologyimages AT litan superresolutionnetworkusingchannelattentionretentionforpathologyimages AT gewang superresolutionnetworkusingchannelattentionretentionforpathologyimages AT caiyanjia superresolutionnetworkusingchannelattentionretentionforpathologyimages AT zhinengchen superresolutionnetworkusingchannelattentionretentionforpathologyimages |