Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning
Abstract Background Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help clinicians diagnose cancer. Recently, the U-N...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-07-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12938-023-01137-4 |
| _version_ | 1797774056827650048 |
|---|---|
| author | Yajiao Liu Jiang Wang Chenpeng Wu Liyun Liu Zhiyong Zhang Haitao Yu |
| author_facet | Yajiao Liu Jiang Wang Chenpeng Wu Liyun Liu Zhiyong Zhang Haitao Yu |
| author_sort | Yajiao Liu |
| collection | DOAJ |
| description | Abstract Background Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help clinicians diagnose cancer. Recently, the U-Net architecture based on convolutional neural networks (CNNs) has been widely used to segment image to accomplish more precise cancer diagnosis. However, the accurate segmentation of important regions with high diagnostic value is still a great challenge due to the insufficient capability of CNN and codec structure in aggregating the detailed and non-local contextual information. In this work, we propose a high performance and low computation solution. Methods Inspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to the pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP. Results Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 79.38% IoU, 88.51% DSC, 92.82% sensitivity and 84.57% precision on the LNM dataset, and the parameter amount is reduced to 23.23 MB. Conclusions The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer. |
| first_indexed | 2024-03-12T22:15:24Z |
| format | Article |
| id | doaj.art-e76cb98c2a8544cda724c51652d68a35 |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-03-12T22:15:24Z |
| publishDate | 2023-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-e76cb98c2a8544cda724c51652d68a352023-07-23T11:20:58ZengBMCBioMedical Engineering OnLine1475-925X2023-07-0122112010.1186/s12938-023-01137-4Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learningYajiao Liu0Jiang Wang1Chenpeng Wu2Liyun Liu3Zhiyong Zhang4Haitao Yu5School of Electrical and Information Engineering, Tianjin UniversitySchool of Electrical and Information Engineering, Tianjin UniversityDepartment of Pathology, Tangshan Gongren HospitalDepartment of Pathology, Tangshan Gongren HospitalDepartment of Pathology, Tangshan Gongren HospitalSchool of Electrical and Information Engineering, Tianjin UniversityAbstract Background Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help clinicians diagnose cancer. Recently, the U-Net architecture based on convolutional neural networks (CNNs) has been widely used to segment image to accomplish more precise cancer diagnosis. However, the accurate segmentation of important regions with high diagnostic value is still a great challenge due to the insufficient capability of CNN and codec structure in aggregating the detailed and non-local contextual information. In this work, we propose a high performance and low computation solution. Methods Inspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to the pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP. Results Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 79.38% IoU, 88.51% DSC, 92.82% sensitivity and 84.57% precision on the LNM dataset, and the parameter amount is reduced to 23.23 MB. Conclusions The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer.https://doi.org/10.1186/s12938-023-01137-4Medical image segmentationColorectal cancerFovea in human retinaAdaptive resolutionFeature importance-awareAttention mechanism |
| spellingShingle | Yajiao Liu Jiang Wang Chenpeng Wu Liyun Liu Zhiyong Zhang Haitao Yu Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning BioMedical Engineering OnLine Medical image segmentation Colorectal cancer Fovea in human retina Adaptive resolution Feature importance-aware Attention mechanism |
| title | Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| title_full | Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| title_fullStr | Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| title_full_unstemmed | Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| title_short | Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| title_sort | fovea unet detection and segmentation of lymph node metastases in colorectal cancer with deep learning |
| topic | Medical image segmentation Colorectal cancer Fovea in human retina Adaptive resolution Feature importance-aware Attention mechanism |
| url | https://doi.org/10.1186/s12938-023-01137-4 |
| work_keys_str_mv | AT yajiaoliu foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning AT jiangwang foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning AT chenpengwu foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning AT liyunliu foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning AT zhiyongzhang foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning AT haitaoyu foveaunetdetectionandsegmentationoflymphnodemetastasesincolorectalcancerwithdeeplearning |