N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images
Colorectal cancer is the cancer with the second highest and the third highest incidence rates for the female and the male, respectively. Colorectal polyps are potential prognostic indicators of colorectal cancer, and colonoscopy is the gold standard for the biopsy and the removal of colorectal polyp...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2022.963590/full |
| _version_ | 1811345006958477312 |
|---|---|
| author | Rongsheng Cui Runzhuo Yang Feng Liu Feng Liu Chunqian Cai Chunqian Cai |
| author_facet | Rongsheng Cui Runzhuo Yang Feng Liu Feng Liu Chunqian Cai Chunqian Cai |
| author_sort | Rongsheng Cui |
| collection | DOAJ |
| description | Colorectal cancer is the cancer with the second highest and the third highest incidence rates for the female and the male, respectively. Colorectal polyps are potential prognostic indicators of colorectal cancer, and colonoscopy is the gold standard for the biopsy and the removal of colorectal polyps. In this scenario, one of the main concerns is to ensure the accuracy of lesion region identifications. However, the missing rate of polyps through manual observations in colonoscopy can reach 14%–30%. In this paper, we focus on the identifications of polyps in clinical colonoscopy images and propose a new N-shaped deep neural network (N-Net) structure to conduct the lesion region segmentations. The encoder-decoder framework is adopted in the N-Net structure and the DenseNet modules are implemented in the encoding path of the network. Moreover, we innovatively propose the strategy to design the generalized hybrid dilated convolution (GHDC), which enables flexible dilated rates and convolutional kernel sizes, to facilitate the transmission of the multi-scale information with the respective fields expanded. Based on the strategy of GHDC designing, we design four GHDC blocks to connect the encoding and the decoding paths. Through the experiments on two publicly available datasets on polyp segmentations of colonoscopy images: the Kvasir-SEG dataset and the CVC-ClinicDB dataset, the rationality and superiority of the proposed GHDC blocks and the proposed N-Net are verified. Through the comparative studies with the state-of-the-art methods, such as TransU-Net, DeepLabV3+ and CA-Net, we show that even with a small amount of network parameters, the N-Net outperforms with the Dice of 94.45%, the average symmetric surface distance (ASSD) of 0.38 pix and the mean intersection-over-union (mIoU) of 89.80% on the Kvasir-SEG dataset, and with the Dice of 97.03%, the ASSD of 0.16 pix and the mIoU of 94.35% on the CVC-ClinicDB dataset. |
| first_indexed | 2024-04-13T19:56:39Z |
| format | Article |
| id | doaj.art-ad9182fc51954ed4a82594cb12e24b05 |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-13T19:56:39Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-ad9182fc51954ed4a82594cb12e24b052022-12-22T02:32:19ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852022-10-011010.3389/fbioe.2022.963590963590N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy imagesRongsheng Cui0Runzhuo Yang1Feng Liu2Feng Liu3Chunqian Cai4Chunqian Cai5College of Electronic Information and Optical Engineering, Nankai University, Tianjin, ChinaCollege of Electronic Information and Optical Engineering, Nankai University, Tianjin, ChinaCollege of Electronic Information and Optical Engineering, Nankai University, Tianjin, ChinaTianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin, ChinaFirst Teaching Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin, ChinaNational Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, Tianjin, ChinaColorectal cancer is the cancer with the second highest and the third highest incidence rates for the female and the male, respectively. Colorectal polyps are potential prognostic indicators of colorectal cancer, and colonoscopy is the gold standard for the biopsy and the removal of colorectal polyps. In this scenario, one of the main concerns is to ensure the accuracy of lesion region identifications. However, the missing rate of polyps through manual observations in colonoscopy can reach 14%–30%. In this paper, we focus on the identifications of polyps in clinical colonoscopy images and propose a new N-shaped deep neural network (N-Net) structure to conduct the lesion region segmentations. The encoder-decoder framework is adopted in the N-Net structure and the DenseNet modules are implemented in the encoding path of the network. Moreover, we innovatively propose the strategy to design the generalized hybrid dilated convolution (GHDC), which enables flexible dilated rates and convolutional kernel sizes, to facilitate the transmission of the multi-scale information with the respective fields expanded. Based on the strategy of GHDC designing, we design four GHDC blocks to connect the encoding and the decoding paths. Through the experiments on two publicly available datasets on polyp segmentations of colonoscopy images: the Kvasir-SEG dataset and the CVC-ClinicDB dataset, the rationality and superiority of the proposed GHDC blocks and the proposed N-Net are verified. Through the comparative studies with the state-of-the-art methods, such as TransU-Net, DeepLabV3+ and CA-Net, we show that even with a small amount of network parameters, the N-Net outperforms with the Dice of 94.45%, the average symmetric surface distance (ASSD) of 0.38 pix and the mean intersection-over-union (mIoU) of 89.80% on the Kvasir-SEG dataset, and with the Dice of 97.03%, the ASSD of 0.16 pix and the mIoU of 94.35% on the CVC-ClinicDB dataset.https://www.frontiersin.org/articles/10.3389/fbioe.2022.963590/fullN-shape deep neural networkgeneralized hybrid dilated convolutioncolonoscopycolorectal polyp identificationlesion region segmentationdeep learning |
| spellingShingle | Rongsheng Cui Runzhuo Yang Feng Liu Feng Liu Chunqian Cai Chunqian Cai N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images Frontiers in Bioengineering and Biotechnology N-shape deep neural network generalized hybrid dilated convolution colonoscopy colorectal polyp identification lesion region segmentation deep learning |
| title | N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| title_full | N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| title_fullStr | N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| title_full_unstemmed | N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| title_short | N-Net: Lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| title_sort | n net lesion region segmentations using the generalized hybrid dilated convolutions for polyps in colonoscopy images |
| topic | N-shape deep neural network generalized hybrid dilated convolution colonoscopy colorectal polyp identification lesion region segmentation deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2022.963590/full |
| work_keys_str_mv | AT rongshengcui nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages AT runzhuoyang nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages AT fengliu nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages AT fengliu nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages AT chunqiancai nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages AT chunqiancai nnetlesionregionsegmentationsusingthegeneralizedhybriddilatedconvolutionsforpolypsincolonoscopyimages |