A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution
Colon carcinoma is one of the leading causes of cancer-related death in both men and women. Automatic colorectal polyp segmentation and detection in colonoscopy videos help endoscopists to identify colorectal disease more easily, making it a promising method to prevent colon cancer. In this study, w...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1441 |
| _version_ | 1797396054308552704 |
|---|---|
| author | Sirojbek Safarov Taeg Keun Whangbo |
| author_facet | Sirojbek Safarov Taeg Keun Whangbo |
| author_sort | Sirojbek Safarov |
| collection | DOAJ |
| description | Colon carcinoma is one of the leading causes of cancer-related death in both men and women. Automatic colorectal polyp segmentation and detection in colonoscopy videos help endoscopists to identify colorectal disease more easily, making it a promising method to prevent colon cancer. In this study, we developed a fully automated pixel-wise polyp segmentation model named A-DenseUNet. The proposed architecture adapts different datasets, adjusting for the unknown depth of the network by sharing multiscale encoding information to the different levels of the decoder side. We also used multiple dilated convolutions with various atrous rates to observe a large field of view without increasing the computational cost and prevent loss of spatial information, which would cause dimensionality reduction. We utilized an attention mechanism to remove noise and inappropriate information, leading to the comprehensive re-establishment of contextual features. Our experiments demonstrated that the proposed architecture achieved significant segmentation results on public datasets. A-DenseUNet achieved a 90% Dice coefficient score on the Kvasir-SEG dataset and a 91% Dice coefficient score on the CVC-612 dataset, both of which were higher than the scores of other deep learning models such as UNet++, ResUNet, U-Net, PraNet, and ResUNet++ for segmenting polyps in colonoscopy images. |
| first_indexed | 2024-03-09T00:44:45Z |
| format | Article |
| id | doaj.art-83a9e484c0e74399ad639e80bc590e9f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T00:44:45Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-83a9e484c0e74399ad639e80bc590e9f2023-12-11T17:37:04ZengMDPI AGSensors1424-82202021-02-01214144110.3390/s21041441A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous ConvolutionSirojbek Safarov0Taeg Keun Whangbo1Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do 461-701, KoreaDepartment of Computer Science, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do 461-701, KoreaColon carcinoma is one of the leading causes of cancer-related death in both men and women. Automatic colorectal polyp segmentation and detection in colonoscopy videos help endoscopists to identify colorectal disease more easily, making it a promising method to prevent colon cancer. In this study, we developed a fully automated pixel-wise polyp segmentation model named A-DenseUNet. The proposed architecture adapts different datasets, adjusting for the unknown depth of the network by sharing multiscale encoding information to the different levels of the decoder side. We also used multiple dilated convolutions with various atrous rates to observe a large field of view without increasing the computational cost and prevent loss of spatial information, which would cause dimensionality reduction. We utilized an attention mechanism to remove noise and inappropriate information, leading to the comprehensive re-establishment of contextual features. Our experiments demonstrated that the proposed architecture achieved significant segmentation results on public datasets. A-DenseUNet achieved a 90% Dice coefficient score on the Kvasir-SEG dataset and a 91% Dice coefficient score on the CVC-612 dataset, both of which were higher than the scores of other deep learning models such as UNet++, ResUNet, U-Net, PraNet, and ResUNet++ for segmenting polyps in colonoscopy images.https://www.mdpi.com/1424-8220/21/4/1441semantic segmentationconvolutional neural networkscolonoscopypolyp segmentationdeep learningattention |
| spellingShingle | Sirojbek Safarov Taeg Keun Whangbo A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution Sensors semantic segmentation convolutional neural networks colonoscopy polyp segmentation deep learning attention |
| title | A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution |
| title_full | A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution |
| title_fullStr | A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution |
| title_full_unstemmed | A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution |
| title_short | A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution |
| title_sort | a denseunet adaptive densely connected unet for polyp segmentation in colonoscopy images with atrous convolution |
| topic | semantic segmentation convolutional neural networks colonoscopy polyp segmentation deep learning attention |
| url | https://www.mdpi.com/1424-8220/21/4/1441 |
| work_keys_str_mv | AT sirojbeksafarov adenseunetadaptivedenselyconnectedunetforpolypsegmentationincolonoscopyimageswithatrousconvolution AT taegkeunwhangbo adenseunetadaptivedenselyconnectedunetforpolypsegmentationincolonoscopyimageswithatrousconvolution |