UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images
Colonoscopy is a gold standard procedure for tracking the lower gastrointestinal region. A colorectal polyp is one such condition that is detected through colonoscopy. Even though technical advancements have improved the early detection of colorectal polyps, there is still a high percentage of misse...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Gastroenterology Insights |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2036-7422/13/3/27 |
| _version_ | 1797488145270308864 |
|---|---|
| author | Subhashree Mohapatra Girish Kumar Pati Manohar Mishra Tripti Swarnkar |
| author_facet | Subhashree Mohapatra Girish Kumar Pati Manohar Mishra Tripti Swarnkar |
| author_sort | Subhashree Mohapatra |
| collection | DOAJ |
| description | Colonoscopy is a gold standard procedure for tracking the lower gastrointestinal region. A colorectal polyp is one such condition that is detected through colonoscopy. Even though technical advancements have improved the early detection of colorectal polyps, there is still a high percentage of misses due to various factors. Polyp segmentation can play a significant role in the detection of polyps at the early stage and can thus help reduce the severity of the disease. In this work, the authors implemented several image pre-processing techniques such as coherence transport and contrast limited adaptive histogram equalization (CLAHE) to handle different challenges in colonoscopy images. The processed image was then segmented into a polyp and normal pixel using a U-Net-based deep learning segmentation model named UPolySeg. The main framework of UPolySeg has an encoder–decoder section with feature concatenation in the same layer as the encoder–decoder along with the use of dilated convolution. The model was experimentally verified using the publicly available Kvasir-SEG dataset, which gives a global accuracy of 96.77%, a dice coefficient of 96.86%, an IoU of 87.91%, a recall of 95.57%, and a precision of 92.29%. The new framework for the polyp segmentation implementing UPolySeg improved the performance by 1.93% compared with prior work. |
| first_indexed | 2024-03-09T23:58:51Z |
| format | Article |
| id | doaj.art-ddd6803ea78c403496b9b6d3b208a9a1 |
| institution | Directory Open Access Journal |
| issn | 2036-7414 2036-7422 |
| language | English |
| last_indexed | 2024-03-09T23:58:51Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Gastroenterology Insights |
| spelling | doaj.art-ddd6803ea78c403496b9b6d3b208a9a12023-11-23T16:21:14ZengMDPI AGGastroenterology Insights2036-74142036-74222022-08-0113326427410.3390/gastroent13030027UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy ImagesSubhashree Mohapatra0Girish Kumar Pati1Manohar Mishra2Tripti Swarnkar3Department of Computer Science & Engineering, Siksha O Anusandhan Deemed to Be University, Bhubaneswar 751030, IndiaDepartment of Gastroenterology, Institute of Medical Science and SUM Hospital, Bhubaneswar 751003, IndiaDepartment of Electrical and Electronics Engineering, Siksha O Anusandhan Deemed to Be University, Bhubaneswar 751030, IndiaDepartment of Computer Application, Siksha O Anusandhan Deemed to Be University, Bhubaneswar 751030, IndiaColonoscopy is a gold standard procedure for tracking the lower gastrointestinal region. A colorectal polyp is one such condition that is detected through colonoscopy. Even though technical advancements have improved the early detection of colorectal polyps, there is still a high percentage of misses due to various factors. Polyp segmentation can play a significant role in the detection of polyps at the early stage and can thus help reduce the severity of the disease. In this work, the authors implemented several image pre-processing techniques such as coherence transport and contrast limited adaptive histogram equalization (CLAHE) to handle different challenges in colonoscopy images. The processed image was then segmented into a polyp and normal pixel using a U-Net-based deep learning segmentation model named UPolySeg. The main framework of UPolySeg has an encoder–decoder section with feature concatenation in the same layer as the encoder–decoder along with the use of dilated convolution. The model was experimentally verified using the publicly available Kvasir-SEG dataset, which gives a global accuracy of 96.77%, a dice coefficient of 96.86%, an IoU of 87.91%, a recall of 95.57%, and a precision of 92.29%. The new framework for the polyp segmentation implementing UPolySeg improved the performance by 1.93% compared with prior work.https://www.mdpi.com/2036-7422/13/3/27segmentationpolypU-Netcolonoscopydeep learning |
| spellingShingle | Subhashree Mohapatra Girish Kumar Pati Manohar Mishra Tripti Swarnkar UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images Gastroenterology Insights segmentation polyp U-Net colonoscopy deep learning |
| title | UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images |
| title_full | UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images |
| title_fullStr | UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images |
| title_full_unstemmed | UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images |
| title_short | UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images |
| title_sort | upolyseg a u net based polyp segmentation network using colonoscopy images |
| topic | segmentation polyp U-Net colonoscopy deep learning |
| url | https://www.mdpi.com/2036-7422/13/3/27 |
| work_keys_str_mv | AT subhashreemohapatra upolysegaunetbasedpolypsegmentationnetworkusingcolonoscopyimages AT girishkumarpati upolysegaunetbasedpolypsegmentationnetworkusingcolonoscopyimages AT manoharmishra upolysegaunetbasedpolypsegmentationnetworkusingcolonoscopyimages AT triptiswarnkar upolysegaunetbasedpolypsegmentationnetworkusingcolonoscopyimages |