Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network
Colorectal cancer is a dangerous disease with a high mortality rate. To increase the likelihood of successful treatment, early detection of polyps is a useful solution. The Unet-architecture network model is showing success in medical image segmentation including analysis of polyps from colonoscopy...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9801845/ |
| _version_ | 1811237742570373120 |
|---|---|
| author | Song-Toan Tran Minh-Hoa Nguyen Huu-Phuc Dang Thanh-Tan Nguyen |
| author_facet | Song-Toan Tran Minh-Hoa Nguyen Huu-Phuc Dang Thanh-Tan Nguyen |
| author_sort | Song-Toan Tran |
| collection | DOAJ |
| description | Colorectal cancer is a dangerous disease with a high mortality rate. To increase the likelihood of successful treatment, early detection of polyps is a useful solution. The Unet-architecture network model is showing success in medical image segmentation including analysis of polyps from colonoscopy images. Traditional Unet and Unet-based models are often huge, requiring training and deployment with a high-performance system. Designing models with compact size and high-performance would be an important goal. In this study, we proposed to modify the Residual Recurrent Unet architecture to improve the size of the model while ensuring the model performance. The proposed model has flexibility in changing the number of filters in convolution units. By taking advantage of the strengths of residual and recurrent structures in terms of reuse of convolutional functions, the new model, therefore, was not only smaller in size but also has superior performance compared to the traditional Unet model and the others. The evaluations were performed on three public Colonoscopy image datasets: CVC-ClinicDB, ETIS-LaribPolypDB, and CVC-ColonDB. The Dice score on CVC-ClinicDB reached 94.59%, ETIS-LaribPolypDB reached 92.73%, and 93.31% on CVC-ColonDB dataset. The experimental results obtained from the proposed network on datasets were better than those in recent related studies. The introduced model has a smaller size than the traditional model nevertheless has outstanding performance, therefore, it would be extremely productive for developing applications on low-performance devices. |
| first_indexed | 2024-04-12T12:28:33Z |
| format | Article |
| id | doaj.art-5048c980ea9c4134a8f72c283197f1a6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T12:28:33Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5048c980ea9c4134a8f72c283197f1a62022-12-22T03:33:05ZengIEEEIEEE Access2169-35362022-01-0110659516596110.1109/ACCESS.2022.31847739801845Automatic Polyp Segmentation Using Modified Recurrent Residual Unet NetworkSong-Toan Tran0https://orcid.org/0000-0002-8329-0036Minh-Hoa Nguyen1https://orcid.org/0000-0001-6494-7779Huu-Phuc Dang2https://orcid.org/0000-0002-9643-7287Thanh-Tan Nguyen3Department of Electrical and Electronic Engineering, Tra Vinh University, Tra Vinh, VietnamDepartment of Electrical and Electronic Engineering, Tra Vinh University, Tra Vinh, VietnamDepartment of Electrical and Electronic Engineering, Tra Vinh University, Tra Vinh, VietnamDepartment of Electrical and Electronic Engineering, Tra Vinh University, Tra Vinh, VietnamColorectal cancer is a dangerous disease with a high mortality rate. To increase the likelihood of successful treatment, early detection of polyps is a useful solution. The Unet-architecture network model is showing success in medical image segmentation including analysis of polyps from colonoscopy images. Traditional Unet and Unet-based models are often huge, requiring training and deployment with a high-performance system. Designing models with compact size and high-performance would be an important goal. In this study, we proposed to modify the Residual Recurrent Unet architecture to improve the size of the model while ensuring the model performance. The proposed model has flexibility in changing the number of filters in convolution units. By taking advantage of the strengths of residual and recurrent structures in terms of reuse of convolutional functions, the new model, therefore, was not only smaller in size but also has superior performance compared to the traditional Unet model and the others. The evaluations were performed on three public Colonoscopy image datasets: CVC-ClinicDB, ETIS-LaribPolypDB, and CVC-ColonDB. The Dice score on CVC-ClinicDB reached 94.59%, ETIS-LaribPolypDB reached 92.73%, and 93.31% on CVC-ColonDB dataset. The experimental results obtained from the proposed network on datasets were better than those in recent related studies. The introduced model has a smaller size than the traditional model nevertheless has outstanding performance, therefore, it would be extremely productive for developing applications on low-performance devices.https://ieeexplore.ieee.org/document/9801845/Colonoscopy imagemedical image segmentationpolyp segmentationrecurrent residual structureUnet architecture |
| spellingShingle | Song-Toan Tran Minh-Hoa Nguyen Huu-Phuc Dang Thanh-Tan Nguyen Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network IEEE Access Colonoscopy image medical image segmentation polyp segmentation recurrent residual structure Unet architecture |
| title | Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network |
| title_full | Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network |
| title_fullStr | Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network |
| title_full_unstemmed | Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network |
| title_short | Automatic Polyp Segmentation Using Modified Recurrent Residual Unet Network |
| title_sort | automatic polyp segmentation using modified recurrent residual unet network |
| topic | Colonoscopy image medical image segmentation polyp segmentation recurrent residual structure Unet architecture |
| url | https://ieeexplore.ieee.org/document/9801845/ |
| work_keys_str_mv | AT songtoantran automaticpolypsegmentationusingmodifiedrecurrentresidualunetnetwork AT minhhoanguyen automaticpolypsegmentationusingmodifiedrecurrentresidualunetnetwork AT huuphucdang automaticpolypsegmentationusingmodifiedrecurrentresidualunetnetwork AT thanhtannguyen automaticpolypsegmentationusingmodifiedrecurrentresidualunetnetwork |