Deep neural network models for colon cancer screening
Early detection of colorectal cancer can significantly facilitate clinicians’ decision-making and reduce their workload. This can be achieved using automatic systems with endoscopic and histological images. Recently, the success of deep learning has motivated the development of image- and video-base...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Multidisciplinary Digital Publishing Institute (MDPI)
2022
|
| Subjects: | |
| Online Access: | https://eprints.ums.edu.my/id/eprint/34643/1/FULL%20TEXT.pdf https://eprints.ums.edu.my/id/eprint/34643/2/ABSTRACT.pdf |
| _version_ | 1796911629277855744 |
|---|---|
| author | Muthu Subash Kavitha Prakash Gangadaran Aurelia Jackson Balu Alagar Venmathi Maran Takio Kurita Ahn, Byeong-Cheol |
| author_facet | Muthu Subash Kavitha Prakash Gangadaran Aurelia Jackson Balu Alagar Venmathi Maran Takio Kurita Ahn, Byeong-Cheol |
| author_sort | Muthu Subash Kavitha |
| collection | UMS |
| description | Early detection of colorectal cancer can significantly facilitate clinicians’ decision-making and reduce their workload. This can be achieved using automatic systems with endoscopic and histological images. Recently, the success of deep learning has motivated the development of image- and video-based polyp identification and segmentation. Currently, most diagnostic colonoscopy rooms utilize artificial intelligence methods that are considered to perform well in predicting invasive cancer. Convolutional neural network-based architectures, together with image patches and preprocesses are often widely used. Furthermore, learning transfer and end-to-end learning techniques have been adopted for detection and localization tasks, which improve accuracy and reduce user dependence with limited datasets. However, explainable deep networks that provide transparency, interpretability, reliability, and fairness in clinical diagnostics are preferred. In this review, we summarize the latest advances in such models, with or without transparency, for the prediction of colorectal cancer and also address the knowledge gap in the upcoming technology. |
| first_indexed | 2024-03-06T03:21:32Z |
| format | Article |
| id | ums.eprints-34643 |
| institution | Universiti Malaysia Sabah |
| language | English English |
| last_indexed | 2024-03-06T03:21:32Z |
| publishDate | 2022 |
| publisher | Multidisciplinary Digital Publishing Institute (MDPI) |
| record_format | dspace |
| spelling | ums.eprints-346432022-10-31T01:21:30Z https://eprints.ums.edu.my/id/eprint/34643/ Deep neural network models for colon cancer screening Muthu Subash Kavitha Prakash Gangadaran Aurelia Jackson Balu Alagar Venmathi Maran Takio Kurita Ahn, Byeong-Cheol RC254-282 Neoplasms. Tumors. Oncology Including cancer and carcinogens Early detection of colorectal cancer can significantly facilitate clinicians’ decision-making and reduce their workload. This can be achieved using automatic systems with endoscopic and histological images. Recently, the success of deep learning has motivated the development of image- and video-based polyp identification and segmentation. Currently, most diagnostic colonoscopy rooms utilize artificial intelligence methods that are considered to perform well in predicting invasive cancer. Convolutional neural network-based architectures, together with image patches and preprocesses are often widely used. Furthermore, learning transfer and end-to-end learning techniques have been adopted for detection and localization tasks, which improve accuracy and reduce user dependence with limited datasets. However, explainable deep networks that provide transparency, interpretability, reliability, and fairness in clinical diagnostics are preferred. In this review, we summarize the latest advances in such models, with or without transparency, for the prediction of colorectal cancer and also address the knowledge gap in the upcoming technology. Multidisciplinary Digital Publishing Institute (MDPI) 2022 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/34643/1/FULL%20TEXT.pdf text en https://eprints.ums.edu.my/id/eprint/34643/2/ABSTRACT.pdf Muthu Subash Kavitha and Prakash Gangadaran and Aurelia Jackson and Balu Alagar Venmathi Maran and Takio Kurita and Ahn, Byeong-Cheol (2022) Deep neural network models for colon cancer screening. Cancers, 14 (3707). pp. 1-14. ISSN 2072-6694 https://www.mdpi.com/2072-6694/14/15/3707/htm https://doi.org/10.3390/cancers14153707 https://doi.org/10.3390/cancers14153707 |
| spellingShingle | RC254-282 Neoplasms. Tumors. Oncology Including cancer and carcinogens Muthu Subash Kavitha Prakash Gangadaran Aurelia Jackson Balu Alagar Venmathi Maran Takio Kurita Ahn, Byeong-Cheol Deep neural network models for colon cancer screening |
| title | Deep neural network models for colon cancer screening |
| title_full | Deep neural network models for colon cancer screening |
| title_fullStr | Deep neural network models for colon cancer screening |
| title_full_unstemmed | Deep neural network models for colon cancer screening |
| title_short | Deep neural network models for colon cancer screening |
| title_sort | deep neural network models for colon cancer screening |
| topic | RC254-282 Neoplasms. Tumors. Oncology Including cancer and carcinogens |
| url | https://eprints.ums.edu.my/id/eprint/34643/1/FULL%20TEXT.pdf https://eprints.ums.edu.my/id/eprint/34643/2/ABSTRACT.pdf |
| work_keys_str_mv | AT muthusubashkavitha deepneuralnetworkmodelsforcoloncancerscreening AT prakashgangadaran deepneuralnetworkmodelsforcoloncancerscreening AT aureliajackson deepneuralnetworkmodelsforcoloncancerscreening AT balualagarvenmathimaran deepneuralnetworkmodelsforcoloncancerscreening AT takiokurita deepneuralnetworkmodelsforcoloncancerscreening AT ahnbyeongcheol deepneuralnetworkmodelsforcoloncancerscreening |