Can Programmable Gradient Information Enhance Polyp Segmentation?

Colorectal cancer ranks as the third leading cause of cancer-related deaths globally, with early detection and removal of polyps crucial in reducing mortality. Despite colonoscopy being an effective diagnostic tool, up to 28% of polyps are missed due to operator variability. Automated polyp segmenta...

Full description

Saved in:
Bibliographic Details
Main Authors: Manas Mehta, C. Gunavathi, Nevin Mathews, D. Ruby
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10752496/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846160683621679104
author Manas Mehta
C. Gunavathi
Nevin Mathews
D. Ruby
author_facet Manas Mehta
C. Gunavathi
Nevin Mathews
D. Ruby
author_sort Manas Mehta
collection DOAJ
description Colorectal cancer ranks as the third leading cause of cancer-related deaths globally, with early detection and removal of polyps crucial in reducing mortality. Despite colonoscopy being an effective diagnostic tool, up to 28% of polyps are missed due to operator variability. Automated polyp segmentation algorithms provide a solution to enhance diagnostic accuracy. However, challenges such as boundary pixel misdetection, varying polyp sizes, and poor model generalization remain prevalent. In this paper, we propose a novel polyp segmentation approach utilizing the YOLOv9 model and its training strategy called Programmable Gradient Information. The study evaluates whether these innovations outperform state-of-the-art polyp segmentation models and introduce a new direction for future architectures. This study addresses the challenges and significantly outperforms state-of-the-art models across five widely-used public datasets. The YOLOv9 based PGI approach exhibits remarkable generalization ability, and demonstrates superior performance, achieving mDice scores of 0.932 on CVC-300, 0.866 on CVC-ColonDB, 0.889 on ETIS-Larib, and 0.919 on KvasirSEG. The model’s high inference speed of 42.3 FPS, make it suitable for real-time applications. These results highlight its potential to improve early colorectal cancer detection.
format Article
id doaj-art-61c3eda19ab044e3ad51b25e28ace676
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-61c3eda19ab044e3ad51b25e28ace6762024-11-22T00:01:43ZengIEEEIEEE Access2169-35362024-01-011216927716929010.1109/ACCESS.2024.349699910752496Can Programmable Gradient Information Enhance Polyp Segmentation?Manas Mehta0https://orcid.org/0009-0000-5077-2998C. Gunavathi1https://orcid.org/0000-0002-4996-069XNevin Mathews2https://orcid.org/0009-0008-0542-0406D. Ruby3https://orcid.org/0000-0001-8938-5020School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Vellore, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Vellore, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Vellore, IndiaColorectal cancer ranks as the third leading cause of cancer-related deaths globally, with early detection and removal of polyps crucial in reducing mortality. Despite colonoscopy being an effective diagnostic tool, up to 28% of polyps are missed due to operator variability. Automated polyp segmentation algorithms provide a solution to enhance diagnostic accuracy. However, challenges such as boundary pixel misdetection, varying polyp sizes, and poor model generalization remain prevalent. In this paper, we propose a novel polyp segmentation approach utilizing the YOLOv9 model and its training strategy called Programmable Gradient Information. The study evaluates whether these innovations outperform state-of-the-art polyp segmentation models and introduce a new direction for future architectures. This study addresses the challenges and significantly outperforms state-of-the-art models across five widely-used public datasets. The YOLOv9 based PGI approach exhibits remarkable generalization ability, and demonstrates superior performance, achieving mDice scores of 0.932 on CVC-300, 0.866 on CVC-ColonDB, 0.889 on ETIS-Larib, and 0.919 on KvasirSEG. The model’s high inference speed of 42.3 FPS, make it suitable for real-time applications. These results highlight its potential to improve early colorectal cancer detection.https://ieeexplore.ieee.org/document/10752496/Computer visiondeep learningpolyp segmentationprogrammable gradient informationYOLOv9
spellingShingle Manas Mehta
C. Gunavathi
Nevin Mathews
D. Ruby
Can Programmable Gradient Information Enhance Polyp Segmentation?
IEEE Access
Computer vision
deep learning
polyp segmentation
programmable gradient information
YOLOv9
title Can Programmable Gradient Information Enhance Polyp Segmentation?
title_full Can Programmable Gradient Information Enhance Polyp Segmentation?
title_fullStr Can Programmable Gradient Information Enhance Polyp Segmentation?
title_full_unstemmed Can Programmable Gradient Information Enhance Polyp Segmentation?
title_short Can Programmable Gradient Information Enhance Polyp Segmentation?
title_sort can programmable gradient information enhance polyp segmentation
topic Computer vision
deep learning
polyp segmentation
programmable gradient information
YOLOv9
url https://ieeexplore.ieee.org/document/10752496/
work_keys_str_mv AT manasmehta canprogrammablegradientinformationenhancepolypsegmentation
AT cgunavathi canprogrammablegradientinformationenhancepolypsegmentation
AT nevinmathews canprogrammablegradientinformationenhancepolypsegmentation
AT druby canprogrammablegradientinformationenhancepolypsegmentation