Real-time multi-class detection of colorectal polyps based on the colon-YOLO network

Colorectal adenomatous polyps are key precursors to colorectal cancer (CRC), but their accurate classification during endoscopy remains challenging due to variability in physician expertise and difficulties in detecting certain lesion types, such as sessile serrated adenomas/polyps (SSAP). To addres...

Full description

Saved in:
Bibliographic Details
Main Author: Yiliu Liu
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016825006660
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229282769895424
author Yiliu Liu
author_facet Yiliu Liu
author_sort Yiliu Liu
collection DOAJ
description Colorectal adenomatous polyps are key precursors to colorectal cancer (CRC), but their accurate classification during endoscopy remains challenging due to variability in physician expertise and difficulties in detecting certain lesion types, such as sessile serrated adenomas/polyps (SSAP). To address this, we developed Colon-YOLO, a real-time polyp detection network based on YOLOv5, incorporating ConvNeXt for global feature extraction, a SimAM attention mechanism for enhanced 3D feature weighting, and a concentrated feature pyramid attention layer for improved context capture. A novel Soft-SIoU-NMS method was introduced to boost occlusion detection and convergence speed. Evaluated on both remote and edge devices, the model achieved a 6.3 % mAP improvement (IoU=0.5) over YOLOv5, with inference speeds of 120.5 FPS (remote) and 28.57 FPS (edge), meeting real-time clinical needs. This approach enhances polyp detection accuracy, reducing missed diagnoses and supporting CRC prevention.
format Article
id doaj-art-0ea3a492243746dfa8f84d50bae02afc
institution Kabale University
issn 1110-0168
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-0ea3a492243746dfa8f84d50bae02afc2025-08-22T04:55:30ZengElsevierAlexandria Engineering Journal1110-01682025-08-0112759560510.1016/j.aej.2025.05.045Real-time multi-class detection of colorectal polyps based on the colon-YOLO networkYiliu Liu0China-Japan Union Hospital of Jilin University, 126 Xiantai Street, Changchun 130033, ChinaColorectal adenomatous polyps are key precursors to colorectal cancer (CRC), but their accurate classification during endoscopy remains challenging due to variability in physician expertise and difficulties in detecting certain lesion types, such as sessile serrated adenomas/polyps (SSAP). To address this, we developed Colon-YOLO, a real-time polyp detection network based on YOLOv5, incorporating ConvNeXt for global feature extraction, a SimAM attention mechanism for enhanced 3D feature weighting, and a concentrated feature pyramid attention layer for improved context capture. A novel Soft-SIoU-NMS method was introduced to boost occlusion detection and convergence speed. Evaluated on both remote and edge devices, the model achieved a 6.3 % mAP improvement (IoU=0.5) over YOLOv5, with inference speeds of 120.5 FPS (remote) and 28.57 FPS (edge), meeting real-time clinical needs. This approach enhances polyp detection accuracy, reducing missed diagnoses and supporting CRC prevention.http://www.sciencedirect.com/science/article/pii/S1110016825006660Deep learningColorectal polypsReal-time multi-class detectionEdge deployment
spellingShingle Yiliu Liu
Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
Alexandria Engineering Journal
Deep learning
Colorectal polyps
Real-time multi-class detection
Edge deployment
title Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
title_full Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
title_fullStr Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
title_full_unstemmed Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
title_short Real-time multi-class detection of colorectal polyps based on the colon-YOLO network
title_sort real time multi class detection of colorectal polyps based on the colon yolo network
topic Deep learning
Colorectal polyps
Real-time multi-class detection
Edge deployment
url http://www.sciencedirect.com/science/article/pii/S1110016825006660
work_keys_str_mv AT yiliuliu realtimemulticlassdetectionofcolorectalpolypsbasedonthecolonyolonetwork