Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 26;15(1):6852.
doi: 10.1038/s41598-025-91467-1.

A colonic polyps detection algorithm based on an improved YOLOv5s

Jianjun Li  1   2 , Jinhui Zhao  3 , Yifan Wang  1 , Jinhui Zhu  4 , Yanhong Wei  1 , Junjiang Zhu  1 , Xiaolu Li  1 , Shubin Yan  2 , Qichun Zhang  5
Affiliations

A colonic polyps detection algorithm based on an improved YOLOv5s

Jianjun Li et al. Sci Rep. .

Abstract

Colon cancer is a prevalent malignancy, substantially it prevented most effectively from killing patients through early endoscopic detection. With the rapid development of artificial intelligence technology, the early diagnosis rate of colonic polyps achieves greater clinical efficacy for colon cancer by applying target detection algorithms to colonoscopy images. This paper presents two outcomes achieved through the application of the improved YOLOv5s algorithm with annotated microscopy images of clinical cases and publicly available polyp image data: (1) enhancement of the C3(Cross Stage Partial Networks) module with multiple layers to C3SE(Cross Stage Partial Networks with Squeeze-and-Excitation) via the attention mechanism SE (squeeze-and-excitation) and (2) fusion of higher-level features utilizing BiFPN (the weighted bi-directional feature pyramid network). Experimental comparisons are performed based on a new image dataset of colonic polyps among more than 6 target detection algorithms to validate the better detection capability. The tests indicate that the YOLOv5s + BiFPN and YOLOv5s-1st-2nd-C3SE models exhibit enhancements of detection capability compared to the YOLOv5 algorithm according to the main indicators of the mAP, accuracy, and recall. The YOLOv5s + SEBiFPN model demonstrate a substantial improvement over the YOLOv5s algorithm, and establishing a benchmark technology for advancing computer-assisted diagnostic systems is feasible.

Keywords: Convolutional neural network; Digestive endoscopy; Feature fusion; Target detection.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Real images of common digestive diseases. (a) Arti polyps. (b) Non-tipped polyps. (c) Tipped polyps. (d) Multiple polyps. (e) Colitis.
Fig. 2
Fig. 2
YOLOv5 network structure diagram.
Fig. 3
Fig. 3
CSPDarknet53 structure diagram.
Fig. 4
Fig. 4
Compression, excitation blocks.
Fig. 5
Fig. 5
Different forms of multi-scale feature fusion networks.
Fig. 6
Fig. 6
Backbone network structure.
Fig. 7
Fig. 7
Introduction to the BiFPN_Concat module.
Fig. 8
Fig. 8
Images of the actual stomach and intestine.
Fig. 9
Fig. 9
Image annotation.
Fig. 10
Fig. 10
XML file content.
Fig. 11
Fig. 11
Dataset distribution and bounding box characteristics for colonic polyp detection.
Fig. 12
Fig. 12
YOLOv5s + SEBifpn algorithm vs. YOLOv5s algorithm visualisations.
Fig. 13
Fig. 13
YOLOv5s + SEBifpn, YOLOv5s-1st-2nd-C3SE, YOLOv5s + Bifpn visualisation comparison.
Fig. 14
Fig. 14
YOLOv5s + SEBifpn algorithm detection visualisation.
Fig. 15
Fig. 15
Distribution of confidence levels comparison.
Fig. 16
Fig. 16
Training results of YOLOv5s + SEBifpn algorithm.
Fig. 17
Fig. 17
Training results of YOLOv5s algorithm.
See this image and copyright information in PMC

References

    1. Sung, H. et al. Global Cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin.71, 209–249. 10.3322/caac.21660 (2021). - PubMed
    1. Ciuti, G. et al. Frontiers of robotic endoscopic capsules: A review. J. Microbiol. Robot.11, 1–18. 10.1007/s12213-016-0087-x (2016). - PMC - PubMed
    1. Choi, I. H. et al. Collagenous gastoduodenitis in the form of a gastric ulcer. Korean J. Gastroenterol.80, 225–228. 10.4166/kjg.2022.079 (2022). - PubMed
    1. Chao, G., Zhu, Y. & Fang, L. Retrospective study of risk factors for colorectal adenomas and non-adenomatous polyps. Transl. Cancer Res.9, 1670–1677. 10.21037/tcr.2020.01.69 (2020). - PMC - PubMed
    1. Liu, J., Zhang, W., Liu, Y. & Zhang, Q. Polyp segmentation based on implicit edge-guided cross-layer fusion networks. Sci. Rep.14. 10.1038/s41598-024-62331-5 (2024). - PMC - PubMed

MeSH terms