Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network_Journal of Biomedical Engineering

Authors：

LI Yiyang ¹ , ZHAO Jiayi ² , YU Ruoyi ² , LIU Huixiang ^3,4 ,  LIANG Shuang ^1,4,5 ,  GU Yu ^1,4,5

1. School of Biomedical Engineering, Capital Medical University, Beijing 100069, P. R. China;
2. School of Basic Medical Sciences, Capital Medical University, Beijing 100069, P. R. China;
3. School of Automation, Beijing Information Science and Technology University, Beijing 100192, P. R. China;
4. Beijing Key Laboratory of Fundamicationental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing 100069, P. R. China;
5. Laboratory for Clinical Medicine, Capital Medical University, Beijing 100069, P. R. China;

Corresponding author：

LIANG Shuang, Email: shliang@ccmu.edu.cn; GU Yu, Email: ygu@ccmu.edu.cn

Keywords：

Colorectal polyps; Colorectal cancer; Target detection; Computer-aided diagnosis; Deep learning

DOI：

10.7507/1001-5515.202312014

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

Citation： LI Yiyang, ZHAO Jiayi, YU Ruoyi, LIU Huixiang, LIANG Shuang, GU Yu. Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network. Journal of Biomedical Engineering, 2024, 41(5): 911-918. doi: 10.7507/1001-5515.202312014 Copy

1.	周雄, 胡明, 李子帅, 等. 2020年全球及中国结直肠癌流行状况分析. 海军军医大学学报, 2022, 43(12): 1356-1364.
2.	田晓彤, 卜淑蕊. 结直肠息肉的临床特征研究. 临床内科杂志, 2022, 39(2): 91-94.
3.	禹蓉, 董卫国, 田山, 等. 不同病理类型结直肠息肉癌变的临床研究进展. 中国全科医学, 2023, 26(14): 1790-1794.
4.	姜华, 曹金恒. 结肠镜下结直肠息肉分型与治疗的研究进展. 内蒙古医学杂志, 2022, 54(9): 1060-1064.
5.	王成龙, 赵子夜, 王颢, 等. 结肠镜检查质量控制研究进展. 结直肠肛门外科, 2021, 27(6): 527-530,535.
6.	Corley D A, Jensen C D, Marks A R, et al. Adenoma detection rate and risk of colorectal cancer and death. New England Journal of Medicine, 2014, 370(14): 1298-1306.
7.	林燕凤, 赵舷宏, 付朝丽, 等. 以人工智能肠道图像识别模型评估结肠镜检查前肠道准备. 中国医学影像术, 2023, 39(7): 1034-1038.
8.	Barclay R L, Vicari J J, Greenlaw R L. Effect of a time-dependent colonoscopic withdrawal protocol on adenoma detection during screening colonoscopy. Clinical Gastroenterology and Hepatology, 2008, 6(10): 1091-1098.
9.	王树玲, 康争春, 赵胜兵, 等. 加强结肠镜检查规范培训,提高结肠腺瘤检出率. 海军军医大学学报, 2023, 44(3): 265-271.
10.	冯燕, 高峰. 结直肠息肉内镜检出率影响因素分析. 新疆医学, 2017, 47(11): 1313-1317.
11.	Bretthauer M, Kaminski MF, Løberg M, et al. Population-based colonoscopy screening for colorectal cancer: a randomized clinical trial. JAMA Intern Med, 2016, 176(7): 894-902.
12.	熊逢春, 吴小微, 王计. 人工智能在结直肠息肉检测与诊断中的应用. 现代消化及介入诊疗, 2022, 27(6): 663-667.
13.	李小雷. 人工智能在医学影像图像处理中的研究进展. 中国医学计算机成像杂志, 2023, 29(4): 454-457.
14.	Byrne M F, Shahidi N, Rex D K. Will computer-aided detection and diagnosis revolutionize colonoscopy?. Gastroenterology, 2017, 153(6): 1460-1464.
15.	木合塔尔·色特瓦勒迪, 古丽巴哈尔·司马义. 人工智能在诊断结直肠癌癌前病变中的应用. 胃肠病学和肝病学杂志, 2023, 32(5): 584-587.
16.	王丽梅, 冯璜, 陈卫昌, 等. 基于人工智能的结直肠息肉辅助诊断系统可提高息肉检出率: 一项前瞻性随机对照研究. 胃肠病学, 2022, 27(3): 163-167.
17.	Sánchez-Peralta L F, Bote-Curiel L, Picón A, et al. Deep learning to find colorectal polyps in colonoscopy: a systematic literature review. Artificial Intelligence in Medicine, 2020, 108: 101923.
18.	刘涛, 丁雪妍, 张冰冰, 等. 改进YOLOv5的遥感图像检测方法. 计算机工程与应用, 2023, 59(10): 253-261.
19.	Sornapudi S, Meng F, Yi S. Region-based automated localization of colonoscopy and wireless capsule endoscopy polyps. Applied Sciences. 2019, 9(12): 2404.
20.	考文涛, 李明, 马金刚. 卷积神经网络在结直肠息肉辅助诊断中的应用综述. 计算机科学与探索, 2024, 18(3): 627-645.
21.	Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas: IEEE, 2016: 779-788.
22.	Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector//Computer Vision – ECCV 2016, Amsterdam: Springer International Publishing, 2016: 21–37.
23.	朱豪, 周顺勇, 刘学, 等. 基于深度学习的单阶段目标检测算法综述. 工业控制计算机, 2023, 36(4): 101-103.
24.	邱天衡, 王玲, 王鹏, 等. 基于改进YOLOv5的目标检测算法研究. 计算机工程与应用, 2022, 58(13): 63-73.
25.	梁礼明, 何安军, 李仁杰, 等. 跨尺度跨维度的自适应Transformer网络应用于结直肠息肉分割. 光学精密工程, 2023, 31(18): 2700-2712.
26.	徐昌佳, 易见兵, 曹锋, 等. 采用DoubleUNet网络的结直肠息肉分割算法. 光学精密工程, 2022, 30(8): 970-983.
27.	Wan J, Chen B, Yu Y. Polyp detection from colorectum images by using attentive YOLOv5. Diagnostics, 2021, 11(12): 2264.
28.	司丙奇, 王志武, 姜萍萍, 等. 基于改进 YOLOv5 网络的内窥镜息肉检测. 中国新通信, 2022, 24(11): 123-128.
29.	Wittenberg T, Zobel P, Rathke M, et al. Computeraided detection of polyps in whitelight- colonoscopy images using deep neural networks. Current Directions in Biomedical Engineering, 2019, 5(1): 231-234.
30.	Liu M, Jiang J, Wang Z. Colonic polyp detection in endoscopic videos with single shot detection based deep convolutional neural network. IEEE Access, 2019, 7: 75058-75066.

1. 周雄, 胡明, 李子帅, 等. 2020年全球及中国结直肠癌流行状况分析. 海军军医大学学报, 2022, 43(12): 1356-1364.
2. 田晓彤, 卜淑蕊. 结直肠息肉的临床特征研究. 临床内科杂志, 2022, 39(2): 91-94.
3. 禹蓉, 董卫国, 田山, 等. 不同病理类型结直肠息肉癌变的临床研究进展. 中国全科医学, 2023, 26(14): 1790-1794.
4. 姜华, 曹金恒. 结肠镜下结直肠息肉分型与治疗的研究进展. 内蒙古医学杂志, 2022, 54(9): 1060-1064.
5. 王成龙, 赵子夜, 王颢, 等. 结肠镜检查质量控制研究进展. 结直肠肛门外科, 2021, 27(6): 527-530,535.
6. Corley D A, Jensen C D, Marks A R, et al. Adenoma detection rate and risk of colorectal cancer and death. New England Journal of Medicine, 2014, 370(14): 1298-1306.
7. 林燕凤, 赵舷宏, 付朝丽, 等. 以人工智能肠道图像识别模型评估结肠镜检查前肠道准备. 中国医学影像术, 2023, 39(7): 1034-1038.
8. Barclay R L, Vicari J J, Greenlaw R L. Effect of a time-dependent colonoscopic withdrawal protocol on adenoma detection during screening colonoscopy. Clinical Gastroenterology and Hepatology, 2008, 6(10): 1091-1098.
9. 王树玲, 康争春, 赵胜兵, 等. 加强结肠镜检查规范培训,提高结肠腺瘤检出率. 海军军医大学学报, 2023, 44(3): 265-271.
10. 冯燕, 高峰. 结直肠息肉内镜检出率影响因素分析. 新疆医学, 2017, 47(11): 1313-1317.
11. Bretthauer M, Kaminski MF, Løberg M, et al. Population-based colonoscopy screening for colorectal cancer: a randomized clinical trial. JAMA Intern Med, 2016, 176(7): 894-902.
12. 熊逢春, 吴小微, 王计. 人工智能在结直肠息肉检测与诊断中的应用. 现代消化及介入诊疗, 2022, 27(6): 663-667.
13. 李小雷. 人工智能在医学影像图像处理中的研究进展. 中国医学计算机成像杂志, 2023, 29(4): 454-457.
14. Byrne M F, Shahidi N, Rex D K. Will computer-aided detection and diagnosis revolutionize colonoscopy?. Gastroenterology, 2017, 153(6): 1460-1464.
15. 木合塔尔·色特瓦勒迪, 古丽巴哈尔·司马义. 人工智能在诊断结直肠癌癌前病变中的应用. 胃肠病学和肝病学杂志, 2023, 32(5): 584-587.
16. 王丽梅, 冯璜, 陈卫昌, 等. 基于人工智能的结直肠息肉辅助诊断系统可提高息肉检出率: 一项前瞻性随机对照研究. 胃肠病学, 2022, 27(3): 163-167.
17. Sánchez-Peralta L F, Bote-Curiel L, Picón A, et al. Deep learning to find colorectal polyps in colonoscopy: a systematic literature review. Artificial Intelligence in Medicine, 2020, 108: 101923.
18. 刘涛, 丁雪妍, 张冰冰, 等. 改进YOLOv5的遥感图像检测方法. 计算机工程与应用, 2023, 59(10): 253-261.
19. Sornapudi S, Meng F, Yi S. Region-based automated localization of colonoscopy and wireless capsule endoscopy polyps. Applied Sciences. 2019, 9(12): 2404.
20. 考文涛, 李明, 马金刚. 卷积神经网络在结直肠息肉辅助诊断中的应用综述. 计算机科学与探索, 2024, 18(3): 627-645.
21. Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas: IEEE, 2016: 779-788.
22. Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector//Computer Vision – ECCV 2016, Amsterdam: Springer International Publishing, 2016: 21–37.
23. 朱豪, 周顺勇, 刘学, 等. 基于深度学习的单阶段目标检测算法综述. 工业控制计算机, 2023, 36(4): 101-103.
24. 邱天衡, 王玲, 王鹏, 等. 基于改进YOLOv5的目标检测算法研究. 计算机工程与应用, 2022, 58(13): 63-73.
25. 梁礼明, 何安军, 李仁杰, 等. 跨尺度跨维度的自适应Transformer网络应用于结直肠息肉分割. 光学精密工程, 2023, 31(18): 2700-2712.
26. 徐昌佳, 易见兵, 曹锋, 等. 采用DoubleUNet网络的结直肠息肉分割算法. 光学精密工程, 2022, 30(8): 970-983.
27. Wan J, Chen B, Yu Y. Polyp detection from colorectum images by using attentive YOLOv5. Diagnostics, 2021, 11(12): 2264.
28. 司丙奇, 王志武, 姜萍萍, 等. 基于改进 YOLOv5 网络的内窥镜息肉检测. 中国新通信, 2022, 24(11): 123-128.
29. Wittenberg T, Zobel P, Rathke M, et al. Computeraided detection of polyps in whitelight- colonoscopy images using deep neural networks. Current Directions in Biomedical Engineering, 2019, 5(1): 231-234.
30. Liu M, Jiang J, Wang Z. Colonic polyp detection in endoscopic videos with single shot detection based deep convolutional neural network. IEEE Access, 2019, 7: 75058-75066.

Previous Article
Feature detection of B-ultrasound images of intussusception in children based on improved YOLOv8n LIUChenyu, XU Jian, LI Ke, WANG Lu
Next Article
High stability enhanced ultrasonic microfluidic structure with flexible tip coupled bubbles LIUYue, ZHOU Yuying, ZHANG Wenchang, CHEN Shaohua, LIANG Shengfa

Journal of Biomedical Engineering

Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content