Construction of artificial intelligence models for multi-category lesion detection in small bowel capsule endoscopy based on various YOLO neural networks(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2025年第5期
- Page:
- 693-700
- Research Field:
- 医学人工智能
- Publishing date:
Info
- Title:
- Construction of artificial intelligence models for multi-category lesion detection in small bowel capsule endoscopy based on various YOLO neural networks
- Author(s):
- CHEN Jian1; WANG Ganhong2; DAI Jianjun1; XIA Kaijian3; XU Xiaodan1; SUN Ying1
- 1. Department of Gastroenterology, Changshu No.1 People’s Hospital, Changshu 215500, China; 2. Department of Gastroenterology, Changshu Hospital of Traditional Chinese Medicine, Changshu 215500, China; 3. Changshu Key Laboratory of Medical Artificial Intelligence and Big Data, Changshu 215500, China
- Keywords:
- small bowel lesion; YOLOv10; artificial intelligence; small bowel capsule endoscopy; object detection
- PACS:
- R574.5；R318
- DOI:
- 10.3969/j.issn.1005-202X.2025.05.021
- Abstract:
- Objective To construct YOLOv10 based artificial intelligence (AI) models for the automatic detection in small bowel capsule endoscopy (SBCE) images. Methods SBCE data from two centers was collected, including 23 115 images and 35 412 annotated labels covering 11 categories of small bowel lesions. The images were annotated using the LabelMe tool and converted into the YOLO format required for deep learning model development. The pre-trained YOLOv10 and YOLOv8 models were used for transfer learning training on the constructed dataset. Model performance was comprehensively evaluated using metrics such as precision, accuracy, sensitivity, specificity, false-positive rate, and detection speed. Finally, the models were deployed on local computers for real-time detection of SBCE images and videos. Results Six different versions of YOLO object detection models were developed, namely YOLOv8n, YOLOv8s, YOLOv8m, YOLOv10n, YOLOv10s, and YOLOv10m. On the validation set, YOLOv10s model achieved the best mAP50 (0.795); although its inference latency was not the fastest (4.803 ms/img), it met the requirements for clinical application. On the test set, YOLOv10s performed well, with an accuracy of 92.69%, a sensitivity of 89.23%, and a false-positive rate of 4.78%. Especially, in category-specific inference, the highest sensitivity was for "bleeding" at 96.41%, while the lowest was for "narrowing" at 82.29%. Conclusion The model constructed based on YOLOv10 neural network can rapidly and accurately detect and classify various small bowel lesions, exhibiting significant clinical application potential.
Last Update: 2025-06-03