基于YOLO v11网络的小肠胶囊内镜病变自动分割AI系统开发OA

Objective An artificial intelligence-assisted system was developed for the automatic detection and segmentation of eight types of small bowel lesions in small bowel capsule endoscopy(SBCE)images.Methods SBCE images were collected from three datasets,and lesion annotations performed using the LabeMe tool with polygonal segmentation,later converted into a You Only Look Once(YOLO)-compatible format for training,validation and testing of the neural network model.The dataset comprised 13,983 images with 17 911 annotated labels.Model performance was evaluated using precision,sensitivity,mean average pre-cision at an intersection-over-union(IoU)threshold of 50%(mAP50),mean average precision across IoU thresholds from 50%to 95%(mAP50～95),and inference speed.Results Five YOLO v11 segmentation models of different scales(v11n,v11s,v11m,v11l,v11x)were developed.Among them,YOLO v11m achieved the high-est mAP50(0.908)while maintaining a fast inference speed of 208.3 frames per second,making it the optimal model.On the external test set,YOLO v11m attained an overall mAP50 of 0.892 for segmenting the eight lesion types.The highest segmentation accuracy was observed for polyps and lymphangiectasia,with mAP50～95 values of 0.723 and 0.707 respectively,whereas the lowest performance was noted for the bleeding category,with an mAP50～95 of only 0.409.Conclusion The SBCE segmentation model YOLO v11m was developed based on the YOLO v11 neural network demonstrated strong lesion recognition capabilities,enabling precise multi-class lesion localization,classification and pixel-level contour delineation.These findings highlight its promising potential for clinical applications.