Construction of an artificial intelligence-assisted system for auto-matic detection of multiple lesions in the small intestine based on various convolutional neural networks
Objective To develop an artificial intelligence-assisted system based on various convolutional neural networks for automatically detecting 11 types of small intestinal lesion images captured by capsule endoscopy(CE),aiming to enhance the efficiency,accuracy,and objectivity of diagnoses.Methods Images were collected from three medical centers across different countries using three different brands of CE equip-ment,building an image dataset for training and testing various convolutional neural network models,totaling 13 683 images and 15 117 annotated labels.The model performance metrics included mean precision,accuracy,sensitivity,specificity,false-positive rate,and detection speed.Results Two YOLO models and two RTMDet models were developed in this study.In a test set containing 2 729 CE images(4 801 annotated labels),the RTMDet_m model achieved the best mAP50(82.58%),but also showed the slowest latency at 47.28 frames per second.Additionally,this model achieved an overall sensitivity of 82.76%and an accuracy of 95.91%;in category-specific inference,the highest sensitivity was observed in the"bleeding"category,while the lowest was for"submucosal tumor".Conclusion The artificial intelligence models developed using mixed-brand CE images can rapidly and accurately detect and classify 11 types of small intestinal lesions,demonstrat-ing significant clinical application potentials in enhancing the efficiency and accuracy of CE diagnoses.
small intestinal lesionsconvolutional neural networkartificial intelligencecapsule endoscopyobject detection
万方数据
维普
