基于卷积网络建立的小肠胶囊内镜人工智能辅助自动识别系统

Establishment of an artificial intelligence‑assisted system for automatic lesion recognition in small intestinal capsule endoscopy based on convolutional networks

摘要:

目的 基于卷积神经网络开发一款能够自动识别多种病变的小肠胶囊内镜人工智能辅助系统，并测试其性能。方法 采用3个小肠胶囊内镜图像数据集进行深度学习模型的训练（n=26 638）、验证（n=6 652）和测试（n=1 013），每一数据集均包括了12类小肠病变（血管畸形、出血、糜烂、红斑、狭窄、淋巴管扩张、黏膜下肿瘤、息肉、淋巴滤泡、异物、静脉以及正常黏膜）。测试时，使用接收者操作特征曲线下面积（area under curve，AUC）、敏感度、特异度、精确度、准确率、F1分数等衡量模型的性能，并开展人机对比实验。结果 最优模型（EfficientNet‑CE）诊断12类小肠病变的敏感度（加权平均）为86.28%，特异度（加权平均）为98.67%，AUC（加权平均）为0.987 4。人机大赛中，最优模型（EfficientNet‑CE）在准确率（加权平均：86.28%）和处理速度（52.43帧/s）方面均表现出色，处理速度约为低年资内镜医师（阅片经验不足3年）的42.4倍、高年资内镜医师（具有超过5年阅片经验）的40.3倍。结论 基于卷积神经网络开发的深度学习模型能够快速、准确地识别12类小肠病变，通过高灵敏度的识别能力，能够有效辅助内镜医师进行小肠胶囊内镜检查的阅片工作。

Abstract:

Objective To develop and validate an artificial intelligence-assisted system based on convolutional neural networks (CNN) for automatic lesion recognition in small intestinal capsule endoscopy. Methods Three small intestinal capsule endoscopy datasets were used for training (n=26 638), validating (n=6 652), and testing (n=1 013) the deep learning model, covering 12 lesion categories, including vascular malformations, hemorrhage, erosion, erythema, stenosis, lymphangiectasia, submucosal tumors, polyps, lymphoid follicles, foreign bodies, veins, and normal mucosa. CNN performance was measured by area under receiver operating characteristic curve (AUC), sensitivity, specificity, precision, accuracy, and F1 score, with comparisons with endoscopists of different experience levels. Results The top-performing model (EfficientNet-CE) achieved 86.28% sensitivity, 98.67% specificity, and AUC of 0.987 4 across all categories. It demonstrated high accuracy (86.28%) and a processing speed of 52.43 frames per second, approximately 42.4 times faster than junior endoscopists (<3 years'' experience) and 40.3 times faster than senior endoscopists (>5 years'' experience). Conclusion The CNN-based model allows rapid, accurate identification of 12 small intestinal lesion types and effectively supports endoscopists in reviewing capsule endoscopy examinations due to its high sensitivity.