用深度学习检测肠鸣音，准确率96%。
BowelRCNN: Region-based Convolutional Neural Network System for Bowel Sound Auscultation
- 将音频转为频谱图，用区域卷积网络定位肠鸣事件
- 在19名患者数据上实现96%准确率、71%F1分数
- 适合医疗辅助诊断与可穿戴听诊设备研发
肠鸣音是反映肠道活动的声学信号，具有识别胃肠道疾病的应用潜力。本文提出BowelRCNN系统，结合音频采集、频谱分析与基于区域的卷积神经网络架构。该系统在来自19名患者的实录数据集上进行训练与验证，数据包含60分钟经整理和标注的音频。BowelRCNN在检测任务中达到96%的分类准确率与71%的F1分数。研究证明了卷积神经网络在肠鸣音听诊中的可行性，性能可媲美递归-卷积方法。
原文摘要 · Abstract (English)
Sound events representing intestinal activity detection is a diagnostic tool with potential to identify gastrointestinal conditions. This article introduces BowelRCNN, a novel bowel sound detection system that uses audio recording, spectrogram analysys and region-based convolutional neural network (RCNN) architecture. The system was trained and validated on a real recording dataset gathered from 19 patients, comprising 60 minutes of prepared and annotated audio data. BowelRCNN achieved a classification accuracy of 96% and an F1 score of 71%. This research highlights the feasibility of using CNN architectures for bowel sound auscultation, achieving results comparable to those of recurrent-convolutional methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。