基于深度学习听诊分析筛查需行血管成形术的血液透析自体动静脉瘘显著狭窄的可行性
前瞻性纳入40例功能障碍自体动静脉瘘患者,PTA前后用无线电子听诊器录制瘘口数字音频并转换为梅尔频谱图,构建DenseNet201、EfficientNetB5和ResNet50深度卷积神经网络模型,以DSA为参考标准评估诊断≥50%动静脉瘘狭窄的性能;ResNet50和EfficientNetB5的AUC分别为0.99和0.98,但Grad-CAM热图仅ResNet50突出显示了与狭窄相关的区域。
要点
- 梅尔频谱图结合深度卷积神经网络可用于预测需行PTA的≥50%自体动静脉瘘狭窄。
- ResNet50模型预测≥50%动静脉瘘狭窄的AUC为0.99,EfficientNetB5为0.98。
- Grad-CAM热图显示仅ResNet50突出显示梅尔频谱图中与动静脉瘘狭窄相关的区域。
核心结论
- 基于梅尔频谱图的深度卷积神经网络模型,尤其是ResNet50,在本可行性研究中成功预测了需行PTA的显著动静脉瘘狭窄,并可能潜在用于动静脉瘘监测。
研究设计与样本
- 前瞻性可行性研究,纳入40例功能障碍自体动静脉瘘患者(男24例、女16例,中位年龄62.5岁),PTA前后用无线电子听诊器录制瘘口数字音频,转换为梅尔频谱图后构建DenseNet201、EfficientNetB5和ResNet50深度卷积神经网络模型,以数字减影血管造影为参考标准。
关键影像表现/征象
- PTA前瘘口听诊音的梅尔频谱图呈现与狭窄性动静脉瘘患者异常高调杂音伴收缩期增强相对应的模式。
诊断标准与关键数值
- 以数字减影血管造影为参考标准,诊断≥50%动静脉瘘狭窄。
- ResNet50模型在优化epoch下预测≥50%动静脉瘘狭窄的受试者工作特征曲线下面积为0.99。
- EfficientNetB5模型在优化epoch下预测≥50%动静脉瘘狭窄的受试者工作特征曲线下面积为0.98。
临床应用与阅片要点
- 作者认为基于梅尔频谱图的深度卷积神经网络模型可能潜在用于动静脉瘘监测。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA).
MATERIALS AND METHODS: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions.
RESULTS: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram.
CONCLUSION: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.
引用
- Park JH, Park I, Han K, et al. Feasibility of Deep Learning-Based Analysis of Auscultation for Screening Significant Stenosis of Native Arteriovenous Fistula for Hemodialysis Requiring Angioplasty. Korean J Radiol. 2022. PMID: 36174999. doi:10.3348/kjr.2022.0364
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。