Korean J Radiol.  2022 Oct;23(10):949-958. 10.3348/kjr.2022.0364.

Feasibility of Deep Learning-Based Analysis of Auscultation for Screening Significant Stenosis of Native Arteriovenous Fistula for Hemodialysis Requiring Angioplasty

• Park JH
• Park I
• Han K
• Yoon J
• Sim Y
• Kim SJ
• Won JY
• Lee S
• Kwon JH
• Moon S
• Kim GM
• Kim Md

• KMID: 2533326
• DOI: http://doi.org/10.3348/kjr.2022.0364

Abstract

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, GradCAM 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.

Keyword

Angioplasty; Deep learning; Arteriovenous fistula; Auscultation; Renal dialysis