Login / Signup

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

Jae Hyon ParkInsun ParkKichang HanJongjin YoonYongsik SimSoo Jin KimJong Yun WonShina LeeJoon Ho KwonSungmo MoonGyoung Min KimMan-Deuk Kim
Published in: Korean journal of radiology (2022)
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.
Keyphrases
  • deep learning
  • public health
  • peritoneal dialysis
  • chronic kidney disease
  • end stage renal disease
  • artificial intelligence
  • machine learning
  • convolutional neural network