Cross-institutional validation of a polar map-free 3D deep learning model for obstructive coronary artery disease prediction using myocardial perfusion imaging: insights into generalizability and bias.

Journal: European journal of nuclear medicine and molecular imaging
Published Date: Apr 8, 2025

Abstract

PURPOSE: Deep learning (DL) models for predicting obstructive coronary artery disease (CAD) using myocardial perfusion imaging (MPI) have shown potential for enhancing diagnostic accuracy. However, their ability to maintain consistent performance across institutions and demographics remains uncertain. This study aimed to investigate the generalizability and potential biases of an in-house MPI DL model between two hospital-based cohorts.

Authors

  • Yu-Cheng Shih
    Department of Nuclear Medicine, Far Eastern Memorial Hospital, New Taipei City, Taiwan.
  • Chi-Lun Ko
    Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan.
  • Shan-Ying Wang
    Department of Nuclear Medicine, Far Eastern Memorial Hospital, New Taipei City, Taiwan.
  • Chen-Yu Chang
    Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan.
  • Shau-Syuan Lin
    Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan.
  • Cheng-Wen Huang
    Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan.
  • Mei-Fang Cheng
    Department of Nuclear Medicine, National Taiwan University Hospital, Taipei, Taiwan.
  • Chung-Ming Chen
    Institute of Biomedical Engineering, National Taiwan University, Taipei 100, Taiwan.
  • Yen-Wen Wu
    Department of Nuclear Medicine, National Taiwan University Hospital, Taipei, Taiwan. wuyw0502@gmail.com.

Keywords

External Resources

Popular Topics
Recent Journals