GUI System to Support Cardiology Examination Based on Explainable Regression CNN for Estimating Pulmonary Artery Wedge Pressure

Yuto Omae, Yuki Saito, Yohei Kakimoto, Daisuke Fukamachi, Koichi Nagashima, Yasuo Okumura, Jun Toyotani

Research output: Contribution to journalArticlepeer-review

Abstract

In this article, a GUI system is proposed to support clinical cardiology examinations. The proposed system estimates "pulmonary artery wedge pressure"based on patients' chest radiographs using an explainable regression-based convolutional neural network. The GUI system was validated by performing an effectiveness survey with 23 cardiology physicians with medical licenses. The results indicated that many physicians considered the GUI system to be effective.

Original languageEnglish
Pages (from-to)423-426
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE106D
Issue number3
DOIs
Publication statusPublished - Mar 2023

Keywords

  • cardiology examination
  • convolutional neural network
  • pulmonary artery wedge pressure
  • regression activation map

Fingerprint

Dive into the research topics of 'GUI System to Support Cardiology Examination Based on Explainable Regression CNN for Estimating Pulmonary Artery Wedge Pressure'. Together they form a unique fingerprint.

Cite this