The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method

TL;DR

This paper presents a CNN-based method with an effective preprocessing technique to improve the accuracy of coronary occlusion site localization, which is critical for timely intervention in heart attack cases.

Contribution

The study introduces a novel preprocessing approach that enhances CNN performance in localizing coronary occlusions, handling three CAO types with improved accuracy.

Findings

Localization performance improved from 0.150 to 0.372

Effective noise reduction and pulse extraction methods used

Applicable to three types of CAO

Abstract

The Coronary Artery Occlusion (CAO) acutely comes to human, and it highly threats the human's life. When CAO detected, Percutaneous Coronary Intervention (PCI) should be conducted timely. Before PCI, localizing the CAO is needed firstly, because the heart is covered with various arteries. We handle the three kinds of CAO in this paper and our purpose is not only localization of CAO but also improving the localizing performance via preprocessing method. We improve localization performance from a minimum of 0.150 to a maximum of 0.372 via our noise reduction and pulse extraction based method.