XCAE: Deep Neural Network for X-ray Coronary Angiograms Quality Enhancement

X-ray Angiography (XA) is the gold standard medical imaging modality used to assess Coronary Artery Disease (CAD), and also the imaging modality used during Percutaneous Coronary Interventions (PCI), and while performing invasive hemodynamic measurements and intravascular imaging. Aside from visuall...

Full description

Saved in:
Bibliographic Details
Main Authors: Dinescu, Andrei Damian, Miron, Radu, Itu, Lucian Mihai, Cristina Plajer, Ioana, Turcea, Alexandru
Format: Conference Proceeding
Language:English
Subjects:
Arteries
Computer Aided Diagnosis
Coronary Artery Disease
Deep learning
Hemodynamics
Image quality
Inspection
Medical Images Quality Enhancement
Visualization
X-ray imaging
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:X-ray Angiography (XA) is the gold standard medical imaging modality used to assess Coronary Artery Disease (CAD), and also the imaging modality used during Percutaneous Coronary Interventions (PCI), and while performing invasive hemodynamic measurements and intravascular imaging. Aside from visually inspecting the coronary arteries, in recent years Computer Aided Diagnosis (CADx) systems have been employed to assist clinicians in the detection and evaluation of CAD. However, both visual inspection and CADx systems rely heavily on the quality of the acquisitions, which, due to factors such as lower cost or older equipment and the desirability of a low radiation dose, among others, can be sub-optimal. In this paper, a Deep Learning (DL) based method is presented to address this issue, by enhancing the quality of coronary angiograms. A quantitative evaluation of the proposed method is performed and additional evaluation methods are proposed for future work.
ISSN:1946-0759
DOI:10.1109/ETFA54631.2023.10275381