EUVIMEDAtrasti EUVIMED
Open access · CC BY 4.0

A deep‐learning‐based pipeline for automatic fusion of CT coronary angiogram and stress perfusion CMR

Wenting Jiang, Ming-Yen Ng, Tsun-Hei Sin, Peng Cao

Medical Physics · 2026-04 · 53 (4)

DOI: 10.1002/mp.70420 ↗

At a glance

Journal article in Medical Physics, published online on 2026-04-10. Written by Wenting Jiang and 3 co-authors. Institution: Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China. Major MEDLINE topics: Deep Learning, Coronary Angiography, Image Processing, Computer-Assisted, Computed Tomography Angiography. Cited 1 times so far (Crossref); 45 references. The full text is freely available (open access, CC BY 4.0).

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Accurate evaluation of coronary artery constriction and myocardial ischemia is essential for diagnosing and managing coronary artery disease (CAD). Combining CT coronary angiography (CTCA) and stress cardiovascular magnetic resonance (CMR) imaging allows examination of both coronary artery narrowing and myocardial perfusion.

Purpose

To develop a deep learning pipeline that integrates CTCA and CMR images, which could help improve accuracy in identifying affected vessels and their associated myocardial territories.

Methods

The proposed pipeline included two deep learning models: one for automatic reorientation of 3D CTCA and another for left ventricle (LV) wall registration between CTCA and CMR images. A 3D spatial co‐registration model, the reorientation spatial transformer network (Reorientation STN), predicted reorientation parameters for input CTCA volumes using ResNet18 and STN. A 2D nonrigid spatial deformation network (Nonrigid SDN) was trained for LV wall registration. Cross‐modal supervision was employed during training. Evaluation criteria included aspect ratio (AR), Dice similarity coefficient (DSC), and long‐axis deviation angles. The process involved quantifying LV wall perfusion on registered CMR images and extracting coronary arteries from reoriented CTCA images to fuse these results. The pipeline was trained and validated on 447 pairs of CTCA and CMR images from 75 patients and tested on 18 subjects.

Results

The pipeline achieved an AR of 0.94 ± 0.03, long‐axis deviation angles of 1.19 ± 0.83 (axial) and 1.54 ± 0.79 (coronal), a DSC of 0.66 ± 0.04 for LV wall reorientation, and a DSC of 0.92 ± 0.03 for LV wall registration between CTCA and CMR.

Conclusions

This automated framework successfully fuses cardiac CTCA and CMR imaging, demonstrating its potential effectiveness.

Subjects

MeSH terms (MEDLINE)

Deep LearningCoronary AngiographyImage Processing, Computer-AssistedComputed Tomography AngiographyMagnetic Resonance ImagingStress, PhysiologicalHumansAutomation

Author keywords

CT coronary angiogramcardiac MRIdeep learningimage fusion

Authors and institutions

  • Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China.

Cite

APA

Jiang, W., Ng, M. Y., Sin, T. H., & Cao, P. (2026). A deep‐learning‐based pipeline for automatic fusion of CT coronary angiogram and stress perfusion CMR. Medical Physics, 53(4). https://doi.org/10.1002/mp.70420

Vancouver

Jiang W, Ng MY, Sin TH, Cao P. A deep‐learning‐based pipeline for automatic fusion of CT coronary angiogram and stress perfusion CMR. Medical Physics. 2026;53(4). doi:10.1002/mp.70420

BibTeX
@article{Jiang2026,
  author = {Jiang, Wenting and Ng, Ming-Yen and Sin, Tsun-Hei and Cao, Peng},
  title = {A deep‐learning‐based pipeline for automatic fusion of CT coronary angiogram and stress perfusion CMR},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {4},
  doi = {10.1002/mp.70420}
}
Start for free →