Related Experiment Video
Updated: May 21, 2026
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Simultaneous multi-slice Cardiac Diffusion Tensor Imaging with variable CAIPIRINHA shifts and artefact-aware AI
Michael Tänzer1, Eun Ji Lim1, Huaqi Harvey Qiu2
1Imperial College London, London, UK; Royal Brompton and Harefield Hospital, London, UK.
Medical Image Analysis
|May 19, 2026
Summary
Cardiac Diffusion Tensor Imaging (cDTI) can now be significantly accelerated using the ORCAS framework. This AI-powered approach drastically reduces scan times while maintaining accuracy for myocardial microstructure analysis.
Area of Science:
- Biomedical Imaging
- Cardiovascular MRI
- Diffusion Tensor Imaging
Background:
- Cardiac Diffusion Tensor Imaging (cDTI) offers vital in-vivo myocardial microstructure insights.
- Current cDTI methods suffer from long acquisition times due to signal averaging needs.
- Existing acceleration techniques like reduced repetitions and simultaneous multi-slice (SMS) imaging have limitations.
Purpose of the Study:
- To introduce ORCAS, a novel framework for accelerated whole-heart cDTI.
- To overcome SNR limitations and SMS-induced artefacts in accelerated cDTI.
- To enable faster and more clinically feasible myocardial microstructure assessment.
Main Methods:
- ORCAS combines a variable CAIPIRINHA acquisition with an artefact-aware AI reconstruction.
- Variable CAIPIRINHA decoheres SMS artefacts across repetitions.
- A dual-domain deep learning model suppresses artefacts and low SNR, guided by auxiliary data.
Main Results:
- ORCAS achieves over 18-fold acceleration, reducing scan time from hours to under 7 minutes.
- Errors in biomarkers like Fractional Anisotropy were reduced by up to 64%.
- The framework successfully preserved microstructural properties and abnormality delineation.
Conclusions:
- ORCAS significantly accelerates whole-heart cDTI, addressing major clinical translation barriers.
- The framework demonstrates high fidelity in assessing myocardial microstructure and pathologies.
- ORCAS represents a substantial advancement towards routine clinical application of cDTI.
