Publications

BibTex format

@article{Tänzer:2025:10.1016/j.jocmr.2025.101971,
author = {Tänzer, M and Scott, AD and Khalique, Z and Molto, M and Rajakulasingam, R and Silva, RD and Pennell, DJ and Ferreira, PF and Yang, G and Rueckert, D and Nielles-Vallespin, S},
doi = {10.1016/j.jocmr.2025.101971},
journal = {Journal of Cardiovascular Magnetic Resonance},
title = {Accelerating cDTI with deep learning-based tensor de-noising and breath hold reduction. a step towards improved efficiency and clinical feasibility},
url = {http://dx.doi.org/10.1016/j.jocmr.2025.101971},
year = {2025}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundCardiac Diffusion Tensor Imaging (cDTI) non-invasively provides unique insights into cardiac microstructure. Current protocols require multiple breath-hold repetitions to achieve adequate signal-to-noise ratio, resulting in lengthy scan times. The aim of this study was to develop a cDTI de-noising method that would enable the reduction of repetitions while preserving image quality.MethodsWe present a novel de-noising framework for cDTI acceleration centred on three fundamental advances: (1) a paradigm shift from image-based to tensor-space de-noising that better preserves structural information, (2) an ensemble of Vision Transformer-based models specifically optimised for tensor processing through adversarial training, and (3) a sophisticated data augmentation strategy that maximises training data utilisation through dynamic repetition selection.ResultsOur approach reduces scan times by a factor of up to 4 while achieving a 20% reduction in cDTI maps errors over existing de-noising methods (Table 1) and preserving anatomical features such as infarct characterisation and transmural cardiomyocyte orientation patterns. Crucially, our proposed method succeeds in clinical cases where other algorithms previously failed.ConclusionsThis demonstrates substantial improvements in cDTI acquisition efficiency, achieving up to 4-fold scan time reduction (3-5 breath-holds) while maintaining diagnostic accuracy across diverse cardiac pathologies.
AU  - Tänzer,M
AU  - Scott,AD
AU  - Khalique,Z
AU  - Molto,M
AU  - Rajakulasingam,R
AU  - Silva,RD
AU  - Pennell,DJ
AU  - Ferreira,PF
AU  - Yang,G
AU  - Rueckert,D
AU  - Nielles-Vallespin,S
DO  - 10.1016/j.jocmr.2025.101971
PY  - 2025///
SN  - 1097-6647
TI  - Accelerating cDTI with deep learning-based tensor de-noising and breath hold reduction. a step towards improved efficiency and clinical feasibility
T2  - Journal of Cardiovascular Magnetic Resonance
UR  - http://dx.doi.org/10.1016/j.jocmr.2025.101971
UR  - https://doi.org/10.1016/j.jocmr.2025.101971
ER  -

Download

Publications

Citation

BibTex format

RIS format (EndNote, RefMan)

Contact