AI for Accelerated and Quantitative Cardiac MRI

The group evaluates accelerated cardiac MRI reconstruction and AI-based quantitative cardiac MRI tools.

Overview

CMRxRecon2024 contributes a multimodality, multiview dataset for accelerated cardiac MRI.

Additional 2025 work from Kai Lin, James Carr, and colleagues evaluates agreement across AI systems for cine MRI-derived function and motion patterns.

Reconstruction and quantitative tool validation are both included.

accelerated MRImachine learningquantitative cardiac MRI

Research overview

Figure from CMRxRecon2024 illustrating dataset preparation and open platform support for accelerated cardiac MRI machine learning.

Selected work

CMRxRecon2024: A Multimodality, Multiview k-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI

Wang Z, Wang F, Qin C, Lyu J, Ouyang C, Wang S, Li Y, Yu M, Zhang H, et al.; including Markl M. Radiol Artif Intell. 2025.

Inter-AI Agreement in Measuring Cine MRI-Derived Cardiac Function and Motion Patterns: A Pilot Study

Lin K, Sarnari R, Gordon DZ, Markl M, Carr JC. J Imaging Inform Med. 2025.

Toward Modality- and Sampling-Universal Learning Strategies for Accelerating Cardiovascular Imaging: Summary of the CMRxRecon2024 Challenge

Wang F, Wang Z, Li Y, Lyu J, Qin C, Wang S, Guo K, et al.; including Markl M. IEEE Trans Med Imaging. 2026.

Computationally Efficient Implicit Training Strategy for Unrolled Networks (IMUNNE): A Preliminary Analysis Using Accelerated Real-Time Cardiac Cine MRI

Iakovlev N, Schiffers FA, Tapia SL, Shen D, Hong K, Markl M, Lee DC, Katsaggelos AK, Kim D. IEEE Trans Biomed Eng. 2025.