Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition - Advanced Cardiac Quantification Methods

Advanced Cardiac Quantification Methods

Oral

Analysis Methods

Thursday, 14 May 2026

Meeting Room 1.40

08:30 - 10:20

Moderators: Ana Beatriz Solana & Daniel Kim

Session Number: 607-01

No CME/CE Credit

Similar Sessions

Advanced analysis methods for cardiovascular MRI: 4D flow, strain quantification, perfusion.

Skill Level: Intermediate

08:30		607-01-001. A CMRsim-based Simulator for Quantitative First-Pass Myocardial Perfusion CMR Chang Yan, Charles McGrath, Vincent Vousten, Maximilian Fuetterer, Sebastian Kozerke University and ETH Zürich, Zürich, Switzerland Impact: Physics-based simulations enable the generation of large datasets for training and validation of advanced reconstruction and processing methods for quantitative perfusion CMR.
08:41		607-01-002. Deep-Learning Based Highly Sub-Sampled 2-Point Velocity Encoding 4D flow MRI Haben Berhane, Ethan Johnson, Sebastian Cohn, Bradley Allen, Michael Markl Biomedical Engineering, Northwestern University, Chicago, United States of America Impact: This technique enables significant reduction of 4D flow MRI scan time without compromising hemodynamic quantifications. Future work will focus on testing this work on prospectively acquired data and across different centers and vendors.
08:52		607-01-003. Deep Learning-based Estimation of Myocardial Extracellular Volume Without Blood Sampling: Multicenter Study in 9,700 Patients Zhuoan Li, Khalid Youssef, Venkateshwar Polsani, Michael Elliott, Rohan Dharmakumar, Robert Judd, Dipan Shah, Orlando Simonetti, Matthew Tong, Behzad Sharif Purdue University, West Lafayette, United States of America Impact: We present a large-scale, retrospective multi-center cardiac MRI (CMR) study in 9,700 patients identifying the optimal feature set to derive synthetic extracellular volume (ECV) without blood sampling using multi-stage deep learning, advancing synthetic ECV quantification toward routine clinical adoption.
09:03		607-01-004. Noninvasive MRI-based Quantification of Pulmonary Arterial Pressure: Toward Clinical Applications Zhaowei Rong, Wenwen Zhou, Rongli Zhang, Xin Huang, Xiuhong Guan, Zhifeng Liu, Hongyan Liu, Xiang Feng, Hairong Zheng, Qi Yang, Chengwang Lei, Guoxi Xie School of Biomedical Engineering, The Fourth Affiliated Hospital, Guangzhou Medical University, Guangzhou, China Impact: The proposed method is a promising alternative to measure mPAP noninvasively and accurately, enabling earlier diagnosis and follow-up study or clinical treatment of PH. This work will lay the groundwork for more applications in noninvasive assessments of cardiovascular diseases.
09:14		607-01-005. Non-invasive Imaging of relative pressure - comparison of approaches by joint velocity and acceleration encoded 4D-Flow MRI Vincent Lechner, Priya Nair, Michael Loecher, Charles McGrath, Simon Thalén, Carlos Castillo-Passi, Lorenzo Ferrari, Chenwei Tang, David Nordsletten, Daniel Ennis, David Marlevi Karolinska Institutet, Solna, Sweden Impact: Relative pressure plays a central role in contemporary clinical management of cardiovascular diseases, with derived metrics potentially shaping future disease management. State-of-the-art non-invasive methods rely on 4D-Flow MRI, but acceleration-informed mapping may offer improvements.
09:25		607-01-006. Fully Automatic Left Atrial Strain Quantification via Multi-Task Learning on Cardiac Cine MRI Haiyang Chen, Yichen Zhao, Yiwen Gong, Zhuo Chen, Juan Gao, Fan Yang, Zhihao Xue, Zeping Qiu, Ji Zhao, Qing Li, Chengyan Wang, Yucheng Chen, Liang Zhong, Sha Hua, Wei Jin, Chenxi Hu National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China Impact: The proposed multi-task learning method for automatic LA strain quantification, validated on multi-center two-vendor data, enhances tracking accuracy and diagnostic power over prior methods, potentially facilitating reliable and efficient atrial function assessment in routine care.
09:36		607-01-007. DeepSENC: AI-Driven Robust Strain-Encoding MRI Quantification for Cardiac-Induced Liver Fibrosis Assessment Khaled Abd-Elmoniem, Ahmed Abdelfadeel, Ahmed Harouni, Ahmed Gharib National Institute of Diabetes and Digestive and Kidney Diseases, Bethesda, United States of America Impact: DeepSENC—supervised deep learning-enhanced strain-encoding (SENC) MRI—addresses SENC-MRI fundamental SNR and artifact limitations, enabling robust liver strain quantification from intrinsic cardiac motion. This external driver-free approach achieves diagnostic performance comparable to MR elastography without specialized hardware or prolonged acquisitions.
09:47		607-01-008. CMR Derived Infarct Burden Enhances Risk Stratification and Treatment Decision-Making in Multivessel Disease Zhaoxin Tian, Ting Liu, Minjie Lu Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China Impact: Quantifying infarct burden by CMR (MI%) improves risk prediction beyond SYNTAX II and informs PCI vs CABG decisions in multivessel disease. This enables personalized revascularization, supports trial stratification by MI%, and motivates studies testing MI%-guided treatment pathways and outcomes.
09:58		607-01-009. PUDIP-Flow: An Unsupervised and Segmentation-Free Phase Unwrapping Method for Aortic and Cerebrovascular 4D Flow MRI Yuyang Ren, Zijian Zhou, Yuan Feng, Yining Wang, Peng Hu ShanghaiTech University, Shanghai, China Impact: PUDIP-Flow outperforms the traditional methods and can yield accurate flow velocity quantifications for 4D flow MRI. The code is available at https://github.com/AssociatedPrimeIdeal/PUDIP-Flow.
10:09		607-01-010. Deep Learning Assessment of Global Radial and Circumferential Strain in Single Ventricle Patients Tina Yao, Nicole St. Clair, Gabriel Miller, Jennifer Steeden, Rahul Rathod, Vivek Muthurangu University College London, London, United Kingdom Impact: We developed a pipeline using automated 3D motion estimation to compute global radial and circumferential strain from short-axis CMR in 1030 single-ventricle patients. It provides rapid, reproducible strain measurements and demonstrates associations with death or transplantation beyond ejection fraction.