ISMRM25 - Quantitative Imaging: AI, Analysis, & Beyond

ISMRM & ISMRT Annual Meeting & Exhibition • 10-15 May 2025 • Honolulu, Hawai'i

Quantitative Imaging: AI, Analysis, & Beyond

Digital Poster

Acquisition & Reconstruction

Monday, 12 May 2025

Exhibition Hall

17:00 - 18:00

Session Number: D-06

No CME/CE Credit

		Computer Number: 1 2102. Lung Water Density (LWD) Imaging with MRI: Normative Values and Dependence on Field Strength, Pulse Sequence and Breathing Maneuver View Presentation Video R. Thompson, C. Keen, A. Kirkham, R. Sherrington, R. Coulden, H. Jones, P. Seres, J. Grenier University of Alberta, Edmonton, Canada Impact: MRI-derived lung water density (LWD) is independent of age, sex and field-strength in healthy individuals but highly sensitive lung inflation (breathing maneuver) and with potential bias due to acquisition approach (k-space trajectory).
		Computer Number: 2 2103. Physics-driven deep unsupervised correction of susceptibility artifacts in blip-reversed multi-echo EPI for rapid T2 mapping View Presentation Video A. Zaid Alkilani, M. Utkur, C. Ariyurek, S. Kurugol, T. Çukur, O. Afacan, E. U. Saritas Bilkent University, Ankara, Turkey Impact: Applicability on multi-echo EPI scans, high anatomical accuracy and fast processing times enabled by meFD-Net significantly enhances feasibility in clinical and research settings. These advancements can facilitate real-time EPI applications through efficient, artifact-free imaging across diverse conditions.
		Computer Number: 3 2104. Accelerating Multi-parametric MRI Sequences Using Learned Acquisition and Reconstruction Optimization (LARO): A Retrospective Study View Presentation Video J. Zhang, H-G Shin, B. Dewey, S. Remedios, A. Carass, X. Li, P. van Zijl, S. Saidha, P. Calabresi, J. Prince Johns Hopkins University, Baltimore, United States Impact: Our study demonstrates LARO’s potential to accelerate time-consuming multi-parametric and multi-contrast MRI sequences, paving the way for comprehensive lesion profiling within practical scan times. LARO acceleration ensured consistent parametric maps (except for R2) and ROI segmentations.
		Computer Number: 4 2105. Accelerating the Whole-Brain Multi-Parametric Imaging through Joint Deep Learning Reconstruction and Physical Model Integration View Presentation Video J. Zhao, Y. Ye, J. Cheng, Y. Liu, Y. Li, J. Xu, D. Liang, S. Jia Medical AI Research Center, Shenzhen Institutes of Advanced Technology, Shenzhen, China Impact: The proposed method accelerated 3D whole-brain multi-parametric imaging while simultaneously quantifying T1/T2*/QSM/PD, benefiting clinicians with faster, high-resolution scans.
		Computer Number: 5 2106. Optimization of IVIM-DKI MR Imaging model using Automatic Differentiation Methods: Enhancing the Computation Efficacy by 100 Fold View Presentation Video H. Hanif, H. Maurya, E. Kayal, G. M, R. Hariprasad, R. Sharma, K. Khare, D. Kandasamy, A. Mehndiratta Indian Institute of Technology - Delhi, New Delhi, India Impact: Novel spatially constrained IDTV-AD method using automatic differentiation demonstrated significantly fast (at least 100 times faster than the state-of-the-art method) and accurate IVIM-DKI parameter estimation, tested in clinical dataset of pancreatic cancer cohort.
		Computer Number: 6 2107. Accelerating Multi-parametric Mapping using a Deep Wave-ESPIRiT Model View Presentation Video X. Yang, X. Han, J. Zhao, H. Zheng, S. Jia, Y. Yang School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, China Impact: The proposed DL-Wave-ESPIRiT method significantly reduces reconstruction time for accelerated MULTIPLEX imaging, achieving high accuracy in seconds instead of minutes. This advancement enhances clinical efficiency and enables faster, more effective imaging workflows.
		Computer Number: 7 2108. Drift-insensitive and motion-robust relaxometry using N-periodic SSFP View Presentation Video C. Beitone, K. Balaji, K. Miller, N. Bangerter, P. Lally Imperial College London, London, United Kingdom Impact: We introduce a novel and flexible approach for SSFP-based relaxometry, which shows advantages over existing approaches in its robustness to slow variations over an experiment.
		Computer Number: 8 2109. Unsupervised quantitative MRI reconstruction with densely-connected generative modeling and Bloch subspace projector Z. Li, H. Sun, C. Liu, W. Chen, R. Li Tsinghua University, Beijing, China Impact: The proposed reconstruction framework is flexible with different physical models. It has potential to be used for other quantitative MRI imaging applications.
		Computer Number: 9 2110. Initial Experience of Cardiac Multi-parametric Mapping at 5.0T with Single-shot Cartesian Acquisition and Dictionary Matching View Presentation Video Z. Lyu, H. Huang, H. Yang, P. Hu, H. Qi School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China, Shanghai, China Impact: The validation of simultaneous myocardial multi-parametric mapping at 5.0T demonstrated promising performance, with potential for more accurate myocardial assessments in clinical settings.
		Computer Number: 10 2111. Robustness of Texture Features in Quantitative Susceptibility Mapping: Influence of Background Field Removal and Inversion Algorithms View Presentation Video S. Fang, Y. Tang, G. Li, W. Zhao, C. Yang, L. Chen, C. Ma, X. Wu, J. Li Shanghai Key Laboratory of Magnetic Resonance, School of Physics and Electronic Science, East China Normal University, Shanghai, China Impact: The robustness of texture features varies across different background field removal and inversion algorithms in QSM reconstruction. The impact of the QSM reconstruction algorithm on texture features should be carefully considered before clinical implementation.
		Computer Number: 11 2112. T2 mapping with Bloch Equation-Informed Physical Intelligent Neural Network View Presentation Video Q. Cai, L. Zhu, J. Zhou, C. Qian, R. Tong, L. Mei, X. Jiang, Q. Xu, X. Qu Xiamen University, Xiamen, China Impact: The proposed method provides a new way to quantify tissue parameter, which does not require analytical formula of Bloch equation under specific sequences, and is expected to simplify the sequence design of quantitative magnetic resonance imaging.
		Computer Number: 12 2113. Deep learning enabled fast free-breathing stack-of-stars multiparameter mapping for fully quantitative analysis of prostate carcinoma. View Presentation Video H. Y. Kim, C. Pirkl, R. Schulte, P. Garcia-Polo, X. Wang, M. Cencini, V. Spieker, S. Gines, A. Guidon, M. Tosetti, L. Marti-Bonmati, J. Schnabel, M. Menzel Technical University of Munich, Munich, Germany Impact: Quantitative transient-state imaging combined with deep learning-based reconstruction provides high image quality T1 and T2 maps, enabling a fully quantitative evaluation of prostate cancer diagnosis with the potential of improving the prostate diagnosis pipeline.
		Computer Number: 13 2114. Deep Learning-based Super-Resolution reconstruction for Fast T1 and T2-weighted Head and Neck MRI View Presentation Video S. Li, W. Yan, X. Y. Zhang, L. Ji, Q. Yue West China Hospital of Sichuan university, Chengdu, China Impact: This integrated deep learning framework offers a clinically viable solution for accelerated head and neck MRI acquisition while enhancing image quality, potentially improving workflow efficiency and patient comfort in routine clinical practice.
		Computer Number: 14 2115. Integrating Classical Image Filters with Physics-Driven Deep Learning for Sharper Image Reconstruction View Presentation Video J. Yun, M. Akçakaya Electrical and Computer Engineering, University of Minnesota, Minneapolis, United States Impact: The proposed approach incorporates simple Laplacian sharpening filters into unrolled networks, which is shown to enhance sharpness, with visual improvements. This hybrid methodology represents a promising direction, merging traditional techniques with DL for superior image quality.
		Computer Number: 15 2116. Robust variable flip angle T1-mapping by time optimal control View Presentation Video C. Graf, A. Jaffray, C. Diwoky, A. Rund, S. Steinerberger, A. Yung, A. Rauscher University of British Columbia, Vancouver, Canada Impact: The advancement in VFA T₁-mapping using robust excitation pulses designed by time-optimal control reduces scan time as no additional acquisition of B₁⁺-maps is necessary, and it minimizes potential errors associated with inaccuracies in the B₁⁺-maps and their correction.
		Computer Number: 16 2117. Quantitative Maps Synthesis from Magnetic Resonance Fingerprinting via Physical-guided Deep Generative Model View Presentation Video B. Zhang, K. Wang, X. Wu, L. Zou, Y. Zhu, D. liang, Y. Zhou, H. Wang Paul C. Lauterbur Research Center for Biomedical Imaging,Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China Impact: Our proposed MRF sequence-based quantitative map generation model produces quantitative maps that better capture clinically relevant contrast details. It also enables the calculation of various weighted images from these more accurate quantitative maps, supporting more comprehensive clinical diagnosis.

Similar Session(s)