Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition

fMRI: Advanced Analysis

Oral

Brain Function & fMRI

Wednesday, 13 May 2026

Hall 1A

13:40 - 15:30

Moderators: Jingyuan Chen & Francesca Saviola

Session Number: 501-03

CME/CE Credit Available

Similar Sessions

This session focuses on advanced analysis of fMRI data, ranging from multivariate statistical approaches to state-of-the-art deep learning and generative models, for novel applications.

Skill Level: Intermediate

13:40		501-03-001. Latent space modelling of whole-brain dynamics: a Koopman-theoretical approach Riccardo Tancredi, Michele Allegra, Gustavo Deco CNR-Nanotec &Santa Lucia Foundation, Rome, Italy Impact: By mapping nonlinear fMRI dynamics onto a Koopman-linear latent space, this framework unifies generative modelling and control theory, enabling interpretable analysis of brain reorganisation and stroke-related alterations.
13:51		501-03-002. Cortex-Inspired Hierarchical Reconstruction of Visual Stimuli from fMRI Signals Shiyi Zhang, liu ming, Qihui Ye, Yanjie Zhu, Haifeng Wang, Dong Liang, Hairong Zheng, Yihang Zhou Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China Impact: Our fMRI-based reconstruction creates a non-invasive window into the mind, translating thoughts into high-resolution visual imagery. This work offers significant potential for creating assistive technologies for the disabled and advancing research into visual neuroscience.
14:02		501-03-003. Bidirectional EEG–fMRI Reconstruction via a Shared Latent Space for Cross-Modal Neuroimaging Khondakar Shahriar, Maruf Ahmed, Enamul Bhuiyan Bangladesh University of Engineering and Technology, Dhaka, Bangladesh Impact: Enables robust EEG–fMRI translation, bridging temporal–spatial domains for multimodal brain mapping.
14:13		501-03-004. Bridging Temporal Scales: A Data-Driven Integration of MEG and fMRI Jiri Benacek, Krish Singh, Derek Jones, David Marshall, Simon Rushton, Marco Palombo Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University, Cardiff, United Kingdom Impact: Our proof-of-concept approach shows high inter-modal predictability between MEG and fMRI. Using data-driven methods, we generated higher-than-trained frequency fMRI maps from MEG inputs, outperforming interpolation. This presents new avenues into investigating neurovascular coupling.
14:24		501-03-005. Modeling of large-vessel BOLD contributions in Echo-Planar Time-resolved Imaging (EPTI) using subject-specific MR angiography Daniel Haenelt, Grant Hartung, Avery Berman, J. Jean Chen, Jian Wu, Berkin Bilgic, Robert Frost, Zijing Dong, Fuyixue Wang, Jonathan Polimeni Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, United States of America Impact: We developed a subject-specific macroscopic vascular anatomical network (VAN) model to simulate macrovascular intra- and extra-vascular BOLD components, providing a framework that can be used to establish computational methods to correct macrovascular bias and thereby enhance spatial specificity in fMRI.
14:35		501-03-006. Connectome-Based Predictive Modeling of Cognitive Function in Major Depressive Disorder: A Neuroimaging-Genetic Study Yuanyuan Li, Xiqin Liu, Qiyong Gong Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, China Impact: Identifying connectivity-based cognitive predictors in first episode drug-naive MDD enables patient stratification and early intervention targeting. These findings advance precision psychiatry by identifying connectivity-based and molecular signatures that may inform future therapeutic approaches targeting cognitive dysfunction in MDD.
14:46		501-03-007. Fourier domain fMRI analysis for robustness to hemodynamic response function heterogeneity Seon-Ha Hwang, HyeRyeong Choi, Sung-Hong Park Korea Advanced Institute of Science & Technology, Daejeon, Korea, Republic of Impact: Fourier domain GLM extends conventional analysis by confirming consistency between the temporal and Fourier domains, providing a paradigm-independent framework applicable to diverse fMRI studies. The proposed magnitude modeling enables detection of additional task-relevant regions, achieving robustness to HRF variability.
14:57		501-03-008. Towards ultra-fast perfusion fMRI using narrow-band velocity-selective arterial spin labeling (nb-VSASL) Jia Guo University of California Riverside, Riverside, United States of America Impact: This work aims to develop novel labeling strategies for ASL-based ultra-fast fMRI with narrow-band velocity-selectivity, which can potentially offer significant TR reduction.
15:08		501-03-009. Bridging the gap with invasive imaging: promises and challenges of a new generation of ultrahigh resolution fMRI Lasse Knudsen, Yulia Lazarova, Steen Moeller, Nils Nothnagel, Lonike Faes, Kamil Ugurbil, Essa Yacoub, Luca Vizioli Center for Magnetic Resonance Research (CMRR), University of Minnesota, Minneapolis, United States of America Impact: Human functional mapping at 10.5T with a spatial resolution of 350 microns isotropic (0.042µL), moving towards the 0.01µL voxel volume goal (Brain Initiative 2.0), heralds major new opportunities in neuroscience, but also presents new challenges that need to be addressed.