12 papers
Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory
Jun Wang, Peirong Liu
Forecasting longitudinal brain lesion evolution is critical for disease monitoring and treatment planning. Existing approaches typically learn a direct mapping from a baseline imag…
A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning
Stefano Cerri, Asbjørn Munk, Sebastian Nørgaard Llambias +11
We present FOMO260K, a large-scale, heterogeneous dataset of 260,927 brain Magnetic Resonance Imaging (MRI) scans from 77,589 MRI sessions and 55,378 subjects, aggregated from 910…
ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang +8
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of…
USB: Unified Synthetic Brain Framework for Bidirectional Pathology-Healthy Generation and Editing
Jun Wang, Peirong Liu
Understanding the relationship between pathological and healthy brain structures is fundamental to neuroimaging, connecting disease diagnosis and detection with modeling, predictio…
Learning to Upscale 3D Segmentations in Neuroimaging
Xiaoling Hu, Peirong Liu, Dina Zemlyanker +3
Obtaining high-resolution (HR) segmentations from coarse annotations is a pervasive challenge in computer vision. Applications include inferring pixel-level segmentations from toke…
Generating healthy counterfactuals with denoising diffusion bridge models
Ana Lawry Aguila, Peirong Liu, Marina Crespo Aguirre +1
Generating healthy counterfactuals from pathological images holds significant promise in medical imaging, e.g., in anomaly detection or for application of analysis tools that are d…