$\texttt{DisMorph}$: learning to disentangle technical distortions from true biological change
Year: 2026
Type: preprint
Abstract: Longitudinal MRI enables sensitive measurement of structural brain change for studying aging and neurodegenerative disease. Deformable image registration is a key tool for estimating such change by computing a dense deformation that captures geometric differences between longitudinal scans. However, MRI scanners introduce geometric distortions that vary across acquisition systems and protocols, such as gradient non-linearity (GNL) distortion. Existing registration methods estimate a single field that conflates biological and technical effects, potentially biasing downstream morphometric measurements if distortions remain (partially) uncorrected. We propose $\texttt{DisMorph}$, a registration framework trained entirely on synthetic data that explicitly decomposes longitudinal deformation into technical and anatomical transforms. It predicts two dense deformations, each encoding one effect. During training, a novel generative model synthesizes both effects separately to provide disentanglement supervision, while domain randomization promotes generalization across imaging protocols. We evaluate our method in three complementary settings. On simulated data with known ground truth, our method detects anatomical change more accurately and consistently than conventional registration. On real image pairs that differ only by GNL distortion, our method assigns most geometric change to the distortion field, demonstrating specificity in the absence of anatomical change. On longitudinal Alzheimer's disease (AD) pairs, our method detects anatomical change in AD-related brain structures while identifying residual distortion left after standard correction. By disentangling MRI-induced distortion from biological change in the longitudinal deformation, our method paves the way for more accurate longitudinal morphometry in clinical settings where maintaining acquisition consistency is challenging.
Source: arXiv (Cornell University)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Massachusetts General Hospital, Massachusetts Life Sciences Center, Knut och Alice Wallenbergs Stiftelse, National Institutes of Health, National Institute on Aging, National Institute of Mental Health, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, National Center for Research Resources
Awards: G1614942108, G2004043075, G2058387751, G2302581481, G323562261, Segmenting Brain Structures for Neurological Disorders, Deep Learning for Detecting the Early Anatomical Effects of Alzheimer's Disease, Algorithms for MR and OCT-based Architectonic and Laminar Segmentation, The Human Connectome Project (HCP), OCTology: histology using optical coherence tomography, G5100925459, G5557224331, Nobrainer: A robust and validated neural network tool suite for imagers, MRI, Genetics & Cognitive Precursors of AD and Dementia, Software Tools for Automated Modeling of White Matter Fascicles from Diffusion MR, A Storage Area Network for Structural and Functional Image Analysis, A Longitudinal Analysis Stream for FreeSurfer, An Acquisition and Analysis Pipeline for Integrating MRI and Neuropathology in TBI-related Dementia and VCID, Functionally guided adult whole brain cell atlas in human and NHP, FreeSurfer Development, Maintenance, and Hardening, Center for Mesoscale Mapping, Fast and Robust Deep Learning for Medical imaging: Segmentation and Registration methods invariant to contrast and resolution, MGH/HMS Internship in NeuroImaging Analysis, Diagnosing the undiagnosable: studies of Alzheimer disease mimics and confounders via "neuropathometry" of dissection photos with 3D scanning, BRAIN CONNECTS: Mapping Connectivity of the Human Brainstem in a Nuclear Coordinate System, BRAIN CONNECTS: The center for Large-scale Imaging of Neural Circuits (LINC), G984581029
OpenAlex ID: W7202164807