Marie-Laure Paillère Martinot

arXiv2026

Automatic sub-bundle tractometry reveals localized microstructural variations in complex white matter topographies

Conventional tractometry averages white matter microstructure into a single profile, masking intra-bundle spatial heterogeneity and diluting localized alterations. We propose an automatic sub-bundle tractometry framework using Fr{é}chet-based hierarchical clustering to decompose bundles into geometrically coherent sub-bundles, resolving complex fanning configurations without empirical thresholds. Multi-compartment metrics (fractional anisotropy, FA; isotropic free-water fraction, IFW) are projected onto these clusters. We evaluated this framework in 140 participants across early-life (ELD) and late-life (LLD) depression cohorts, alongside age-matched healthy controls. We assessed performance based on microstructural homogeneity, sensitivity to age, and clinical group differences. Proposed sub-bundle metrics were significantly more homogeneous than classical full bundle profiles (p < 0.001). Our approach showed enhanced sensitivity, detecting more age-correlated bundles in elderly controls (11 vs. 5) and more clinical group differences in LLD (FA: 6 vs. 4; IFW: 23 vs. 17) with larger effect sizes. In ELD, it improved the detection of subtle FA differences between remitted and resistant individuals (2.9% vs. 1.8%). Gains were particularly pronounced in LLD, reflecting the framework's ability to resolve fanning tracts susceptible to brain aging. By preserving spatial heterogeneity, this automatic decomposition provides a robust foundation for large-scale clinical tractometry.

eess.SP↗

arXiv2025

Automatic rating of incomplete hippocampal inversions evaluated across multiple cohorts

Incomplete Hippocampal Inversion (IHI), sometimes called hippocampal malrotation, is an atypical anatomical pattern of the hippocampus found in about 20% of the general population. IHI can be visually assessed on coronal slices of T1 weighted MR images, using a composite score that combines four anatomical criteria. IHI has been associated with several brain disorders (epilepsy, schizophrenia). However, these studies were based on small samples. Furthermore, the factors (genetic or environmental) that contribute to the genesis of IHI are largely unknown. Large-scale studies are thus needed to further understand IHI and their potential relationships to neurological and psychiatric disorders. However, visual evaluation is long and tedious, justifying the need for an automatic method. In this paper, we propose, for the first time, to automatically rate IHI. We proceed by predicting four anatomical criteria, which are then summed up to form the IHI score, providing the advantage of an interpretable score. We provided an extensive experimental investigation of different machine learning methods and training strategies. We performed automatic rating using a variety of deep learning models (conv5-FC3, ResNet and SECNN) as well as a ridge regression. We studied the generalization of our models using different cohorts and performed multi-cohort learning. We relied on a large population of 2,008 participants from the IMAGEN study, 993 and 403 participants from the QTIM/QTAB studies as well as 985 subjects from the UKBiobank. We showed that deep learning models outperformed a ridge regression. We demonstrated that the performances of the conv5-FC3 network were at least as good as more complex networks while maintaining a low complexity and computation time. We showed that training on a single cohort may lack in variability while training on several cohorts improves generalization.

eess.IV↗