Achieving detailed medial temporal lobe segmentation with upsampled isotropic training from implicit neural representation

Yue Li; Pulkit Khandelwal; Rohit Jena; Long Xie; Michael Duong; Amanda E. Denning; Christopher A. Brown; Laura E. M. Wisse

cs.CVAug 24, 2025

Achieving detailed medial temporal lobe segmentation with upsampled isotropic training from implicit neural representation

Authors: Yue Li, Pulkit Khandelwal, Rohit Jena, Long Xie, Michael Duong, Amanda E. Denning, Christopher A. Brown, Laura E. M. Wisse, +3 more

Organizations: University of Pennsylvania, Philadelphia, United States · Siemens Healthineers, Princeton, United States · Lund University, Lund, Sweden

Abstract

Imaging biomarkers in magnetic resonance imaging (MRI) are important tools for diagnosing, tracking and treating Alzheimer's disease (AD). Neurofibrillary tau pathology in AD is closely linked to neurodegeneration and generally follows a pattern of spread in the brain, with early stages involving subregions of the medial temporal lobe (MTL). Accurate segmentation of MTL subregions is needed to extract granular biomarkers of AD progression. MTL subregions are often imaged using T2-weighted (T2w) MRI scans that are highly anisotropic due to constraints of MRI physics and image acquisition, making it difficult to reliably model MTL subregions geometrically and extract morphological measures, such as thickness. In this study, we propose a segmentation framework for MTL subregions in isotropic space, in which an implicit neural representation is used to construct the isotropic training atlas from the anisotropic low-resolution T2w data, with T1w MRI as an auxiliary modality to support the INR and segmentation. In an independent test set, the morphological measures extracted using this isotropic model showed stronger effect sizes than those from models trained on anisotropic data in distinguishing participants with mild cognitive impairment (MCI) from cognitively unimpaired individuals. In the test-retest analysis, the morphological measures extracted using the isotropic model showed greater stability than those from the anisotropic segmentation. This study demonstrates improved reliability of MRI-derived MTL subregion biomarkers without additional atlas annotation effort, which may more accurately quantify and track the relationship between AD pathology and brain atrophy for monitoring disease progression.

Explore similar work

May 14, 2026cs.CV

Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI

Precise segmentation of brain structures in magnetic resonance imaging (MRI) is essential for reliable neuroimaging analysis, yet voxel-wise deep models often yield anatomically inconsistent results that diverge from expert-defined boundaries. In this research, we propose a landmark-guided 3D brain segmentation approach that explicitly mimics the manual segmentation protocol of the Harvard--Oxford Atlas. A Global-to-Local network automatically detects 16 landmarks representing key subcortical reference points. Then, a semantic segmentation model produces a coarse segmentation of 12 anatomical labels, each grouping multiple subcortical regions. Finally, a landmark-driven post-processing step separates these 12 labels into 26 distinct structures by enforcing local anatomical constraints. Experimental results demonstrate consistent improvements in boundary accuracy. Overall, integrating learned landmarks aligns segmentations more closely with manual protocols.

Ahmed Rekik, R. Jarrett Rushmore, Sylvain Bouix +1

1 ´Ecole de technologie sup´erieure (´ETS), Montr´eal, Canada · 2Boston University School of Medicine, Boston, MA, USA · 3Signal and Smart Systems Lab (L3S), National School of Engineering of Tunis, University of Tunis El Manar, Tunisia

Brain Tumor Segmentation Magnetic Resonance Imaging Voxel Human Visual Cortex Auto Research

Ask PDF

Sep 14, 2026cs.CV

Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI

Deep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irrelevant regions, and multimodal models that add clinical tables frequently rely on variables that were used to assign the diagnostic label in the first place. We study both issues with a deliberately lightweight slice-based encoder (ResNet18 with a one-layer Transformer over slices) on 1,075 baseline T1-weighted scans from ADNI-1. First, we use FastSurfer segmentations as an anatomical reference: YOLOv8 models trained on segmentation-derived labels localize Alzheimer-relevant structures with mAP_50 above 0.96, and a Grad-CAM comparison shows that the image-only classifier frequently attends to the skull, orbits and background. Second, we adapt a CLIP-style image - tabular contrastive framework and organize ADNIMERGE variables along a label-leakage spectrum. Fusion with cognitive scores yields 87.3% three-way accuracy, which we treat as a leakage-driven upper bound rather than an imaging result; fusion with regional volumes yields 73.0%. We observe that the choice of contrastive target changes what the image encoder learns: on MCI vs. CN, the image-only head reaches 52.4% when the encoder is aligned to cognitive scores and 73.8% when aligned to volumes, although no tabular input is used at inference. Third, restricting the input to a per-subject crop of the medial temporal lobe raises image-only three-way accuracy from 58.7% to 65.1%. All results come from single runs on a small balanced test set, and we report confidence intervals and the protocol differences that prevent direct comparison with published numbers.

Paul-Gabriel Nicolae, Irina Georgiana Mocanu

Computer Science and Engineering Department, Faculty of Automatic Control and Computers, National University of Science and Technology POLITEHNICA Bucharest, Romania

Alzheimer Multimodal Contrastive Learning Disease Anatomy Deep Network

Ask PDF

May 27, 2026cs.CV

Adaptive Temporal Gating of Longitudinal Magnetic Resonance Imaging for Alzheimer's Prediction

Predicting conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is critical for early intervention. Current deep learning paradigms predominantly rely on cross-sectional structural MRI, neglecting prognostic value in patient-specific anatomical trajectories. We introduce the Temporal Adaptive Fusion Network (TAF-Net), a hybrid CNN-Transformer architecture that models paired longitudinal 3D MRI scans. Central to TAF-Net is a Temporal Fusion Module governed by an Adaptive Temporal Gate, which learns patient-specific weightings to synthesize three spatiotemporal representations: explicit structural change, region-to-region temporal cross-attention, and bilateral feature concatenation. Evaluated on the Alzheimer's Disease Neuroimaging Initiative cohort for three-year MCI-to-AD conversion prediction, TAF-Net achieved the highest discriminative performance among all evaluated methods using only structural MRI, significantly outperforming the strongest baseline and approaching multimodal methods requiring PET, CSF, or genetic data. The architecture exhibited exceptional data efficiency, matching baseline performance with a fraction of training data. Ablation studies demonstrate that longitudinal fusion improves discrimination while reducing predictive variance by 48% compared to single-timepoint evaluation. Interpretability analyses reveal spatial attention aligned with established AD pathology in the medial temporal lobe and ventricles, while the gating mechanism prioritizes explicit volumetric change with strong positive correlation to conversion risk.

Alireza Moayedikia, Sara Fin, Alicia Troncoso Lora +1

School of Business Law and Entrepreneurship, Swinburne University of Technology, Melbourne, VIC, Australia · Australian Regenerative Medicine Institute, Monash University, Melbourne, VIC, Australia · Data Science & Big Data Lab, Universidad Pablo de Olavide, Seville, Spain +1

Alzheimer Magnetic Resonance Imaging Multimodal Deep Learning Spatial Attention Human Visual Cortex

Ask PDF