Development of an isotropic segmentation model for medial temporal lobe subregions on anisotropic MRI atlas using implicit neural representation

2025-08-23

AI Summary

T2-weighted MRI suffers from anisotropic resolution, limiting accurate quantification of medial temporal lobe (MTL) cortical subregion thickness and undermining the reliability of early Alzheimer’s disease (AD) biomarkers. To address this, we propose an unsupervised multimodal fusion framework based on implicit neural representations that jointly leverages T1w and T2w MRI to achieve super-resolution reconstruction—from anisotropic to isotropic—of MTL cortical maps while simultaneously performing high-precision subregion segmentation, without requiring manual annotations. Our method overcomes limitations of conventional registration and interpolation approaches, significantly improving cortical thickness measurement accuracy and scan-rescan stability. On an independent test set, thickness features derived by our method demonstrate superior discriminability between mild cognitive impairment and cognitively normal older adults. Longitudinal analysis reveals reduced biomarker variability and enhanced reproducibility, establishing a generalizable, unsupervised paradigm for high-resolution, atlas-free MTL mapping in early AD neuroimaging assessment.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising

Abstract

Imaging biomarkers in magnetic resonance imaging (MRI) are important tools for diagnosing and tracking Alzheimer's disease (AD). As medial temporal lobe (MTL) is the earliest region to show AD-related hallmarks, brain atrophy caused by AD can first be observed in the MTL. Accurate segmentation of MTL subregions and extraction of imaging biomarkers from them are important. However, due to imaging limitations, the resolution of T2-weighted (T2w) MRI is anisotropic, which makes it difficult to accurately extract the thickness of cortical subregions in the MTL. In this study, we used an implicit neural representation method to combine the resolution advantages of T1-weighted and T2w MRI to accurately upsample an MTL subregion atlas set from anisotropic space to isotropic space, establishing a multi-modality, high-resolution atlas set. Based on this atlas, we developed an isotropic MTL subregion segmentation model. In an independent test set, the cortical subregion thickness extracted using this isotropic model showed higher significance than an anisotropic method in distinguishing between participants with mild cognitive impairment and cognitively unimpaired (CU) participants. In longitudinal analysis, the biomarkers extracted using isotropic method showed greater stability in CU participants. This study improved the accuracy of AD imaging biomarkers without increasing the amount of atlas annotation work, which may help to more accurately quantify the relationship between AD and brain atrophy and provide more accurate measures for disease tracking.

Problem

• Develop isotropic segmentation for MTL subregions on anisotropic MRI
• Improve accuracy of cortical thickness extraction in Alzheimer's diagnosis
• Enhance biomarker stability for tracking mild cognitive impairment

Innovation

• Implicit neural representation for upsampling
• Combining T1 and T2 MRI resolution advantages
• Isotropic segmentation model for MTL subregions