Nearly isotropic segmentation for medial temporal lobe subregions in multi-modality MRI

2025-04-25

AI Summary

T2-weighted (T2w) MRI suffers from low out-of-plane resolution, leading to inaccurate cortical thickness estimation in medial temporal lobe (MTL) subregions. Method: We propose an isotropic segmentation framework comprising three stages: (1) non-local means-based image super-resolution to enhance T2w resolution; (2) a UNet-driven label super-resolution mapping model to generate high-fidelity subregional labels; and (3) a T1w+T2w multimodal 3D U-Net for precise MTL substructure segmentation. Contribution/Results: This work establishes the first high-resolution, near-isotropic multimodal MTL atlas and enables reliable subregional thickness quantification under T2w-dominant acquisition. Validation demonstrates significant improvement in MTL subregion thickness measurement accuracy, enhancing sensitivity and clinical utility of MTL thickness as an imaging biomarker for neurodegenerative disorders such as Alzheimer’s disease.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning
• 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: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Morphometry of medial temporal lobe (MTL) subregions in brain MRI is sensitive biomarker to Alzheimers Disease and other related conditions. While T2-weighted (T2w) MRI with high in-plane resolution is widely used to segment hippocampal subfields due to its higher contrast in hippocampus, its lower out-of-plane resolution reduces the accuracy of subregion thickness measurements. To address this issue, we developed a nearly isotropic segmentation pipeline that incorporates image and label upsampling and high-resolution segmentation in T2w MRI. First, a high-resolution atlas was created based on an existing anisotropic atlas derived from 29 individuals. Both T1-weighted and T2w images in the atlas were upsampled from their original resolution to a nearly isotropic resolution 0.4x0.4x0.52mm3 using a non-local means approach. Manual segmentations within the atlas were also upsampled to match this resolution using a UNet-based neural network, which was trained on a cohort consisting of both high-resolution ex vivo and low-resolution anisotropic in vivo MRI with manual segmentations. Second, a multi-modality deep learning-based segmentation model was trained within this nearly isotropic atlas. Finally, experiments showed the nearly isotropic subregion segmentation improved the accuracy of cortical thickness as an imaging biomarker for neurodegeneration in T2w MRI.

Problem

• Improving accuracy of MTL subregion thickness measurements in MRI
• Developing isotropic segmentation for T2w MRI with upsampling
• Enhancing cortical thickness as biomarker for neurodegeneration

Innovation

• Upsampling T1 and T2w images to near-isotropic resolution
• UNet-based neural network for label upsampling
• Multi-modality deep learning segmentation model