V2C-Long: Longitudinal Cortex Reconstruction with Spatiotemporal Correspondence

2024-02-27

arXiv.org

AI Summary

Accurate spatiotemporal point correspondence on highly convoluted cortical surfaces in longitudinal MRI data remains challenging, leading to unreliable morphometric change analysis. Method: We propose the first end-to-end deep learning framework for longitudinal cortical reconstruction, featuring a novel cascaded dual-template deformation network that aggregates subject-specific templates within the mesh space to ensure intrinsic spatiotemporal consistency in surface reconstruction. Contribution/Results: Trained and validated on multicenter longitudinal neuroimaging data, our method significantly outperforms mainstream tools (e.g., FreeSurfer) in surface reconstruction accuracy, inter-timepoint consistency, test–retest reliability, and sensitivity to Alzheimer’s disease–related cortical atrophy. It establishes a more robust and comparable cortical representation for longitudinal modeling of brain development and neurodegeneration.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Reconstructing the cortex from longitudinal magnetic resonance imaging (MRI) is indispensable for analyzing morphological alterations in the human brain. Despite the recent advancement of cortical surface reconstruction with deep learning, challenges arising from longitudinal data are still persistent. Especially the lack of strong spatiotemporal point correspondence between highly convoluted brain surfaces hinders downstream analyses, as local morphology is not directly comparable if the anatomical location is not matched precisely. To address this issue, we present V2C-Long, the first dedicated deep learning-based cortex reconstruction method for longitudinal MRI. V2C-Long exhibits strong inherent spatiotemporal correspondence across subjects and visits, thereby reducing the need for surface-based post-processing. We establish this correspondence directly during the reconstruction via the composition of two deep template-deformation networks and innovative aggregation of within-subject templates in mesh space. We validate V2C-Long on two large neuroimaging studies, focusing on surface accuracy, consistency, generalization, test-retest reliability, and sensitivity. The results reveal a substantial improvement in longitudinal consistency and accuracy compared to existing methods. In addition, we demonstrate stronger evidence for longitudinal cortical atrophy in Alzheimer's disease than longitudinal FreeSurfer.

Problem

• Reconstructing cortex from longitudinal MRI
• Ensuring spatiotemporal correspondence in brain surfaces
• Improving accuracy in longitudinal cortical atrophy detection

Innovation

• Deep learning-based reconstruction
• Spatiotemporal correspondence enhancement
• Template-deformation networks composition