Exploring Robustness of Cortical Morphometry in the presence of white matter lesions, using Diffusion Models for Lesion Filling

2025-03-26

AI Summary

White matter lesions (WMLs) substantially compromise the accuracy and robustness of cortical thickness estimation, particularly undermining the reliability of neurodegenerative disease biomarkers. To address this, we propose a pseudo-3D U-Net–driven conditional denoising diffusion model that synthesizes healthy white matter tissue and fills lesions conditioned on binary lesion masks, achieving high-fidelity reconstruction. We conduct the first systematic evaluation of the robustness of mainstream deep learning–based segmentation tools—FastSurfer, DL+DiReCT, and ANTsPyNet—in the presence of WMLs for cortical morphometric measurement. The diffusion model is jointly trained on the OASIS and MSSEG multicenter datasets. Results demonstrate that deep learning methods inherently improve measurement robustness over FreeSurfer; following lesion filling with our diffusion model, mean global and regional cortical thickness estimation bias decreases by 42%, significantly enhancing biomarker reliability and clinical interpretability.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Cortical thickness measurements from magnetic resonance imaging, an important biomarker in many neurodegenerative and neurological disorders, are derived by many tools from an initial voxel-wise tissue segmentation. White matter (WM) hypointensities in T1-weighted imaging, such as those arising from multiple sclerosis or small vessel disease, are known to affect the output of brain segmentation methods and therefore bias cortical thickness measurements. These effects are well-documented among traditional brain segmentation tools but have not been studied extensively in tools based on deep-learning segmentations, which promise to be more robust. In this paper, we explore the potential of deep learning to enhance the accuracy and efficiency of cortical thickness measurement in the presence of WM lesions, using a high-quality lesion filling algorithm leveraging denoising diffusion networks. A pseudo-3D U-Net architecture trained on the OASIS dataset to generate synthetic healthy tissue, conditioned on binary lesion masks derived from the MSSEG dataset, allows realistic removal of white matter lesions in multiple sclerosis patients. By applying morphometry methods to patient images before and after lesion filling, we analysed robustness of global and regional cortical thickness measurements in the presence of white matter lesions. Methods based on a deep learning-based segmentation of the brain (Fastsurfer, DL+DiReCT, ANTsPyNet) exhibited greater robustness than those using classical segmentation methods (Freesurfer, ANTs).

Problem

• Assessing cortical thickness robustness with WM lesions
• Evaluating deep learning vs traditional segmentation methods
• Developing lesion filling using diffusion models for accuracy

Innovation

• Using diffusion models for lesion filling
• Pseudo-3D U-Net for synthetic healthy tissue
• Deep learning enhances cortical thickness accuracy