Self-Supervised CSF Inpainting with Synthetic Atrophy for Improved Accuracy Validation of Cortical Surface Analyses

TL;DR

This paper introduces a 3D GAN-based self-supervised inpainting method to generate realistic CSF regions in MRI images, enhancing the validation of cortical thickness measurements by producing more plausible synthetic atrophy.

Contribution

The paper presents a novel 3D GAN model with patch dropout, edge priors, and sinusoidal encoding for realistic CSF inpainting in MRI, improving upon prior 2D methods.

Findings

Enhanced quality of synthetic MRI images with realistic CSF regions

Improved validation accuracy for cortical thickness measurements

Framework adaptable to unseen data with fine-tuning

Abstract

Accuracy validation of cortical thickness measurement is a difficult problem due to the lack of ground truth data. To address this need, many methods have been developed to synthetically induce gray matter (GM) atrophy in an MRI via deformable registration, creating a set of images with known changes in cortical thickness. However, these methods often cause blurring in atrophied regions, and cannot simulate realistic atrophy within deep sulci where cerebrospinal fluid (CSF) is obscured or absent. In this paper, we present a solution using a self-supervised inpainting model to generate CSF in these regions and create images with more plausible GM/CSF boundaries. Specifically, we introduce a novel, 3D GAN model that incorporates patch-based dropout training, edge map priors, and sinusoidal positional encoding, all of which are established methods previously limited to 2D domains. We show that our framework significantly improves the quality of the resulting synthetic images and is adaptable to unseen data with fine-tuning. We also demonstrate that our resulting dataset can be employed for accuracy validation of cortical segmentation and thickness measurement.