Robust 3D Brain MRI Inpainting with Random Masking Augmentation

TL;DR

This paper presents a novel 3D brain MRI inpainting method using a U-Net with random masking augmentation, achieving state-of-the-art results and winning the 2025 BraTS-Inpainting Challenge.

Contribution

The paper introduces a new deep learning framework with a random masking augmentation strategy for improved 3D MRI inpainting performance.

Findings

Achieved top performance in the 2025 BraTS-Inpainting Challenge.

Outperformed previous years' winning solutions.

Demonstrated high SSIM and PSNR scores on validation and test sets.

Abstract

The ASNR-MICCAI BraTS-Inpainting Challenge was established to mitigate dataset biases that limit deep learning models in the quantitative analysis of brain tumor MRI. This paper details our submission to the 2025 challenge, a novel deep learning framework for synthesizing healthy tissue in 3D scans. The core of our method is a U-Net architecture trained to inpaint synthetically corrupted regions, enhanced with a random masking augmentation strategy to improve generalization. Quantitative evaluation confirmed the efficacy of our approach, yielding an SSIM of 0.873$\pm$0.004, a PSNR of 24.996$\pm$4.694, and an MSE of 0.005$\pm$0.087 on the validation set. On the final online test set, our method achieved an SSIM of 0.919$\pm$0.088, a PSNR of 26.932$\pm$5.057, and an RMSE of 0.052$\pm$0.026. This performance secured first place in the BraTS-Inpainting 2025 challenge and surpassed the winning solutions from the 2023 and 2024 competitions on the official leaderboard.