Saved in:
Bibliographic Details
Main Authors: Zhang, Juexin, Weng, Ying, Chen, Ke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20202
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911286032334848
author Zhang, Juexin
Weng, Ying
Chen, Ke
author_facet Zhang, Juexin
Weng, Ying
Chen, Ke
contents 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$0.026. This performance secured first place in the BraTS-Inpainting 2025 challenge and surpassed the winning solutions from the 2023 and 2024 competitions on the official leaderboard.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20202
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust 3D Brain MRI Inpainting with Random Masking Augmentation
Zhang, Juexin
Weng, Ying
Chen, Ke
Computer Vision and Pattern Recognition
The ASNR-MICCAI BraTS-Inpainting Challenge was established to mitigate dataset biases that limit deep learning models in the quantitative analysis of brain tumor MRI. This paper details our submission to the 2025 challenge, a novel deep learning framework for synthesizing healthy tissue in 3D scans. The core of our method is a U-Net architecture trained to inpaint synthetically corrupted regions, enhanced with a random masking augmentation strategy to improve generalization. Quantitative evaluation confirmed the efficacy of our approach, yielding an SSIM of 0.873$\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.
title Robust 3D Brain MRI Inpainting with Random Masking Augmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20202