Skip to main navigation Skip to search Skip to main content

Robust 3D Brain MRI Inpainting with Random Masking Augmentation

  • Juexin Zhang
  • , Ying Weng*
  • , Ke CHEN
  • *Corresponding author for this work

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

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 ± 0.004, a PSNR of 24.996 ± 4.694, and an MSE of 0.005 ± 0.087 on the validation set. On the final online test set, our method achieved an SSIM of 0.919 ± 0.088, a PSNR of 26.932 ± 5.057, and an RMSE of 0.052 ± 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.

Original languageEnglish
Title of host publicationSegmentation, Classification, and Synthesis for Brain Tumors and Traumatic Brain Injuries - MICCAI 2025 Challenges
Subtitle of host publicationBraTS-Lighthouse 2025 and AIMS-TBI 2025, Held in Conjunction with MICCAI 2025, Proceedings
EditorsSpyridon Bakas, Emily Dennis, Mehdi Astaraki, Ujjwal Baid, Gian Marco Conte, Martha Foltyn-Dumitru, Zhifan Jiang, Marius George Linguraru, Dominic Labella, Marie-Christin Metz, Udunna Anazodo, Maria Correia de Verdier, Florian Kofler, Hongwei Bran Li, Nazanin Maleki
PublisherSpringer Science and Business Media Deutschland GmbH
Pages102-109
Number of pages8
ISBN (Print)9783032163691
DOIs
Publication statusPublished - 2026
EventBrain TumorS Lighthouse Cluster of Challenges, and the Automated Identification of Moderate-Severe Traumatic Brain Injury Lesions Challenge, BraTS 2025 and AIMS-TBI 2025, held in Conjunction International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2025 - Daejeon, Korea, Republic of
Duration: 23 Sept 202527 Sept 2025

Publication series

NameLecture Notes in Computer Science
Volume16377 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceBrain TumorS Lighthouse Cluster of Challenges, and the Automated Identification of Moderate-Severe Traumatic Brain Injury Lesions Challenge, BraTS 2025 and AIMS-TBI 2025, held in Conjunction International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2025
Country/TerritoryKorea, Republic of
CityDaejeon
Period23/09/2527/09/25

Free Keywords

  • BraTS 2025
  • Healthy Tissue Synthesis
  • Inpainting
  • MRI

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Robust 3D Brain MRI Inpainting with Random Masking Augmentation'. Together they form a unique fingerprint.

Cite this