Robust 3D Brain MRI Inpainting with Random Masking Augmentation

• URL: http://arxiv.org/abs/2511.20202v1
• Date: Tue, 25 Nov 2025 11:26:10 GMT
• Title: Robust 3D Brain MRI Inpainting with Random Masking Augmentation
• Abstract summary: This paper details our submission to the BraTS-Inpainting 2025 challenge, a novel deep learning framework for synthesizing healthy tissue in 3D scans.<n>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.<n>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.
• Score: 8.979979393832672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing [0.5626158829476339]
  Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue.<n>On the BraTS local-synthesis benchmark, which ranks submissions on the structural similarity index (SSIM), the peak signal-to-noise ratio, and the mean squared error (MSE) jointly, the strongest recent models are accurate.<n>We address this in post-processing, forming a deep ensemble of the two co-first-place 2025 models and training a lightweight residual refiner on the ensemble's own outputs.
  arXiv  Detail & Related papers  (2026-09-03T15:13:59Z)
• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI [1.2560645967579729]
  We address the challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints.<n>Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1.<n>The final model was selected based on the highest Dice Similarity Coefficient achieved on the validation set after fine-tuning.
  arXiv  Detail & Related papers  (2025-10-29T21:57:12Z)
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model [100.86587937568832]
  Ring-1T is the first open-source, state-of-the-art thinking model with a trillion-scale parameter.<n>It features 1 trillion total parameters and activates approximately 50 billion per token.
  arXiv  Detail & Related papers  (2025-10-21T17:46:14Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow [3.024548464833694]
  Contrast-enhanced (CE) T1-weighted MRI is central to neuro-oncologic diagnosis but requires gadolinium-based agents.<n>We propose a two-stage Posterior-Mean Rectified Flow pipeline for synthesizing CE brain MRI from non-contrast inputs.
  arXiv  Detail & Related papers  (2025-08-18T05:55:57Z)
• U-Net Based Healthy 3D Brain Tissue Inpainting [5.347187213114967]
  This paper introduces a novel approach to synthesize healthy 3D brain tissue from masked input images.<n>Our proposed method employs a U-Net-based architecture, which is designed to effectively reconstruct the missing or corrupted regions of brain MRI scans.<n>Our model is trained on the BraTS-Local-Inpainting dataset and demonstrates the exceptional performance in recovering healthy brain tissue.
  arXiv  Detail & Related papers  (2025-07-24T06:26:46Z)
• A Privacy-Preserving Federated Learning Framework for Generalizable CBCT to Synthetic CT Translation in Head and Neck [0.0]
  Cone-beam computed tomography (CBCT) has become a widely adopted modality for image-guided radiotherapy (IGRT)<n>We propose a cross-silo horizontal federated learning (FL) approach for CBCT-to-sCT synthesis in the head and neck region.
  arXiv  Detail & Related papers  (2025-06-10T10:10:56Z)
• The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report [170.81876816944754]
  The NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR) aims to advance the development of models that optimize key computational metrics.<n>This paper meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques.
  arXiv  Detail & Related papers  (2025-04-14T20:18:21Z)
• Weakly Supervised Spatial Implicit Neural Representation Learning for 3D MRI-Ultrasound Deformable Image Registration in HDR Prostate Brachytherapy [5.457582385030137]
  This study introduces a novel weakly supervised SINR-based approach for 3D MRI-US deformable registration.<n>It achieves accurate, robust, and computationally efficient registration, enhancing real-time image guidance in HDR prostate brachytherapy.
  arXiv  Detail & Related papers  (2025-03-18T16:30:08Z)
• Cancer-Net PCa-Seg: Benchmarking Deep Learning Models for Prostate Cancer Segmentation Using Synthetic Correlated Diffusion Imaging [65.83291923029985]
  Prostate cancer (PCa) is the most prevalent cancer among men in the United States, accounting for nearly 300,000 cases, 29% of all diagnoses and 35,000 total deaths in 2024.<n>Traditional screening methods such as prostate-specific antigen (PSA) testing and magnetic resonance imaging (MRI) have been pivotal in diagnosis, but have faced limitations in specificity and generalizability.<n>We employ several state-of-the-art deep learning models, including U-Net, SegResNet, Swin UNETR, Attention U-Net, and LightM-UNet, to segment prostate glands from a 200 CDI$
  arXiv  Detail & Related papers  (2025-01-15T22:23:41Z)
• Brain Tumour Removing and Missing Modality Generation using 3D WDM [2.0697927556594573]
  This paper presents the second-placed solution for task 8 and the participation solution for task 7 of BraTS 2024.<n>The adoption of automated brain analysis algorithms to support clinical practice is increasing.<n>Many of these algorithms struggle with the presence of brain lesions or the absence of certain MRI modalities.
  arXiv  Detail & Related papers  (2024-11-07T11:29:55Z)
• H2NF-Net for Brain Tumor Segmentation using Multimodal MR Imaging: 2nd Place Solution to BraTS Challenge 2020 Segmentation Task [96.49879910148854]
  Our H2NF-Net uses the single and cascaded HNF-Nets to segment different brain tumor sub-regions. We trained and evaluated our model on the Multimodal Brain Tumor Challenge (BraTS) 2020 dataset. Our method won the second place in the BraTS 2020 challenge segmentation task out of nearly 80 participants.
  arXiv  Detail & Related papers  (2020-12-30T20:44:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.