POWDR: Pathology-preserving Outpainting with Wavelet Diffusion for 3D MRI

2026-01-14

AI Summary

This study addresses the challenge of scarce and class-imbalanced pathological samples in medical imaging, which limits the performance of segmentation and classification models. To overcome this, the authors propose a 3D MRI pathology-preserving outpainting framework based on a conditional wavelet diffusion model. By integrating a wavelet-domain conditioning mechanism with a stochastic connected masking strategy, the method generates anatomically plausible surrounding tissues while preserving authentic lesion structures, thereby enhancing data diversity without fabricating pathologies. Evaluated on BraTS and knee MRI datasets, the synthesized images achieve strong performance in terms of FID, SSIM, and LPIPS metrics. When incorporated into downstream tasks, the synthetic data improve tumor segmentation Dice scores from 0.6992 to 0.7137, with no significant deviation in brain tissue volume distributions, demonstrating the framework’s practical utility for controllable synthesis across diverse anatomical regions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Medical imaging datasets often suffer from class imbalance and limited availability of pathology-rich cases, which constrains the performance of machine learning models for segmentation, classification, and vision-language tasks. To address this challenge, we propose POWDR, a pathology-preserving outpainting framework for 3D MRI based on a conditioned wavelet diffusion model. Unlike conventional augmentation or unconditional synthesis, POWDR retains real pathological regions while generating anatomically plausible surrounding tissue, enabling diversity without fabricating lesions. Our approach leverages wavelet-domain conditioning to enhance high-frequency detail and mitigate blurring common in latent diffusion models. We introduce a random connected mask training strategy to overcome conditioning-induced collapse and improve diversity outside the lesion. POWDR is evaluated on brain MRI using BraTS datasets and extended to knee MRI to demonstrate tissue-agnostic applicability. Quantitative metrics (FID, SSIM, LPIPS) confirm image realism, while diversity analysis shows significant improvement with random-mask training (cosine similarity reduced from 0.9947 to 0.9580; KL divergence increased from 0.00026 to 0.01494). Clinically relevant assessments reveal gains in tumor segmentation performance using nnU-Net, with Dice scores improving from 0.6992 to 0.7137 when adding 50 synthetic cases. Tissue volume analysis indicates no significant differences for CSF and GM compared to real images. These findings highlight POWDR as a practical solution for addressing data scarcity and class imbalance in medical imaging. The method is extensible to multiple anatomies and offers a controllable framework for generating diverse, pathology-preserving synthetic data to support robust model development.

Problem

• class imbalance
• data scarcity
• pathology-rich cases
• medical imaging
• 3D MRI

Innovation

• pathology-preserving outpainting
• wavelet diffusion
• 3D MRI synthesis
• conditional diffusion model
• data augmentation