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

Authors

Abstract

<b>Background:</b> Medical imaging datasets often suffer from class imbalance and limited availability of pathology-rich cases, which limit the performance of machine learning models for segmentation, classification, and vision-language tasks. We propose POWDR, a pathology-preserving outpainting framework for 3D MRI that uses real pathological regions as conditioning evidence while generating anatomically plausible surrounding tissue. <b>Methods:</b> 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 reduce conditioning-induced collapse and improve diversity outside the lesion. POWDR is evaluated on brain MRI using BraTS datasets and extended to knee MRI to assess applicability beyond brain imaging. <b>Results:</b> Quantitative metrics (FID, MS-SSIM, LPIPS) were used to assess image realism. Random connected mask training improved diversity, reducing cosine similarity from 0.9947 to 0.9580 and increasing KL divergence from 0.00026 to 0.01494. To validate pathology preservation, we compared lesion overlap, volume, intensity, and morphology. For downstream segmentation, nnU-Net performance improved from 0.6992 to 0.7137 Dice after augmentation with 50 synthetic cases, representing a modest but statistically significant improvement (paired <i>t</i>-test, <i>p</i> = 0.016). Tissue volume analysis showed no significant differences for CSF and GM compared to real images, while WM volume was lower in synthetic images. <b>Conclusions:</b> POWDR provides a framework for generating diverse, pathology-preserving synthetic MRI data. The results suggest potential utility for data augmentation while maintaining clinically relevant lesion characteristics.

Tags

Topics