SOURCE-LINKED INTELLIGENCE

CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

BraTS local synthesis replaces masked regions in T1-weighted brain MRI with plausible tumor-free tissue while preserving observed anatomy. We present CATCH, conditional 3D diffusion in an invertible Haar-wavelet domain. Its denoiser receives noisy target coefficients, voided-image coefficients, and a signed mask; tumor-excluded wavelet reconstruction and a hole-focused loss guide training, and hard compositing preserves observed voxels. We compare fixed masks, tumor-component augmentation, and a weighted mixture of tumor-derived, irregular-blob, and ellipsoidal masks. Of 25 development cases,

Read original source ↗ Open in workspace

recordType

paper

region

Global