Abstract
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, tumorcomponent
augmentation, and a weighted mixture of tumor-derived,
irregular-blob, and ellipsoidal masks. Of 25 development cases, five
prespecified cases select each arm’s checkpoint and all 25 of their trajectory
aggregations; a separate 75-case internal set compares the frozen
pipelines and selects a weighted mixture for organizer evaluation. Fivetrajectory
averaging yielded internal SSIM/PSNR/MSE (mean±SD) of
0.80±0.13, 19.18±1.80 dB, and 0.010±0.005. As the sole officially evaluated
pipeline, weighted mixture yielded 0.772 ± 0.119, 20.89 ± 3.27 dB,
and 0.0098 ± 0.0054 on the 219-case BraTS 2026 validation set. Against
compute-matched random augmentation internally, it improved SSIM
by 0.019 (95% bootstrap CI: 0.013–0.025), PSNR by 0.95 dB, and MSE
by 0.003; all three paired comparisons remained significant after Holm
correction. Results favor the complete weighted-mixture policy within
CATCH; absent official fixed- and random-pipeline scores and a directly
comparable external baseline limit broader conclusions.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/BraTS_Inpainting_018.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=FOlGqDQq9v
BibTex
@InProceedings{AlbSim_CATCH_MICCAISAT2026,
author = { Albertsen, Simon Winther AND Bjoernstrup, Hjalte AND Said, Said Djafar AND Mehdipour Ghazi, Mostafa},
title = { { CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17254},
month = {pending},
page = {pending}
}