arXiv:2604.08015v3 Announce Type: replace-cross
Abstract: Small lesions in brain MRI are hard to segment because they occupy a tiny fraction of the volume and are dominated by background and larger l...
By Minh Sao Khue Luu, Evgeniy N. Pavlovskiy, Bair N. Tuchinov
CATCH is a conditional 3D diffusion model operating in an invertible Haar-wavelet domain designed to inpaint masked regions in T1‑weighted brain MRI with plausible, tumor‑free tissue while preserving observed anatomy. The model’s denoiser uses noisy target coefficients, voided‑image coefficients, and a signed mask, guided by tumor‑excluded wavelet reconstruction and a hole‑focused loss, and hard compositing ensures observed voxels remain unchanged. Experiments on BraTS data show that a weighted mixture of tumor‑derived, irregular‑blob, and ellipsoidal masks yields the best performance, achieving higher SSIM, PSNR, and lower MSE compared to fixed or random augmentation baselines.
By Simon Winther Albertsen, Hjalte Bjoernstrup, Said Djafar Said, Mostafa Mehdipour Ghazi
arXiv:2608. 16377v1 Announce Type: cross Abstract: Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap.
By Qinghui Liu, Jon Andr\'e Ottesen, Atle Bj{\o}rnerud, Kyrre Eeg Emblem
The paper presents a segmentation pipeline for brain metastases in both pre‑ and post‑treatment cases using a 5‑fold nnU‑Net ResEnc‑L ensemble trained on 1,296 four‑modality cases. A rule‑based post‑processing cascade improves the lesion‑wise Dice similarity coefficient (LW‑DSC) for enhancing tumour, tumour core, whole tumour, and resection cavity sub‑regions, achieving LW‑DSC scores of 0.733, 0.751, 0.713, and 0.549 respectively on the official validation leaderboard. The authors conduct a five‑fold out‑of‑fold analysis to validate the robustness of each post‑processing stage, provide a mechanistic explanation of LW‑DSC behaviour, and report thirteen negative results that challenge common intuitions, with all code released under Apache‑2.0.
By Haobin Liu, Xin Wang
The paper proposes a lightweight residual refiner that post‑processes the outputs of a two‑model ensemble for brain‑MRI inpainting. By training the refiner with an λ‑weighted combination of α loss and SSIM, the authors achieve a modest but statistically significant SSIM improvement (from 0.8767 to 0.8780 on a held‑out set) without altering MSE. Ablations show that adding a third model or using classical unsharp masking does not yield similar gains, indicating the improvement comes from learned sharpening rather than generic post‑processing.
By Kubilay Ka\u{g}an K\"om\"urc\"u, \.Ilkay \"Oks\"uz
The paper introduces a bi‑temporal framework that links admission computed tomography perfusion (CTP) data with follow‑up diffusion‑weighted MRI (DWI) outcomes in acute ischemic stroke. By extracting statistical, radiomic, and deep‑learning features from CTP and classifying tissue into six outcome‑aware regions, the authors demonstrate that CTP signatures can distinguish salvaged versus infarcted penumbra and identify non‑hypoperfused tissue that later infarcts. Cross‑dataset validation on the ISLES'24 dataset confirms consistent feature‑space separations, suggesting that admission CTP contains richer outcome information than traditional core‑penumbra delineation.
By Md Sazidur Rahman, Kjersti Engan, Kathinka D{\ae}hli Kurz, Mahdieh Khanmohammadi