SADL is a size‑adaptive decision layer that improves chronic stroke lesion segmentation on T1‑weighted MRI by combining an eleven‑member nnU‑Net ensemble with adaptive thresholding and pruning. The ensemble incorporates dice + top‑K loss, heavy augmentation, per‑lesion volume re‑weighting, stochastic weight averaging, and a cohort‑balanced sampling block with a residual‑encoder backbone. On a 91‑case holdout, SADL achieves Dice 0.7322, lesion‑F1 0.7461, and PR‑AUC 0.8430, with a statistically significant gain in lesion‑F1 (p=0.024) especially for small lesions.
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...
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.
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.
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.
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.
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.
The paper presents a pragmatic segmentation pipeline for brain metastases in the BraTS 2026 Task 1, using a 5‑fold nnU-Net ResEnc‑L ensemble trained for 1,000 epochs on 1,296 four‑modality cases. A rule‑based post‑processing cascade tuned for the lesion‑wise Dice similarity coefficient (LW‑DSC) improves performance, achieving LW‑DSC scores of 0.733, 0.751, 0.713, and 0.549 on enhancing tumour, tumour core, whole tumour, and resection cavity, respectively. The authors audit each post‑processing stage with a five‑fold out‑of‑fold analysis, confirm two stages as robust, and provide a mechanistic analysis of LW‑DSC, along with thirteen negative results that challenge common intuitions.
This study presents a domain-aware deep learning framework based on nnU-Net for segmenting ischemic stroke lesions on non‑contrast CT scans and quantifying net water uptake (NWU). Trained on data from Hamburg and the Acute Ischemic Stroke Dataset, the model was fine‑tuned on small target‑domain subsets from Boston and ISLES, achieving median Dice scores of 0.68 and 0.56 for lesions ≥30 mL, and an NWU mean absolute error of 1.37 percentage points on the Boston cohort. The results demonstrate that target‑domain adaptation can enable accurate NCCT‑only infarct segmentation and low‑error NWU estimation across heterogeneous multicenter datasets.
arXiv:2608. 19769v1 Announce Type: cross Abstract: Fast and accurate segmentation of Acute Ischemic Stroke (AIS) lesions is essential for stroke prognosis and treatment planning.
arXiv:2609.24769v1 Announce Type: new Abstract: Brain metastases are the most common intracranial malignancy, occurring in roughly 30% of patients with primary solid tumors and carrying a median surv...
The study investigates how image‑domain Poisson perturbations affect the classification of ischemic core/penumbra in non‑contrast CT slices. Using a CPAISD cohort, the authors compared direct ResNet‑18 classification with a denoising‑then‑classifying pipeline and found that denoising generally reduced performance. A prospective experiment with joint denoising‑classification models showed no statistically significant advantage over direct noisy classification, indicating limited robustness to Poisson noise.
arXiv:2609.09634v1 Announce Type: new Abstract: Large networks and ensembles often lead medical image segmentation challenges, but their storage and inference demands complicate deployment. We presen...