arXiv:2606. 19300v1 Announce Type: cross Abstract: Glioma segmentation in multiparametric MRI is a critical component of treatment planning.
The study evaluates the reliability of deep‑ensemble uncertainty for brain tumour segmentation on the BraTS‑GoAT dataset. A 5‑fold cross‑validated nnU‑Net baseline and a 3‑seed deep ensemble were compared for calibration and error detection; the ensemble showed modest gains in calibration on in‑distribution data but the single model’s confidence remained flat while accuracy degraded under synthetic corruptions. Disagreement among ensemble members rose sharply with corruption severity, proving to be a more sensitive indicator of acquisition shift than single‑model confidence.
arXiv:2607. 16317v1 Announce Type: cross Abstract: Deep networks now subtype brain tumors on MRI about as well as specialist readers, yet accuracy is not what keeps them out of the clinic.
arXiv:2609.21412v1 Announce Type: new Abstract: Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem...
The paper introduces Missing Modality-Aware Local Temperature Scaling (MMA‑LTS), a post‑hoc voxel‑wise confidence calibration technique designed for multimodal brain tumor segmentation. MMA‑LTS adapts a temperature field based on which MRI modalities are present and a voxel‑wise difficulty score, addressing calibration errors that arise when specific modalities are missing. Experiments on BraTS 2020 and FeTS 2024 demonstrate that MMA‑LTS improves calibration while maintaining segmentation accuracy across various missing‑modality scenarios.
arXiv:2608. 08173v1 Announce Type: cross Abstract: Longitudinal MRI enables sensitive measurement of structural brain change for studying aging and neurodegenerative disease.
arXiv:2607. 22727v1 Announce Type: cross Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can be quiet: sensor noise, patient motion, low- resolution acquisition, and contrast variability may all alter model behavior without producing an obvious warning.
The paper introduces Contrastive Uncertainty Learning (CUL), a supervised framework that leverages voxel‑wise predictive uncertainty to guide representation learning for multi‑structure segmentation in lower‑pelvic MRI. Using Monte Carlo Dropout, CUL identifies uncertain voxels and shapes the embedding space so that low‑uncertainty, correctly predicted features become stable while high‑uncertainty or misclassified features are repelled, preventing feature collapse at challenging boundaries. Evaluated on 589 prostate MRI scans with a ViT‑based UperNet decoder, CUL achieves comparable Dice scores to a baseline while significantly reducing surface distance for most structures, and ablation studies confirm the necessity of both uncertainty‑guided sampling and the contrastive objective.
arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.
The paper introduces Recursive Uncertainty-Gated Image Registration (RUGI), an iterative refinement method that updates deformation fields predicted by learning-based registration models using a gating map. Two gating strategies are explored: an uncertainty-based approach and an image residual error approach, both concentrating updates on difficult regions. Experiments on cardiac MRI and echocardiography datasets show that RUGI consistently improves registration accuracy, with the error-gated variant reducing MSE by 27‑37% on pretrained models and lowering ejection fraction estimation errors.
arXiv:2610.17401v1 Announce Type: new Abstract: Incomplete field-of-view (FOV) diffusion MRI (dMRI) acquisitions compromise whole-brain white matter analysis by excluding brain regions from tractogra...
arXiv:2606. 00123v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks.