arXiv:2606. 16868v1 Announce Type: cross Abstract: While federated learning (FL) enables collaborative medical image segmentation without centralizing sensitive data, real-world deployment is frequently complicated by cross-site label imperfections such as contour disagreement, missing or additional structures, and confused labels.
arXiv:2609.14943v1 Announce Type: new Abstract: Pseudo-labeling is a strong paradigm for semi-supervised medical image segmentation, yet its effectiveness is highly sensitive to confidence thresholdi...
The paper introduces Report Supervision (R‑Super), a framework that uses radiology reports to supervise tumor segmentation models. By incorporating loss functions that align segmentation outputs with report‑derived tumor counts, sizes, and locations, R‑Super improves detection and segmentation performance. Experiments on kidney and pancreatic tumors show up to a 15% increase in F1‑Score and DSC compared to mask‑only training, outperforming methods like CLIP and multi‑task learning.
arXiv:2608. 04147v1 Announce Type: cross Abstract: Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases.
SAM-DCE is a framework that adapts the Segment Anything Model (SAM) for fully automatic, prompt‑free medical image segmentation. It introduces Spatial Representation Compensation (SRC) to recover fine anatomical details from intermediate Vision Transformer features and Semantic Token Calibration (STC) to enhance the consistency of foreground mask tokens. By refining spatial and semantic representations before using SAM’s original token‑to‑mask mechanism, SAM‑DCE achieves superior performance on the Synapse multi‑organ CT segmentation dataset, with a mean Dice score of 83.86% and an HD95 of 16.04 mm, outperforming several CNN, Transformer, and SAM baselines.
The paper introduces the Semantic‑Spatial Residual Bank (SSRB) for single‑annotation, multi‑hypothesis segmentation, where each training image has only one mask but the model must generate a set of masks that cover possible human annotations at test time. SSRB combines a frozen semantic bank, trained with balanced assignments, with a residual learned from the image for each hypothesis. Experiments on five medical endpoints and the BSDS dataset show that SSRB improves coverage of held‑out masks compared to a Probabilistic U‑Net, produces more distinct useful masks on LIDC and LIDC‑hard, and maintains semantic grouping performance while its advantage grows with the number of returned masks.
The paper introduces a denoising mutual knowledge distillation framework for bi-directional multiple instance learning (MIL) applied to whole slide image classification in digital pathology. By integrating instance-level classifiers and masks, the method grounds predictions on supporting patches while mitigating noisy labels. The proposed algorithm enhances both bag- and instance-level performance, as demonstrated on public pathology datasets.
arXiv:2610.26954v1 Announce Type: new Abstract: Auxiliary learning (AL), which can improve the performance of a primary task by leveraging related auxiliary tasks, is commonly regarded as a special c...
arXiv:2609.23815v1 Announce Type: new Abstract: Medical image segmentation models typically rely on large amounts of densely annotated volumetric data, limiting their scalability across tasks and ima...
arXiv:2606. 11695v1 Announce Type: cross Abstract: High-quality labeled data is essential for training reliable ML/DL models.
arXiv:2610.17354v1 Announce Type: cross Abstract: Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, wh...
The paper presents a semi‑supervised biomedical image segmentation method that uses a diffusion‑based teacher–student framework. The teacher is pretrained via unsupervised diffusion reconstruction and then co‑trained with a student, leveraging supervised labels and cross pseudo‑supervision on unlabeled data. A multi‑round extension generates multiple stochastic reconstructions to further refine pseudo‑labels, achieving competitive or superior results on several 2D and 3D biomedical datasets, especially when labels are scarce.