Sampling error yields exclusively reactive, non-lesional brain parenchyma in a significant proportion of intracranial biopsies, leaving the underlying disease undiagnosed. We benchmark four pathology...
arXiv:2608. 05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume.
arXiv:2604. 27277v3 Announce Type: replace-cross Abstract: Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data.
arXiv:2607. 25497v2 Announce Type: replace-cross Abstract: Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines generalisation across institutions.
arXiv:2601. 20503v2 Announce Type: replace-cross Abstract: White matter hyperintensities (WMH) and ischaemic stroke lesions (ISL) are key imaging biomarkers of cerebral small vessel disease (SVD) detectable on magnetic resonance imaging (MRI).
arXiv:2607. 25497v1 Announce Type: cross Abstract: Pathology foundation models are approaching clinical deployment, yet remain vulnerable to systematic non-biological variation across centres.
The paper introduces CoPath, a lightweight framework for diagnosing peripheral neuroblastic tumors (pNTs) from whole-slide images. CoPath combines CoHisNet, a multi‑scale feature‑fusion network that replaces traditional MLPs with Kolmogorov‑Arnold Network layers for efficient nonlinear modeling, and PathVote, which aggregates patch‑level predictions using pathology‑informed priors. Experiments on a private pNT cohort and the public BreakHis dataset show that CoPath matches or surpasses existing classifiers while reducing computational complexity.
arXiv:2608. 06429v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior.
arXiv:2606. 00092v1 Announce Type: cross Abstract: Weakly-supervised classification of whole-slide images with attention-based multiple instance learning (ABMIL) on top of foundation features now reaches near-saturation on Camelyon16 slide-level performance, but the corresponding attention maps are an imperfect localization signal: in clinical interpretation, a model that classifies correctly without firing on the actual lesion is hard to trust.
The paper presents an optimal‑transport based generative model that learns the distributional differences between healthy and diseased patients, producing per‑patient counterfactuals and label‑free attribution heatmaps. On tabular breast cancer data the model achieves high malignancy scoring (AUROC ≈ 0.91) and its attributions correlate moderately with a supervised classifier, yet it does not surpass logistic regression. In chest X‑ray experiments the transport heatmaps capture population‑level signals but fail to localize real lesions, revealing a synthetic‑to‑real gap that challenges the reliability of label‑free explanations.
Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans.
arXiv:2606. 07590v1 Announce Type: cross Abstract: Pathology foundation models are pretrained on large streams of WSI-derived patches, while supervision during data construction is often slide-level, sparse, or heterogeneous.