The paper introduces a multiscale evidential learning framework for cervical cytology that models disease progression along an ordinal continuum using clinically grounded soft anchors. It encodes nuclear, cytoplasmic, and neighborhood cellular features separately with a shared DINOv2 backbone, then transforms calibrated predictions into Dempster–Shafer belief masses, fusing them with reliability discounting to explicitly handle conflicting or insufficient evidence. The resulting belief state enables interpretable routing that distinguishes confidently classified cases from those requiring further review, and demonstrates consistent generalization across two public cytology datasets with uncertainty correlating strongly with diagnostic difficulty.
Cervical cytology presents a fundamentally ambiguous diagnostic landscape, where equivocal categories such as Atypical Squamous Cells of Undetermined Significance (ASC-US) occupy a morphological grey...
arXiv:2606. 06224v1 Announce Type: cross Abstract: Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology.
arXiv:2609.09189v1 Announce Type: cross Abstract: High classification accuracy alone is insufficient for clinical image analysis, where calibrated confidence and reliable uncertainty estimates are es...
arXiv:2609.17545v1 Announce Type: new Abstract: Deep learning models for cervical cytology are almost always evaluated as if every prediction must be acted upon, yet a screening system deployed along...
arXiv:2609.31314v1 Announce Type: new Abstract: Cytopathology detection requires open-vocabulary recognition because cellular categories are fine-grained, long-tailed, and continuously evolving acros...
TAM-Chain is a multi‑scale thyroid cytology classification framework that uses Absorbing Markov Chains and Shannon Entropy to quantify uncertainty and dynamically decide when to stop processing and refer to a specialist. It processes images at 10×, 20×, and 40× magnifications, achieving a Macro F1 score of 0.9741 on an internal test set with a 0 % false‑negative rate, and maintains a Macro F1 of 0.7026 on an external validation set with severe domain shift. The method outperforms single‑magnification baselines by adaptively adjusting stopping steps and triggering specialist referrals, thereby reducing critical diagnostic errors.
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content. Such control is essential because clinical scenarios diverge: emergency triage prioritizes sensitivity to reduce missed findings, whereas confirmatory interpretation emphasizes specificity to limit unnecessary interventions.
The paper introduces CytoCRF, a conditional random field framework tailored for cytology images. It adapts pairwise terms to focus on chromatin and cytology-specific staining and enriches neighborhood information by combining multiple backbone models. Across ten cytology datasets, CytoCRF surpasses existing CRF methods at all annotation budgets, achieving up to +13.6 percentage points over the best baseline and +33.7 over zero‑shot performance with only 50 annotations.
arXiv:2605.07785v3 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final...
arXiv:2608. 10505v1 Announce Type: new Abstract: Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content.
arXiv:2511. 05150v2 Announce Type: replace-cross Abstract: Molecular biomarker testing in pathology is often costly and tissue-consuming, limiting scalable clinical deployment.
Spatial multi-omics technologies jointly profile gene expression, surface proteins, and histology at each tissue spot, yet most spatial domain discovery methods provide only cluster assignments, witho...