Newest papers

Learning to Reason Like a Cytopathologist:Clinically Grounded Multiscale Evidential Learning for Cervical Cytology

AJEET KUMAR SINGH, Neha Mishra, Anurag Tripathi, Santanu Chaudhury, Dorien Herremans · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29665 · cited by 0 works (OpenAlex) · open-access PDF

French

La cytologie du col de l'utérus présente un paysage de diagnostic fondamentalement ambigu, où les catégories de cadres équivoques telles que les cellules squameuses atypiques de signification indéterminée (ASC-US) occupent une zone grise morphologique fortement défini. Pour le soutien aux décisions cliniques, l'objectif s'étend au-delà de l'attribution d'un label définitif à chaque échantillon: les cas doivent également être distingués par le fait que les preuves disponibles soutiennent une décision confiante ou justifient une considération plus approfondie, un modèle de classification classification conventionnelle de distinction n'est pas conçu pour représenter explicitement. Nous proposons un cadre de preuve multiscale qui modèle la cytologie du col de l

Machine translation (Meta M2M100); the English original follows.

Abstract

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 zone that is definitional. For clinical decision support, the goal extends beyond assigning a definitive label to every sample: cases must also be distinguished by whether the available evidence supports a confident decision or warrants further consideration, a distinction conventional classification models are not designed to explicitly represent. We propose a multiscale evidential framework that models cervical cytology along an ordinal disease continuum using clinically grounded soft anchors, representing progression from benign reactive changes to precancerous lesions and malignancy. Three biologically motivated spatial contexts--nuclear morphology, cytoplasmic characteristics, and neighbourhood cellular architecture--are independently encoded using a shared frozen DINOv2 backbone, preserving inter-scale disagreement that early fusion may obscure. Calibrated predictions are transformed into Dempster--Shafer belief masses and fused with reliability discounting, allowing conflicting evidence and insufficient support to remain explicitly uncommitted rather than forcing a decision. The fused belief state drives interpretable routing that separates confidently classified cases from those with irreducible evidential insufficiency, enabling clinically meaningful triage. Across two independent publicly available conventional cytology datasets, RIVA and CRIC Cervix, the framework generalises consistently, with uncertainty strongly associated with diagnostic difficulty: incorrect predictions carry 1.94x-4.13x higher uncertainty than correct ones.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Evidential reasoning approach, Artificial intelligence, Psychology, Cytology, Pairwise comparison, Natural language processing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange