Original articles

Vol. 118: Issue 2 - April 2026

AI for cervical cancer screening on whole slide images: opportunities with open-source simple tools

Authors

Laura Nonnis , Lorenzo Putzu , Michela Vincis , Stefano Guerriero , Marco Palomba , Alessio Rocca , Daniela Fanni , Clara Gerosa , Marcello Trucas

Keywords: Uterine Cervical Neoplasms, Squamous Intraepithelial Lesions, Histological Techniques, Machine Learning, Computer-Assisted Diagnosis
DOI: 10.32074/1591-951X-1763
Publication Date: 2026-05-13

Summary

Objective. Cervical cancer remains a major global health burden, where early detection is critical. Cytological and histological assessments aim to identify precancerous squamous intraepithelial lesions (SILs). While artificial intelligence and machine learning have shown promise, most approaches rely on cytology or are not tailored for SIL classification. The aim of this study is to develop and evaluate a weakly supervised, pixel-level machine learning framework for the histological classification of low grade and high grade SIL in whole slide images (WSIs). Specifically, we sought to assess whether an open source segmentation pipeline trained on sparsely annotated WSIs could accurately support slide-level diagnostic interpretation while minimizing annotation burden and maintaining clinical interpretability.

Methods. We propose a weakly supervised machine learning framework for classifying low grade and high grade SILs in whole-slide histological images. Using Random Forest classifiers for pixel-level segmentation, the system mimics pathologists by quantifying tissue components. Training required only sparse annotations from a limited set of WSIs, yielding millions of pixel-level samples and reducing annotation burden.

Results. Applied on a test set of 309 cervical WSIs, the system achieved over 96% concordance with expert pathologists, correctly distinguishing low grade LSIL, high grade HSIL, and normal epithelium, with only one false negative and a 7-10 false positives, depending on the used model.

Conclusions. Our approach offers accurate, interpretable, and low-cost diagnostic support, with potential for integration into routine workflows, especially in resource-limited settings.

Downloads

PDF
Authors

Laura Nonnis - Department of Medical Sciences and Public Health, University of Cagliari, Unit of Anatomical Pathology, Cittadella Universitaria, 09042 Monserrato, Italy

Lorenzo Putzu - University of Cagliari

Michela Vincis - Department of Medical Sciences and Public Health, University of Cagliari, Unit of Anatomical Pathology, Cittadella Universitaria, 09042 Monserrato, Italy

Stefano Guerriero - Department of Maternal and Child Health, University of Cagliari, Integrated Center for Medically Assisted Reproduction (PMA) and Obstetric-Gynecological Diagnostics, Cittadella Universitaria, 09042 Monserrato, Italy

Marco Palomba - Department of Maternal and Child Health, University of Cagliari, Integrated Center for Medically Assisted Reproduction (PMA) and Obstetric-Gynecological Diagnostics, Cittadella Universitaria, 09042 Monserrato, Italy

Alessio Rocca - Department of Maternal and Child Health, University of Cagliari, Integrated Center for Medically Assisted Reproduction (PMA) and Obstetric-Gynecological Diagnostics, Cittadella Universitaria, 09042 Monserrato, Italy

Daniela Fanni - Department of Medical Sciences and Public Health, University of Cagliari, Unit of Anatomical Pathology, Cittadella Universitaria, 09042 Monserrato, Italy

Clara Gerosa - Department of Medical Sciences and Public Health, University of Cagliari, Unit of Anatomical Pathology, Cittadella Universitaria, 09042 Monserrato, Italy

Marcello Trucas - Department of Biomedical Sciences, University of Cagliari, Unit of Citomorphology, Cittadella Universitaria, 09042 Monserrato, Italy

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Copyright

Copyright (c) 2026 Società Italiana di Anatomia Patologica e Citopatologia Diagnostica, Divisione Italiana della International Academy of Pathology

How to Cite
Nonnis, L. ., Putzu, L., Vincis, M., Guerriero, S., Palomba, M., Rocca, A., Fanni, D., Gerosa, C., & Trucas, M. (2026). AI for cervical cancer screening on whole slide images: opportunities with open-source simple tools. Pathologica - Journal of the Italian Society of Anatomic Pathology and Diagnostic Cytopathology, 118(2). https://doi.org/10.32074/1591-951X-1763
  • Abstract viewed - 0 times
  • PDF downloaded - 0 times