Fernando C. Schmitt

Ongoing Challenges in Maintaining the Diagnostic Quality of Cervical Cytopathology: Is It Possible to Minimize Differences in Morphological Interpretations?

Background: The efficiency of the cytological test largely depends on the control and quality assurance of laboratory procedures, to avoid false results. The objectives of this descriptive review were to point out and discuss the main mechanisms for controlling and ensuring the quality of cytological diagnosis. Summary: A critical revision was performed to identify the principal challenges involved in the processes of all the main issues related to the morphological alterations that characterize a true-related lesion in the daily routine of the Pap test examination. Principles of QC and QA are already being implemented worldwide, and the positive aspects and limitations of these are discussed as well as proposing alternatives when pertinent. Most of the articles evaluated highlighted the necessity of implementing audit mechanisms to control the performance of the professionals involved with the cytology evaluation. Key Message: Promising data from the new image-based technological arsenal appear to be a remarkable tool for improving cytological evaluation, reducing errors of interpretation and serving as a powerful arm for cytology teaching.

Clinical-grade autonomous cytopathology through whole-slide edge tomography

Abstract Cytopathology, often abbreviated as cytology, has a central role in the early detection of cancer, such as cervical, lung and bladder cancers, owing to its speed, simplicity and minimally invasive nature 1–9 . However, its effectiveness is limited by variability in diagnostic accuracy stemming from subjective visual interpretation 10–21 . Although many artificial intelligence (AI)-powered systems have been proposed to improve consistency 22–26 , none have achieved fully autonomous, clinical-grade performance. Existing approaches serve as assistive tools and still rely on human oversight for interpretation and decision-making 22–26 . Here we present a clinical-grade autonomous cytopathology pipeline that combines high-resolution, real-time optical whole-slide tomography with edge computing to deliver end-to-end automation. The system achieves practical performance in imaging speed, quality and data volume, with localized data compression enabling streamlined storage and accelerated AI-driven analysis. In addition to supporting cell-level classification, the platform enables flow cytometry-like, population-wide morphological profiling for comprehensive interpretation of cellular distributions and patterns. A vision transformer achieved area under the receiver operating characteristic (ROC) curve (AUC) values exceeding 0.99 at the single-cell level for detecting low-grade squamous intraepithelial lesions (LSILs), high-grade squamous intraepithelial lesions (HSILs) and adenocarcinoma. In a multicentre evaluation of 1,124 cervical liquid-based cytology samples across four centres, the AI model achieved slide-level AUC values of 0.86–0.91 for LSIL + and 0.89–0.97 for HSIL + , with LSIL counts correlating strongly with human papillomavirus positivity and HSIL counts scaling with diagnostic severity. The system enables autonomous triage cytology, offering a foundation for routine, scalable and objective diagnostics.