# Quantitative Texture Analysis of Cervical Cytology Identifies Endometrial Lesions in Atypical Glandular Cells on Liquid-Based Cytology: A Pilot Study

## TL;DR

This study shows that analyzing cell textures in cervical samples can help identify endometrial issues, especially after menopause, using machine learning.

## Contribution

The study introduces a machine learning approach to distinguish endometrial lesions in atypical glandular cells using quantitative cytology analysis.

## Key findings

- Machine learning models achieved AUCs of 0.805 (SurePath) and 0.887 (ThinPrep) in distinguishing endometrial lesions from normal cases.
- Performance improved post-menopause, with AUCs reaching up to 0.841 (SurePath) and 0.884 (ThinPrep).
- Platform-specific features influenced model performance, indicating differences in data from SurePath and ThinPrep preparations.

## Abstract

Background/Objectives: Within human papillomavirus (HPV)-based screening, cytology remains essential for cervical cancer detection while also potentially revealing endometrial pathology. This pilot study aimed to distinguish benign (normal) cases from atypical endometrial hyperplasia (AEH) and endometrial cancer (EC) within atypical glandular cell (AGC) cytology using quantitative analysis of liquid-based cervical cytology. Methods: SurePath and ThinPrep sets included 62 (37 normal, 25 AEH/EC) and 52 (24 normal, 28 AEH/EC) AGC cases, respectively. Semi-automatic QuPath analysis workflow detected cellular clusters; extracted texture, intensity, and geometric features; and produced case-level summaries. A random forest (RF) classifier was used to discriminate AEH/EC from normal cases. Feature subset selection was performed using a beam-search wrapper and joint hyperparameter tuning. Primary performance evaluation comprised stratified 5-fold cross-validation with metrics averaged across these folds. Results: Across both preparations, univariable analyses showed moderate discrimination overall which improved post-menopause. For SurePath and ThinPrep, the highest 10 areas under the curve (AUCs) were 0.701–0.773 (improving to 0.798–0.841 post-menopause) and 0.740–0.778 (improving to 0.832–0.884 post-menopause), respectively. Machine-learning RF models improved performance beyond univariable baselines. Cross-validated AUCs for SurePath and ThinPrep were 0.805 (95% confidence interval [CI], 0.683–0.927) and 0.887 (95% CI, 0.787–0.987), respectively. Features associated with higher AUCs differed between SurePath and ThinPrep, indicating platform-specific signals. Conclusions: Quantitative analysis of routine cervical cytology can augment expert reviews to help distinguish endometrial lesions among AGCs, particularly post-menopause. These software-based readouts can fit within existing workflows and may improve triage when morphology is subtle, including scenarios with HPV-negative screening results.