Enhanced Cellular Detection in Cervical Cytopathology: A Systematic Study of YOLO11 Training Paradigms
Open Access
- 2 May 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (9) , 4464
Abstract
Automated cellular detection using deep learning is a key strategy for optimising cervical cancer screening by reducing the healthcare workload and inter-observer variability. However, analysing Whole Slide Image (WSI) patches presents challenges such as annotation scarcity, morphological complexity, and class imbalance. This study systematically evaluates YOLO11-n, YOLO11-s, and YOLO11-m to assess the impact of target variable granularity and training paradigms on performance. Four strategies were analysed: independent and multi-class models, each evaluated at both the specific cell label and diagnostic macro-group levels. To ensure clinical robustness, patient-level data partitioning was implemented to prevent data leakage. Performance was measured using precision, recall, and mAP (0.5 and 0.5:0.95). The results reveal critical trade-offs between fine-grained discrimination and model generalisation when varying the architectural complexity and labelling strategies. The findings indicate that diagnostic aggregation improves stability, whereas single-class training optimises specialised detection. These results provide methodological guidelines for designing AI-assisted screening systems and may inform future extensions of WSI-level diagnostic pipelines.Keywords
All Related Versions
Funding Information
- Secretary of State for Digitalization and Artificial Intelligence
This publication has 17 references indexed in Scilit:
- Performance of artificial intelligence for diagnosing cervical intraepithelial neoplasia and cervical cancer: a systematic review and meta-analysiseClinicalMedicine, 2024
- Artificial intelligence in cytopathological applications for cancer: a review of accuracy and analytic validityEuropean Journal of Medical Research, 2024
- A systematic review of deep learning-based cervical cytology screening: from cell identification to whole slide image analysisArtificial Intelligence Review, 2023
- Electrocardiogram signal filtering using circulant singular spectrum analysis and cascaded Savitzky-Golay filterBiomedical Signal Processing and Control, 2022
- Data-efficient and weakly supervised computational pathology on whole-slide imagesNature Biomedical Engineering, 2021
- Clinical-grade computational pathology using weakly supervised deep learning on whole slide imagesNature Medicine, 2019
- Survey on deep learning with class imbalanceJournal of Big Data, 2019
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- Impact of variations in triage cytology interpretation on human papillomavirus–based cervical screening and implications for screening algorithmsEuropean Journal of Cancer, 2016
- Microsoft COCO: Common Objects in Context2014