Mathematical Modeling and Statistical Evaluation of Hybrid Deep Learning Architectures for Multiclass Classification of Cervical Cells in Digital Papanicolaou Images

Valles-Coral M.A.; Navarro-Cabrera J.R.; Pinedo L.; Cotrina-Linares J.; Sánchez-Flores J.; Arévalo-Ramirez H.; Arévalo-Fasanando L.; Reátegui-Lozano N.; Injante R. · Mathematics (2026) · DOI: 10.3390/math14071139

Resumen

Cervical cytology screening remains dependent on manual analysis, which is time-consuming and subject to variability. This study proposes a leakage-free hybrid deep learning framework for multiclass classification of cervical cells extracted from whole-slide Papanicolaou images. A fine-tuned DenseNet121 feature extractor was combined with three classifiers: Support Vector Machine (SVM), Stacked Extreme Learning Machine (SELM), and Cascaded Deep Forest (CDF). Experiments were conducted on the CRIC Cervix Collection dataset using slide-level data partitioning and group-aware stratified 7-fold cross-validation. Model comparison followed a paired non-parametric protocol (Friedman test with Wilcoxon post hoc and Holm correction). DenseNet121 + CDF achieved the highest cross-validation Accuracy (0.7370 ± 0.0357), significantly outperforming SVM (0.6644 ± 0.0287) and SELM (0.6431 ± 0.0471) (χ2(2) = 11.14, p = 0.0038; Kendall’s W = 0.79). Independent testing showed competitive generalization across models. These results support the statistical robustness of the Cascaded Deep Forest-based hybrid architecture for multiclass cervical cytology classification under realistic slide-level conditions.

Instituciones: Universidad Nacional de San Martín; Universidad Privada Norbert Wiener