Self-Supervised Learning-Based Cervical Cytology Diagnostics in Low-Data Regime and Low-Resource Setting
Lists
Only you see this
Abstract
Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality. However, the lack of trained cytopathologists hinders its widespread implementation in low-resource settings. Deep learning-based telecytology diagnosis emerges as an appealing alternative, but it requires the collection of large annotated training datasets, which is costly and time-consuming. In this paper, we demonstrate that the abundance of unlabeled images that can be extracted from Pap smear test whole slide images presents a fertile ground for self-supervised learning methods, yielding performance improvements relative to readily available pre-trained models for various downstream tasks. In particular, we propose \textbf{C}ervical \textbf{C}ell \textbf{C}opy-\textbf{P}asting ($\texttt{C}^{3}\texttt{P}$) as an effective augmentation method, which enables knowledge transfer from open-source and labeled single-cell datasets to unlabeled tiles. Not only does $\texttt{C}^{3}\texttt{P}$ outperforms naive transfer from single-cell images, but we also demonstrate its advantageous integration into multiple instance learning methods. Importantly, all our experiments are conducted on our introduced \textit{in-house} dataset comprising liquid-based cytology Pap smear images obtained using low-cost technologies. This aligns with our objective of leveraging deep learning-based telecytology for diagnosis in low-resource settings.
BibTeX
@article{stegmuller2024self,
author = {Thomas Stegmüller and Christian Abbet and Behzad Bozorgtabar and Holly Clarke and Patrick Petignat and Pierre Vassilakos and Jean-Philippe Thiran},
title = {{Self-Supervised Learning-Based Cervical Cytology Diagnostics in Low-Data Regime and Low-Resource Setting}},
journal = {Computers in Biology and Medicine},
year = {2024},
doi = {10.1016/j.compbiomed.2023.107809},
}