The Impact of Cervical Cytology Category Imbalance on Self-Supervised Representation Learning

Read full text Summarise with VIRAT
Authors: Shijie Liu, Xuben Chang, Jiaxin Bai, Li Chen, Shaoqun Zeng, Tingwei Quan, Xiuli Liu, Shenghua Cheng
Cited by: 0
References: 35

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The method of pre-training on extensive unlabeled data, followed by transferring the learned representations to downstream tasks with limited labeled data, has been effective in various fields. However, this paradigm faces the challenge of extreme data imbalance in cervical cytology, with positive cells in whole-slide images constituting approximately 1%. In this paper, we propose a pipeline for investigating the impact of this extreme category imbalance on self-supervised representation learning (SSRL). The pipeline consists of 2 stages: SSRL and downstream tasks. In the SSRL stage, we employ 2 well-established methods, masked autoencoders and the simple framework for contrastive learning, across 9 datasets with varying degrees of imbalance. The pre-trained representations are then transferred to downstream tasks by employing both linear probing and fine-tuning techniques. Additionally, we examine the effect of SSRL on annotation efficiency by varying the quantities of annotation (annotation budget). Our investigation leverages a total of 168,000 image tiles derived from 1,320 whole-slide images obtained from multiple centers. Our findings indicate a noticeable decline in accuracy (Acc) within downstream tasks as data balance shifts from 1:1 to 1:100, with a maximum drop of about 4%. This highlights the substantial impact of data imbalance on SSRL, particularly evident in downstream tasks with lower annotation rates, such as at a 1% budget. Furthermore, the downstream tasks demonstrate the potential to achieve accuracy comparable to those of scenarios with a high annotation budget (50%), even when utilizing a limited annotation budget (5%). The code is available at https://github.com/LGBluesky/ICISSRL.

Fields of Study & Subjects

AI in cancer detection Domain Adaptation and Few-Shot Learning Cell Image Analysis Techniques

Publication details

Journal / source
Computational and Structural Biotechnology Journal
Volume
35
Issue
1
Pages
0048–0048
Publication date
1 March 2026
Language
EN