Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis

Xueguang Li; Mingyue Du; Shanru Zuo; Mingqing Zhou; Qiyao Peng; Ziyao Chen; Junhua Zhou; Quanyuan He

doi:10.3389/fbinf.2023.1101667

Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis

Front Bioinform. 2023 Mar 9:3:1101667. doi: 10.3389/fbinf.2023.1101667. eCollection 2023.

Authors

Xueguang Li¹, Mingyue Du¹, Shanru Zuo¹, Mingqing Zhou¹, Qiyao Peng¹, Ziyao Chen¹, Junhua Zhou¹, Quanyuan He¹

Affiliation

¹ The Key Laboratory of Model Animals and Stem Cell Biology in Hunan Province, School of Medicine, Hunan Normal University, Changsha, Hunan, China.

Abstract

Cervical cancer (CC) is the fourth most common malignant tumor among women worldwide. Constructing a high-accuracy deep convolutional neural network (DCNN) for cervical cancer screening and diagnosis is important for the successful prevention of cervical cancer. In this work, we proposed a robust DCNN for cervical cancer screening using whole-slide images (WSI) of ThinPrep cytologic test (TCT) slides from 211 cervical cancer and 189 normal patients. We used an active learning strategy to improve the efficiency and accuracy of image labeling. The sensitivity, specificity, and accuracy of the best model were 96.21%, 98.95%, and 97.5% for CC patient identification respectively. Our results also demonstrated that the active learning strategy was superior to the traditional supervised learning strategy in cost reduction and improvement of image labeling quality. The related data and source code are freely available at https://github.com/hqyone/cancer_rcnn.

Keywords: CNN; active learning strategy; cervical cancer; deep learning; whole slide image.

Grants and funding

This work was supported by the High-Level Talent Program in Hunan Province (2019RS1035), the Major Scientific and Technological Project for Collaborative Prevention and Control of Birth Defect in Hunan Province (2019SK1012), and the National Natural Science Foundation of China (31771445).