28 Deep learning based cytology negative sample screening method. (18th September 2019)

• Record Type: Journal Article
• Authors: Konishi, T; Kolodziejczyk, J; Saito, K; Hayashi, H; Iwabuchi, T; Nakamura, R; Akagami, Y; Washiya, K; Abe, K; Nanjo, H
• Is Part Of: International journal of gynecological cancer. Volume 29(2019)Supplement 3
• Page Start: A17
• Page End: A17
• Publication Date: 2019-09-18
• Subjects: Generative organs, Female -- Cancer -- Periodicals; 616.99465
• DOI: 10.1136/ijgc-2019-IGCS.28
• Languages: English
• ISSNs: 1048-891X

Abstract

Abstract : Objectives: We show that deep learning can be used to create high accuracy cells classifiers that can support cytologists in their work. Two deep learning models are presented. The first model is used for cervical cancer cytology negative/positive prescreening and we show its high specificity at 100% Negative Predict Value (NPV). The second model is used to predict among 15 categories common to cervical analysis, as listed in figure 1(b) . Our classifiers include Grad-Cam visualizations that show both models concentrate on relevant areas of images. Methods: Classifiers are based on deep convolutional networks. The crucial aspects in achieving high accuracy are data augmentation and focal loss. Grad-Cam visualizations are used to explain models' reasoning. Results: Prescreening model, based on 2700 samples, achieves 95.89% overall accuracy and 91.62% specificity at 100% NPV (figure 1(a) ) ; second stage screening model, based on approximately 9500 samples, achieves 92.03% overall accuracy (figure 1(b) ). Grad-Cam visualizations show that both models concentrate on relevant areas of the image when making predictions (figure 1(c) ). Conclusions: We show that deep learning based classifiers can be useful in supporting cytologist in their work. Approximately 92% of samples that cytologist screen for cervical cancer are negative. With our model cytologists can concentrate their efforts on only positive samples and a small number of false positives predictions.