Abstract
Cytology is the first pathological examination performed in the diagnosis of lung cancer. In our previous study, we introduced a deep convolutional neural network (DCNN) to automatically classify cytological images as images with benign or malignant features and achieved an accuracy of 81.0%. To further improve the DCNN’s performance, it is necessary to train the network using more images. However, it is difficult to acquire cell images which contain a various cytological features with the use of many manual operations with a microscope. Therefore, in this study, we aim to improve the classification accuracy of a DCNN with the use of actual and synthesized cytological images with a generative adversarial network (GAN). Based on the proposed method, patch images were obtained from a microscopy image. Accordingly, these generated many additional similar images using a GAN. In this study, we introduce progressive growing of GANs (PGGAN), which enables the generation of high-resolution images. The use of these images allowed us to pretrain a DCNN. The DCNN was then fine-tuned using actual patch images. To confirm the effectiveness of the proposed method, we first evaluated the quality of the images which were generated by PGGAN and by a conventional deep convolutional GAN. We then evaluated the classification performance of benign and malignant cells, and confirmed that the generated images had characteristics similar to those of the actual images. Accordingly, we determined that the overall classification accuracy of lung cells was 85.3% which was improved by approximately 4.3% compared to a previously conducted study without pretraining using GAN-generated images. Based on these results, we confirmed that our proposed method will be effective for the classification of cytological images in cases at which only limited data are acquired.
Highlights
Lung cancer is the leading cause of death among men worldwide [1]
To confirm the effectiveness of progressive growing of GANs (PGGAN), we compared the quality of images generated by PGGAN and by Deep convolutional generative adversarial networks (DCGANs), which is a conventional method that has no progressive structure
The pretraining of VGG-16 using the PGGAN-generated images and the classification performance of the deep convolutional neural network (DCNN) fine-tuned by actual images were evaluated
Summary
According to the pathological examinations performed to provide detailed lung cancer diagnoses, it has become possible to identify tissue types and subtypes via immunostaining and genetic examinations [2]. Based on these tests, patients may undergo surgery, radiation therapy, drug therapy, or a combination of these treatments. In the pathology-based diagnosis of lung cancer, cytology is first performed using cells biopsied during a bronchoscopy [4], and comprehensive diagnostic results are obtained from histological examinations. The detection of abnormal cells from many cell images is a very difficult task. If the identification can be supported using image analyses or artificial intelligence technologies [5,6,7,8,9,10], diagnostic accuracy could be improved
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
