Deep learning approach to classification of lung cytological images: Two-step training using actual and synthesized images by progressive growing of generative adversarial networks

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.

WITHDRAWN: Advanced machine learning-based analytics on COVID-19 data using generative adversarial networks

“…Magnetic resonance imaging (MRI) doesn't add radiation to light. The reinforcement learning strategy was used to iterative methods the nonlinear relationship between MRI and CT, and to produce more realistic images [11] , [25] . The Medical Images (MI-GAN) emits synthetic medical images and their based segmentation masks which could be used to apply structured medical imaging analysis [26] .…”

WITHDRAWN: Few-shot Learning on the Diagnosis of Lymphatic Metastasis of Lung Carcinoma

“…The accuracy of the weakly supervised deep learning may be affected by the labels [9] and the size of the dataset which could be improved by upgrading the algorithm iteration [11][12][13]. Atsushi Teramoto improves 4% AUC by using a two-step supervised strategy for the classification of lung cytological images with 60 cases dataset [14]. However, to further enhance the performance of the AI model, it would be necessary to increase the number of images used to train the CNN model.…”

Automated Sewer Defects Detection Using Style-Based Generative Adversarial Networks and Fine-Tuned Well-Known CNN Classifier

“…Since the advent of GANs [24], a number of variations and progressions have emerged, such as the DCGAN (Deep Convolutional GAN) [25,26], PGGAN (Progressive Growing of GAN) [27] and its variants [28,29], BigGAN [30] and StyleGAN (a style-based GAN) [21]. Among the techniques, the DCGAN managed to stabilize the model training process with a CNN setting, but the generated images have relatively low accuracies.…”