Ryo Toda1, Atsushi Teramoto2, Masakazu Tsujimoto3, Hiroshi Toyama4, Kazuyoshi Imaizumi4, Kuniaki Saito1, Hiroshi Fujita5. 1. Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. 2. Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. teramoto@fujita-hu.ac.jp. 3. Fujita Health University Hospital, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. 4. School of Medicine, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. 5. Faculty of Engineering, Gifu University, 1-1 Yanagido, Gifu City, 510-1193, Japan.
Abstract
PURPOSE: In recent years, convolutional neural network (CNN), an artificial intelligence technology with superior image recognition, has become increasingly popular and frequently used for classification tasks in medical imaging. However, the amount of labelled data available for classifying medical images is often significantly less than that of natural images, and the handling of rare diseases is often challenging. To overcome these problems, data augmentation has been performed using generative adversarial networks (GANs). However, conventional GAN cannot effectively handle the various shapes of tumours because it randomly generates images. In this study, we introduced semi-conditional InfoGAN, which enables some labels to be added to InfoGAN, for the generation of shape-controlled tumour images. InfoGAN is a derived model of GAN, and it can represent object features in images without any label. METHODS: Chest computed tomography images of 66 patients diagnosed with three histological types of lung cancer (adenocarcinoma, squamous cell carcinoma, and small cell lung cancer) were used for analysis. To investigate the applicability of the generated images, we classified the histological types of lung cancer using a CNN that was pre-trained with the generated images. RESULTS: As a result of the training, InfoGAN was possible to generate images that controlled the diameters of each lesion and the presence or absence of the chest wall. The classification accuracy of the pre-trained CNN was 57.7%, which was higher than that of the CNN trained only with real images (34.2%), thereby suggesting the potential of image generation. CONCLUSION: The applicability of semi-conditional InfoGAN for feature learning and representation in medical images was demonstrated in this study. InfoGAN can perform constant feature learning and generate images with a variety of shapes using a small dataset.
PURPOSE: In recent years, convolutional neural network (CNN), an artificial intelligence technology with superior image recognition, has become increasingly popular and frequently used for classification tasks in medical imaging. However, the amount of labelled data available for classifying medical images is often significantly less than that of natural images, and the handling of rare diseases is often challenging. To overcome these problems, data augmentation has been performed using generative adversarial networks (GANs). However, conventional GAN cannot effectively handle the various shapes of tumours because it randomly generates images. In this study, we introduced semi-conditional InfoGAN, which enables some labels to be added to InfoGAN, for the generation of shape-controlled tumour images. InfoGAN is a derived model of GAN, and it can represent object features in images without any label. METHODS: Chest computed tomography images of 66 patients diagnosed with three histological types of lung cancer (adenocarcinoma, squamous cell carcinoma, and small cell lung cancer) were used for analysis. To investigate the applicability of the generated images, we classified the histological types of lung cancer using a CNN that was pre-trained with the generated images. RESULTS: As a result of the training, InfoGAN was possible to generate images that controlled the diameters of each lesion and the presence or absence of the chest wall. The classification accuracy of the pre-trained CNN was 57.7%, which was higher than that of the CNN trained only with real images (34.2%), thereby suggesting the potential of image generation. CONCLUSION: The applicability of semi-conditional InfoGAN for feature learning and representation in medical images was demonstrated in this study. InfoGAN can perform constant feature learning and generate images with a variety of shapes using a small dataset.
Entities:
Keywords:
CNN; CT imaging; Classification; GAN; Image synthesis; Lung cancer