Attribute-guided image generation of three-dimensional computed tomography images of lung nodules using a generative adversarial network. (November 2020)

• Record Type: Journal Article
• Authors: Nishio, Mizuho; Muramatsu, Chisako; Noguchi, Shunjiro; Nakai, Hirotsugu; Fujimoto, Koji; Sakamoto, Ryo; Fujita, Hiroshi
• Is Part Of: Computers in biology and medicine. Volume 126(2020)
• Publication Date: 2020-11
• Subjects: Computed tomography -- Deep learning -- Generative adversarial network -- Lung nodule -- Image generation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104032
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Purpose: To develop and evaluate a three-dimensional (3D) generative model of computed tomography (CT) images of lung nodules using a generative adversarial network (GAN). To guide the GAN, lung nodule size was used. Materials and methods: A public CT dataset of lung nodules was used, from where 1182 lung nodules were obtained. Our proposed GAN model used masked 3D CT images and nodule size information to generate images. To evaluate the generated CT images, two radiologists visually evaluated whether the CT images with lung nodule were true or generated, and the diagnostic ability was evaluated using receiver-operating characteristic analysis and area under the curves (AUC). Then, two models for classifying nodule size into five categories were trained, one using the true and the other using the generated CT images of lung nodules. Using true CT images, the classification accuracy of the sizes of the true lung nodules was calculated for the two classification models. Results: The sensitivity, specificity, and AUC of the two radiologists were respectively as follows: radiologist 1: 81.3%, 37.7%, and 0.592; radiologist 2: 77.1%, 30.2%, and 0.597. For categorization of nodule size, the mean accuracy of the classification model constructed with true CT images was 85% (range 83.2–86.1%), and that with generated CT images was 85% (range 82.2–88.1%). Conclusions: Our results show that it was possible to generate 3D CT images of lung nodules that could be used to construct a classification model of lung nodule size without true CT images. Highlights: A generative adversarial network (GAN) was trained for 3D CT lung nodule images. To guide the GAN, lung nodule size was used. The images generated by GAN were difficult to distinguish from true images. Using the generated images, a classification model of lung nodule size was built.