Next Article in Journal
A Proteomic Study of Atherosclerotic Plaques in Men with Coronary Atherosclerosis
Previous Article in Journal
Estimating the Spatial Accessibility to Blood Group and Rhesus Type Point-of-Care Testing for Maternal Healthcare in Ghana
Previous Article in Special Issue
Breast Cancer Diagnosis Using an Efficient CAD System Based on Multiple Classifiers
Open AccessArticle

Breast Ultrasound Image Synthesis using Deep Convolutional Generative Adversarial Networks

1
Department of Diagnostic Radiology, Tokyo Medical and Dental University Hospital 1-5-45, Yushima, Bunkyo-ku, Tokyo 113-8501, Japan
2
Department of Radiology, Dokkyo Medical University Hospital, 880 Kitakobayashi, Mibu, Shimotsugagun, Tochigi 321-0293, Japan
3
Department of Surgery, Breast Surgery, Tokyo Medical and Dental University Hospital 1-5-45, Yushima, Bunkyo-ku, Tokyo 113-8501, Japan
*
Author to whom correspondence should be addressed.
Diagnostics 2019, 9(4), 176; https://doi.org/10.3390/diagnostics9040176
Received: 9 October 2019 / Revised: 30 October 2019 / Accepted: 5 November 2019 / Published: 6 November 2019
(This article belongs to the Special Issue Multimodality Breast Imaging)
Deep convolutional generative adversarial networks (DCGANs) are newly developed tools for generating synthesized images. To determine the clinical utility of synthesized images, we generated breast ultrasound images and assessed their quality and clinical value. After retrospectively collecting 528 images of 144 benign masses and 529 images of 216 malignant masses in the breasts, synthesized images were generated using a DCGAN with 50, 100, 200, 500, and 1000 epochs. The synthesized (n = 20) and original (n = 40) images were evaluated by two radiologists, who scored them for overall quality, definition of anatomic structures, and visualization of the masses on a five-point scale. They also scored the possibility of images being original. Although there was no significant difference between the images synthesized with 1000 and 500 epochs, the latter were evaluated as being of higher quality than all other images. Moreover, 2.5%, 0%, 12.5%, 37.5%, and 22.5% of the images synthesized with 50, 100, 200, 500, and 1000 epochs, respectively, and 14% of the original images were indistinguishable from one another. Interobserver agreement was very good (|r| = 0.708–0.825, p < 0.001). Therefore, DCGAN can generate high-quality and realistic synthesized breast ultrasound images that are indistinguishable from the original images. View Full-Text
Keywords: breast imaging; ultrasound; deep learning; convolutional neural network; generative adversarial networks; artificial intelligence breast imaging; ultrasound; deep learning; convolutional neural network; generative adversarial networks; artificial intelligence
Show Figures

Figure 1

MDPI and ACS Style

Fujioka, T.; Mori, M.; Kubota, K.; Kikuchi, Y.; Katsuta, L.; Adachi, M.; Oda, G.; Nakagawa, T.; Kitazume, Y.; Tateishi, U. Breast Ultrasound Image Synthesis using Deep Convolutional Generative Adversarial Networks. Diagnostics 2019, 9, 176.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop