scholarly journals StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

2019 ◽  
Vol 41 (8) ◽  
pp. 1947-1962 ◽  
Author(s):  
Han Zhang ◽  
Tao Xu ◽  
Hongsheng Li ◽  
Shaoting Zhang ◽  
Xiaogang Wang ◽  
...  
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Realistic Image

scholarly journals mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis

2021 ◽  
pp. 101944
Author(s):  
Mahmut Yurt ◽  
Salman U.H. Dar ◽  
Aykut Erdem ◽  
Erkut Erdem ◽  
Kader K Oguz ◽  
...  
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Mr Image ◽  
Adversarial Networks

scholarly journals A Realistic Image Generation of Face From Text Description Using the Fully Trained Generative Adversarial Networks

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 1250-1260
Author(s):  
Muhammad Zeeshan Khan ◽  
Saira Jabeen ◽  
Muhammad Usman Ghani Khan ◽  
Tanzila Saba ◽  
Asim Rehmat ◽  
...  
Keyword(s):  
Generative Adversarial Networks ◽  
Image Generation ◽  
Adversarial Networks ◽  
Realistic Image

scholarly journals Breast Ultrasound Image Synthesis using Deep Convolutional Generative Adversarial Networks

Diagnostics ◽  
2019 ◽  
Vol 9 (4) ◽  
pp. 176 ◽  
Author(s):  
Tomoyuki Fujioka ◽  
Mio Mori ◽  
Kazunori Kubota ◽  
Yuka Kikuchi ◽  
Leona Katsuta ◽  
...  
Keyword(s):  
Ultrasound Image ◽  
Image Synthesis ◽  
Breast Ultrasound ◽  
Generative Adversarial Networks ◽  
Ultrasound Images ◽  
Clinical Value ◽  
Adversarial Networks ◽  
Significant Difference ◽  
Definition Of ◽  
The Masses

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.

Sign in / Sign up

Export Citation Format

Share Document