Quality analysis of DCGAN-generated mammography lesions

Basel Alyafi; Oliver Diaz; Premkumar Elangovan; Joan C. Vilanova; Javier del Riego; Robert Marti

doi:10.1117/12.2560473

22 May 2020 Quality analysis of DCGAN-generated mammography lesions

Basel Alyafi, Oliver Diaz, Premkumar Elangovan, Joan C. Vilanova, Javier del Riego, Robert Marti

Proceedings Volume 11513, 15th International Workshop on Breast Imaging (IWBI2020); 115130B (2020) https://doi.org/10.1117/12.2560473
Event: Fifteenth International Workshop on Breast Imaging, 2020, Leuven, Belgium

Abstract

Medical image synthesis has gained a great focus recently, especially after the introduction of Generative Adversarial Networks (GANs). GANs have been used widely to provide anatomically-plausible and diverse samples for augmentation and other applications, including segmentation and super resolution. In our previous work, Deep Convolutional GANs were used to generate synthetic mammogram lesions, masses mainly, that could enhance the classification performance in imbalanced datasets. In this new work, a deeper investigation was carried out to explore other aspects of the generated images evaluation, i.e., realism, feature space distribution, and observer studies. t-Stochastic Neighbor Embedding (t-SNE) was used to reduce the dimensionality of real and fake images to enable 2D visualisations. Additionally, two expert radiologists performed a realism-evaluation study. Visualisations showed that the generated images have a similar feature distribution of the real ones, avoiding outliers. Moreover, the Receiver Operating Characteristic (ROC) study showed that the radiologists could not, in many cases, distinguish between synthetic and real lesions, giving accuracies between 51% and 59% using a balanced sample set.

Citation Download Citation

Basel Alyafi, Oliver Diaz, Premkumar Elangovan, Joan C. Vilanova, Javier del Riego, and Robert Marti "Quality analysis of DCGAN-generated mammography lesions", Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115130B (22 May 2020); https://doi.org/10.1117/12.2560473

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available