Generative adversarial network-based image completion to identify abnormal locations in digital breast tomosynthesis images

Albert Swiecicki; Mateusz Buda; Ashirbani Saha; Nianyi Li; Sujata V. Ghate; Ruth Walsh; Maciej A. Mazurowski

doi:10.1117/12.2551379

16 March 2020 Generative adversarial network-based image completion to identify abnormal locations in digital breast tomosynthesis images

Albert Swiecicki, Mateusz Buda, Ashirbani Saha, Nianyi Li, Sujata V. Ghate, Ruth Walsh, Maciej A. Mazurowski

Author Affiliations +

Proceedings Volume 11314, Medical Imaging 2020: Computer-Aided Diagnosis; 1131428 (2020) https://doi.org/10.1117/12.2551379
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

Deep learning has achieved great success in image analysis and decision making in radiology. However, a large amount of annotated imaging data is needed to construct well-performing deep learning models. A particular challenge in the context of breast cancer is the number of available cases that contain cancer, given the very low prevalence of the disease in the screening population. The question arises whether normal cases, which in the context of breast cancer screening are available in abundance, can be used to train a deep learning model that identifies locations that are abnormal. In this study, we propose to achieve this goal through the generative adversarial network (GAN)-based image completion. Our hypothesis is that if a generative network has a difficulty to correctly complete a part of an image at a certain location, then such a location is likely to represent an abnormality. We test this hypothesis using a dataset of 4348 patients with digital breast tomosynthesis (DBT) imaging from our institution. We trained our model on normal only images, to be able to fill in parts of images that were artificially removed. Then, using an independent test set, at different locations in the images, we measured how difficult it was for the network to reconstruct an artificially removed patch of the image. The difficulty was measured by mean squared error (MSE) between the original removed patch and the reconstructed patch. On average, the MSE was 2.11 times higher (with standard deviation equal to 1.01) at the locations containing expert-annotated cancerous lesions than that at the locations outside those abnormal locations. Our generative approach demonstrates a great potential for using this model to aid breast cancer detection.

Citation Download Citation

Albert Swiecicki, Mateusz Buda, Ashirbani Saha, Nianyi Li, Sujata V. Ghate, Ruth Walsh, and Maciej A. Mazurowski "Generative adversarial network-based image completion to identify abnormal locations in digital breast tomosynthesis images", Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 1131428 (16 March 2020); https://doi.org/10.1117/12.2551379

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