Multi-space-enabled deep learning of breast tumors improves prediction of distant recurrence risk

Dooman Arefan; Bingjie Zheng; David J. Dabbs; Rohit Bhargava; Shandong Wu

doi:10.1117/12.2513013

15 March 2019 Multi-space-enabled deep learning of breast tumors improves prediction of distant recurrence risk

Dooman Arefan, Bingjie Zheng, David J. Dabbs, Rohit Bhargava, Shandong Wu

Proceedings Volume 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications; 109540L (2019) https://doi.org/10.1117/12.2513013
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

In this study, we proposed a multi-space-enabled deep learning modeling method for predicting Oncotype DX recurrence risk categories from digital mammogram images on breast cancer patients. Our study included 189 estrogen receptor-positive (ER+) and node-negative invasive breast cancer patients, who all have Oncotype DX recurrence risk score available. Breast tumors were segmented manually by an expert radiologist. We built a 3- channel convolutional neural network (CNN) model that accepts three-space tumor data: the spatial intensity information and the phase and amplitude components in the frequency domain. We compared this multi-space model to a baseline model that is based on sorely the intensity information. Classification accuracy is based on 5- fold cross-validation and average area-under the receiver operating characteristics curve (AUC). Our results showed that the 3-channel multi-space CNN model achieved a statistically significant improvement than the baseline model.

Citation Download Citation

Dooman Arefan, Bingjie Zheng, David J. Dabbs, Rohit Bhargava, and Shandong Wu "Multi-space-enabled deep learning of breast tumors improves prediction of distant recurrence risk", Proc. SPIE 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 109540L (15 March 2019); https://doi.org/10.1117/12.2513013

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