Multi-path deep learning model for automated mammographic density categorization

Xiangyuan Ma; Caleb Fisher; Jun Wei; Mark A. Helvie; Heang-Ping Chan; Chuan Zhou; Lubomir Hadjiiski; Yao Lu

doi:10.1117/12.2511544

13 March 2019 Multi-path deep learning model for automated mammographic density categorization

Xiangyuan Ma, Caleb Fisher, Jun Wei, Mark A. Helvie, Heang-Ping Chan, Chuan Zhou, Lubomir Hadjiiski, Yao Lu

Author Affiliations +

Proceedings Volume 10950, Medical Imaging 2019: Computer-Aided Diagnosis; 109502E (2019) https://doi.org/10.1117/12.2511544
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

Breast density is one of the strongest risk factors for breast cancer. Our purpose of this study is to develop a deep learning model for BI-RADS density classification on digital mammograms (DM). With IRB approval, 2581 DMs were retrospectively collected from 672 women in our institution. We designed a multi-path DCNN (MP-DCNN) to classify each DM into one of four BI-RADS density categories. The MP-DCNN has four inputs: (1) subsampled DM (800 μm pixel spacing), (2) a mask of dense area (MDA) obtained with a U-net (800 μm pixel spacing), (3) the largest square region of interest (ROI) within mammographic breast (100 μm pixel spacing), and (4) automated percentage of breast density (PD). As the baseline statistic, a single path DCNN with subsampled DM (800 um pixel spacing) as input was used. An experienced Mammography Quality Standards Act (MQSA) radiologist provided BI-RADS density category and PD by interactive thresholding as the reference standards. With ten-fold cross-validation, the BI-RADS categories by MP-DCNN for 2068 of the 2581 cases agreed with radiologist’s assessment (accuracy = 80.7%, weighted kappa = 0.83) and the accuracy reached 89.0% if the breasts were categorized as non-dense (BI-RADS A & B) and dense (BIRADS C & D). For comparison, a single path DCNN as the baseline model obtained agreement in 1906 of the 2581 cases (accuracy = 73.8%, weighted kappa = 0.75). The improvement in BI-RADS classification from the baseline to the MP-DCNN was statistically significant (p<0.001).

Citation Download Citation

Xiangyuan Ma, Caleb Fisher, Jun Wei, Mark A. Helvie, Heang-Ping Chan, Chuan Zhou, Lubomir Hadjiiski, and Yao Lu "Multi-path deep learning model for automated mammographic density categorization", Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 109502E (13 March 2019); https://doi.org/10.1117/12.2511544

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