Abstract
BackgroundTo determine if mammographic features from deep learning networks can be applied in breast cancer to identify groups at interval invasive cancer risk due to masking beyond using traditional breast density measures.MethodsFull-field digital screening mammograms acquired in our clinics between 2006 and 2015 were reviewed. Transfer learning of a deep learning network with weights initialized from ImageNet was performed to classify mammograms that were followed by an invasive interval or screen-detected cancer within 12 months of the mammogram. Hyperparameter optimization was performed and the network was visualized through saliency maps. Prediction loss and accuracy were calculated using this deep learning network. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were generated with the outcome of interval cancer using the deep learning network and compared to predictions from conditional logistic regression with errors quantified through contingency tables.ResultsPre-cancer mammograms of 182 interval and 173 screen-detected cancers were split into training/test cases at an 80/20 ratio. Using Breast Imaging-Reporting and Data System (BI-RADS) density alone, the ability to correctly classify interval cancers was moderate (AUC = 0.65). The optimized deep learning model achieved an AUC of 0.82. Contingency table analysis showed the network was correctly classifying 75.2% of the mammograms and that incorrect classifications were slightly more common for the interval cancer mammograms. Saliency maps of each cancer case found that local information could highly drive classification of cases more than global image information.ConclusionsPre-cancerous mammograms contain imaging information beyond breast density that can be identified with deep learning networks to predict the probability of breast cancer detection.
Highlights
To determine if mammographic features from deep learning networks can be applied in breast cancer to identify groups at interval invasive cancer risk due to masking beyond using traditional breast density measures
The purpose of this study was to implement a deep learning network to investigate if unique imaging characteristics exist beyond breast density, to classify precancerous mammograms that later result in either an interval or screen-detected invasive cancer within 12 months of the mammogram
Participants Participants were selected from a screening population that had received full-field digital mammograms acquired from 2006 to 2015 from four radiology facilities, University of California – San Francisco, California Pacific Medical Center, Marin General Hospital, and Novato Community Hospital that participate in the San Francisco Mammography Registry
Summary
To determine if mammographic features from deep learning networks can be applied in breast cancer to identify groups at interval invasive cancer risk due to masking beyond using traditional breast density measures. Mammography is the current gold standard in screening for breast cancer in average-risk women. Radiologically dense and complex tissue can reduce screening detection sensitivity leading to obscured breast lesions and cancers missed by screening mammography [3, 4]. These cancers discovered within 12 months after normal screening mammograms are defined as interval cancers, and the reduction of mammographic sensitivity from breast density is commonly called masking. 13% of breast cancers diagnosed in the U.S are interval cancers [5], and identifying women at high risk of interval cancers could prove useful to inform discussions on supplemental imaging
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
