TY - JOUR
T1 - Using Convolutional Neural Networks for Enhanced Capture of Breast Parenchymal Complexity Patterns Associated with Breast Cancer Risk
AU - Gastounioti, Aimilia
AU - Oustimov, Andrew
AU - Hsieh, Meng Kang
AU - Pantalone, Lauren
AU - Conant, Emily F.
AU - Kontos, Despina
N1 - Funding Information:
Support for this project was provided by the Susan G. Komen Foundation [ PDF17479714 ] and the National Cancer Institute at the National Institutes of Health [Population-based Research Optimizing Screening through Personalized Regimens (PROSPR) Network ( U54CA163313 ), an R01 Research Project ( 2R01CA161749-05 ), and a Resource-Related Research Project—Cooperative Agreement ( 1U24CA189523-01A1 )].
Publisher Copyright:
© 2018 The Association of University Radiologists
PY - 2018/8
Y1 - 2018/8
N2 - Rationale and Objectives: We evaluate utilizing convolutional neural networks (CNNs) to optimally fuse parenchymal complexity measurements generated by texture analysis into discriminative meta-features relevant for breast cancer risk prediction. Materials and Methods: With Institutional Review Board approval and Health Insurance Portability and Accountability Act compliance, we retrospectively analyzed “For Processing” contralateral digital mammograms (GE Healthcare 2000D/DS) from 106 women with unilateral invasive breast cancer and 318 age-matched controls. We coupled established texture features (histogram, co-occurrence, run-length, structural), extracted using a previously validated lattice-based strategy, with a multichannel CNN into a hybrid framework in which a multitude of texture feature maps are reduced to meta-features predicting the case or control status. We evaluated the framework in a randomized split-sample setting, using the area under the curve (AUC) of the receiver operating characteristic (ROC) to assess case-control discriminatory capacity. We also compared the framework to CNNs directly fed with mammographic images, as well as to conventional texture analysis, where texture feature maps are summarized via simple statistical measures that are then used as inputs to a logistic regression model. Results: Strong case-control discriminatory capacity was demonstrated on the basis of the meta-features generated by the hybrid framework (AUC = 0.90), outperforming both CNNs applied directly to raw image data (AUC = 0.63, P <.05) and conventional texture analysis (AUC = 0.79, P <.05). Conclusions: Our results suggest that informative interactions between patterns exist in texture feature maps derived from mammographic images, which can be extracted and summarized via a multichannel CNN architecture toward leveraging the associations of textural measurements to breast cancer risk.
AB - Rationale and Objectives: We evaluate utilizing convolutional neural networks (CNNs) to optimally fuse parenchymal complexity measurements generated by texture analysis into discriminative meta-features relevant for breast cancer risk prediction. Materials and Methods: With Institutional Review Board approval and Health Insurance Portability and Accountability Act compliance, we retrospectively analyzed “For Processing” contralateral digital mammograms (GE Healthcare 2000D/DS) from 106 women with unilateral invasive breast cancer and 318 age-matched controls. We coupled established texture features (histogram, co-occurrence, run-length, structural), extracted using a previously validated lattice-based strategy, with a multichannel CNN into a hybrid framework in which a multitude of texture feature maps are reduced to meta-features predicting the case or control status. We evaluated the framework in a randomized split-sample setting, using the area under the curve (AUC) of the receiver operating characteristic (ROC) to assess case-control discriminatory capacity. We also compared the framework to CNNs directly fed with mammographic images, as well as to conventional texture analysis, where texture feature maps are summarized via simple statistical measures that are then used as inputs to a logistic regression model. Results: Strong case-control discriminatory capacity was demonstrated on the basis of the meta-features generated by the hybrid framework (AUC = 0.90), outperforming both CNNs applied directly to raw image data (AUC = 0.63, P <.05) and conventional texture analysis (AUC = 0.79, P <.05). Conclusions: Our results suggest that informative interactions between patterns exist in texture feature maps derived from mammographic images, which can be extracted and summarized via a multichannel CNN architecture toward leveraging the associations of textural measurements to breast cancer risk.
KW - Digital mammography
KW - breast cancer risk
KW - convolutional neural network
KW - parenchymal texture
UR - http://www.scopus.com/inward/record.url?scp=85041197030&partnerID=8YFLogxK
U2 - 10.1016/j.acra.2017.12.025
DO - 10.1016/j.acra.2017.12.025
M3 - Article
C2 - 29395798
AN - SCOPUS:85041197030
SN - 1076-6332
VL - 25
SP - 977
EP - 984
JO - Academic Radiology
JF - Academic Radiology
IS - 8
ER -