Deep learning in computer-aided diagnosis incorporating mammographic characteristics of both tumor and parenchyma stroma

We investigated the additive role of breast parenchyma stroma in the computer-aided diagnosis (CADx) of tumors on full-field digital mammograms (FFDM) by combining images of the tumor and contralateral normal parenchyma information via deep learning. The study included 182 breast lesions in which 106 were malignant and 76 were benign. All FFDM images were acquired using a GE 2000D Senographe system and retrospectively collected under an Institution Review Board (IRB) approved, Health Insurance Portability and Accountability Act (HIPAA) compliant protocol. Convolutional neutral networks (CNNs) with transfer learning were used to extract image-based characteristics of lesions and of parenchymal patterns (on the contralateral breast) directly from the FFDM images. Classification performance was evaluated and compared between analysis of only tumors and that of combined tumor and parenchymal patterns in the task of distinguishing between malignant and benign cases with the area under the Receiver Operating Characteristic (ROC) curve (AUC) used as the figure of merit. Using only lesion image data, the transfer learning method yielded an AUC value of 0.871 (SE=0.025) and using combined information from both lesion and parenchyma analyses, an AUC value of 0.911 (SE=0.021) was observed. This improvement was statistically significant (p-value=0.0362). Thus, we conclude that using CNNs with transfer learning to combine extracted image information of both tumor and parenchyma may improve breast cancer diagnosis.

[1]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[2]  M. Giger,et al.  Analysis of spiculation in the computerized classification of mammographic masses. , 1995, Medical physics.

[3]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[4]  Hui Li,et al.  Relationships between computer-extracted mammographic texture pattern features and BRCA1/2mutation status: a cross-sectional study , 2014, Breast Cancer Research.

[5]  Andrew D. A. Maidment,et al.  Mammographic parenchymal patterns as an imaging marker of endogenous hormonal exposure: a preliminary study in a high-risk population. , 2013, Academic radiology.

[6]  E. Conant,et al.  Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment , 2016, Breast Cancer Research.

[7]  M. Giger,et al.  Computerized characterization of mammographic masses: analysis of spiculation. , 1994, Cancer letters.

[8]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  H. Lynch,et al.  Psychologic Aspects of Cancer Genetic Testing: A Research Update for Clinicians , 1997 .

[11]  M. Giger,et al.  Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM. , 2008, Medical physics.

[12]  Michael J. Carston,et al.  Texture Features from Mammographic Images and Risk of Breast Cancer , 2009, Cancer Epidemiology Biomarkers & Prevention.

[13]  J. Wolfe.  Breast patterns as an index of risk for developing breast cancer. , 1976, AJR. American journal of roentgenology.

[14]  Li Lan,et al.  Evaluation of computer-aided diagnosis on a large clinical full-field digital mammographic dataset. , 2008, Academic radiology.

[15]  C. Floyd,et al.  Prediction of breast cancer malignancy using an artificial neural network , 1994, Cancer.

[16]  N Karssemeijer,et al.  Use of border information in the classification of mammographic masses , 2006, Physics in medicine and biology.

[17]  M. Giger,et al.  Automated computerized classification of malignant and benign masses on digitized mammograms. , 1998, Academic radiology.

[18]  J. Wolfe.  Risk for breast cancer development determined by mammographic parenchymal pattern , 1976, Cancer.

[19]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Andrew D. A. Maidment,et al.  Analysis of parenchymal texture with digital breast tomosynthesis: comparison with digital mammography and implications for cancer risk assessment. , 2011, Radiology.

[21]  Li Lan,et al.  Pilot study demonstrating potential association between breast cancer image-based risk phenotypes and genomic biomarkers. , 2014, Medical physics.

[22]  Maryellen L. Giger,et al.  Computerized Analysis of Mammographic Parenchymal Patterns on a Large Clinical Dataset of Full-Field Digital Mammograms: Robustness Study with Two High-Risk Datasets , 2012, Journal of Digital Imaging.

[23]  M. Giger,et al.  Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. , 2013, Annual review of biomedical engineering.

[24]  Hui Li,et al.  Digital mammographic tumor classification using transfer learning from deep convolutional neural networks , 2016, Journal of medical imaging.

[25]  Martin J. Yaffe,et al.  Mammographic densities as a marker of human breast cancer risk and their use in chemoprevention , 2001, Current oncology reports.

[26]  Berkman Sahiner,et al.  Association of computerized mammographic parenchymal pattern measure with breast cancer risk: a pilot case-control study. , 2011, Radiology.

[27]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[28]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[29]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[30]  Lubomir M. Hadjiiski,et al.  Improvement of mammographic mass characterization using spiculation meausures and morphological features. , 2001, Medical physics.

[31]  Syed Muhammad Anwar,et al.  Deep Learning in Medical Image Analysis , 2017 .

[32]  Natalia Antropova,et al.  A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets , 2017, Medical physics.

[33]  Lubomir M. Hadjiiski,et al.  Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms , 2017, Physics in medicine and biology.

[34]  M. Giger,et al.  Computerized analysis of mammographic parenchymal patterns for breast cancer risk assessment: feature selection. , 2000, Medical physics.

[35]  J Y Lo,et al.  Computer-aided diagnosis of breast cancer: artificial neural network approach for optimized merging of mammographic features. , 1995, Academic radiology.