Deep learning methods aid in predicting risk of interval cancer

Purpose: The purpose of this study was to apply a neural net to a dataset of women who later experienced either screening detected or interval cancers and determine if it aids in classifying risk of interval cancer compared to using BI-RADS density. Materials and Methods: Full-field digital screening mammograms acquired in our clinics were reviewed from 2006-2015. Interval cancers were matched to screening-detected cancers based on age, race, exam date, and time since last imaging examination. A deep learning architecture (ResNet50) was trained on this dataset with the goal to classify between interval and screen detected cancers. Network weights were initialized from ImageNet training and the final fully connected layers were retrained. Prediction loss, prediction accuracy, and ROC curves were calculated using this deep learning architecture and compared to predictions from conditional logistic regression using BI-RADS density. Results: 182 interval and 173 screening-detected cancers were found in our study group. The prediction accuracy improved from 63% using only BI-RADS density to 78% after including predictions from the deep learning model. The area under the ROC curve improved from 0.65 using only BI-RADS density to 0.84 after including the deep learning network as a predictor. Conclusions: We conclude that deep learning methods may be useful in identifying individuals at risk of interval cancer and that these methods can provide additional risk information not contained in breast density alone.

[1]  K. Czene,et al.  Novel mammographic image features differentiate between interval and screen-detected breast cancer: a case-case study , 2016, Breast Cancer Research.

[2]  M. Yaffe,et al.  Quantifying masking in clinical mammograms via local detectability of simulated lesions. , 2016, Medical physics.

[3]  C R Key,et al.  Biologic characteristics of interval and screen-detected breast cancers. , 2000, Journal of the National Cancer Institute.

[4]  C. Lehman,et al.  Identifying women with dense breasts at high risk for interval cancer: a cohort study. , 2015, Annals of internal medicine.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jingmei Li,et al.  Risk factors and tumor characteristics of interval cancers by mammographic density. , 2015, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

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

[8]  C. Lehman,et al.  Comparative Effectiveness of Digital Versus Film-Screen Mammography in Community Practice in the United States , 2011, Annals of Internal Medicine.

[9]  Solveig Hofvind,et al.  Comparing Interval Breast Cancer Rates in Norway and North Carolina: Results and Challenges , 2009, Journal of medical screening.

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

[11]  C. Vachon,et al.  Mammographic texture and risk of breast cancer by tumor type and estrogen receptor status , 2016, Breast Cancer Research.