Deep Learning to Improve Breast Cancer Early Detection on Screening Mammography

The rapid development of deep learning, a family of machine learning techniques, has spurred much interest in its application to medical imaging problems. Here, we develop a deep learning algorithm that can accurately detect breast cancer on screening mammograms using an "end-to-end" training approach that efficiently leverages training datasets with either complete clinical annotation or only the cancer status (label) of the whole image. In this approach, lesion annotations are required only in the initial training stage, and subsequent stages require only image-level labels, eliminating the reliance on rarely available lesion annotations. Our all convolutional network method for classifying screening mammograms attained excellent performance in comparison with previous methods. On an independent test set of digitized film mammograms from Digital Database for Screening Mammography (DDSM), the best single model achieved a per-image AUC of 0.88, and four-model averaging improved the AUC to 0.91 (sensitivity: 86.1%, specificity: 80.1%). On a validation set of full-field digital mammography (FFDM) images from the INbreast database, the best single model achieved a per-image AUC of 0.95, and four-model averaging improved the AUC to 0.98 (sensitivity: 86.7%, specificity: 96.1%). We also demonstrate that a whole image classifier trained using our end-to-end approach on the DDSM digitized film mammograms can be transferred to INbreast FFDM images using only a subset of the INbreast data for fine-tuning and without further reliance on the availability of lesion annotations. These findings show that automatic deep learning methods can be readily trained to attain high accuracy on heterogeneous mammography platforms, and hold tremendous promise for improving clinical tools to reduce Preprint. Work in progress. ar X iv :1 70 8. 09 42 7v 5 [ cs .C V ] 3 1 D ec 2 01 8 false positive and false negative screening mammography results. Code and model available at: https://github.com/lishen/end2end-all-conv

[1]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[2]  C. D'Orsi,et al.  Influence of computer-aided detection on performance of screening mammography. , 2007, The New England journal of medicine.

[3]  Richard H. Moore,et al.  THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY , 2007 .

[4]  M. Elter,et al.  CADx of mammographic masses and clustered microcalcifications: a review. , 2009, Medical physics.

[5]  Luca Maria Gambardella,et al.  Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images , 2012, NIPS.

[6]  Maryellen L. Giger,et al.  Breast image feature learning with adaptive deconvolutional networks , 2012, Medical Imaging.

[7]  Jaime S. Cardoso,et al.  INbreast: toward a full-field digital mammographic database. , 2012, Academic radiology.

[8]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[10]  M. Yaffe,et al.  Impact of computer-aided detection systems on radiologist accuracy with digital mammography. , 2014, AJR. American journal of roentgenology.

[11]  J. Lortet-Tieulent,et al.  Breast Cancer Screening for Women at Average Risk: 2015 Guideline Update From the American Cancer Society. , 2015, JAMA.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[14]  Daniel L. Rubin,et al.  Probabilistic visual search for masses within mammography images using deep learning , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[15]  Gustavo Carneiro,et al.  Automated Mass Detection in Mammograms Using Cascaded Deep Learning and Random Forests , 2015, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[16]  Gustavo Carneiro,et al.  Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models , 2015, MICCAI.

[17]  Zheng Zhang,et al.  MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[18]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  C. Lehman,et al.  Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection. , 2015, JAMA internal medicine.

[21]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[23]  Miguel Ángel Guevara-López,et al.  Convolutional neural networks for mammography mass lesion classification , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Dayong Wang,et al.  Deep Learning for Identifying Metastatic Breast Cancer , 2016, ArXiv.

[25]  Daniel Lévy,et al.  Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks , 2016, ArXiv.

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

[27]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[28]  Gustavo Carneiro,et al.  The Automated Learning of Deep Features for Breast Mass Classification from Mammograms , 2016, MICCAI.

[29]  Miguel Ángel Guevara-López,et al.  Representation learning for mammography mass lesion classification with convolutional neural networks , 2016, Comput. Methods Programs Biomed..

[30]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[31]  Leonid Karlinsky,et al.  A Region Based Convolutional Network for Tumor Detection and Classification in Breast Mammography , 2016, LABELS/DLMIA@MICCAI.

[32]  Yoni Choukroun,et al.  Mammogram Classification and Abnormality Detection from Nonlocal Labels using Deep Multiple Instance Neural Network , 2017, VCBM.

[33]  Xiaohui Xie,et al.  Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification , 2016, bioRxiv.

[34]  Thomas Frauenfelder,et al.  Deep Learning in Mammography: Diagnostic Accuracy of a Multipurpose Image Analysis Software in the Detection of Breast Cancer , 2017, Investigative radiology.

[35]  Eun-Kyung Kim,et al.  Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study , 2018, Scientific Reports.

[36]  István Csabai,et al.  Detecting and classifying lesions in mammograms with Deep Learning , 2017, Scientific Reports.

[37]  Reyer Zwiggelaar,et al.  Deep learning in mammography and breast histology, an overview and future trends , 2018, Medical Image Anal..

[38]  Aly A. Mohamed,et al.  Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer Screening , 2018, Clinical Cancer Research.

[39]  Ulas Bagci,et al.  Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks. , 2018, The British journal of radiology.