Assessment of Machine Learning of Breast Pathology Structures for Automated Differentiation of Breast Cancer and High-Risk Proliferative Lesions

Key Points Question Can computer vision and machine learning methods be used for automated diagnosis of preinvasive and invasive lesions of the breast to improve diagnostic accuracy? Findings This diagnostic study of 240 breast biopsies categorized by 3 expert pathologists evaluated 2 sets of image features, which achieved sensitivity and specificity comparable with 87 pathologists in the diagnosis of breast biopsy samples. The computer-based, automated approach outperformed pathologists in differentiating ductal carcinoma in situ from atypia. Meaning The findings suggest that machine learning methods are potentially suitable as diagnostic support systems in differentiating challenging preinvasive lesions of the breast.

[1]  A. Jemal,et al.  Cancer statistics, 2019 , 2019, CA: a cancer journal for clinicians.

[2]  Linda G. Shapiro,et al.  Learning to Segment Breast Biopsy Whole Slide Images , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[3]  Donald L Weaver,et al.  Understanding diagnostic variability in breast pathology: lessons learned from an expert consensus review panel , 2014, Histopathology.

[4]  Yinan Kong,et al.  Histopathological Breast Cancer Image Classification by Deep Neural Network Techniques Guided by Local Clustering , 2018, BioMed research international.

[5]  Iman Hajirasouliha,et al.  Breast Cancer Histopathological Image Classification: A Deep Learning Approach , 2018, bioRxiv.

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

[7]  Linda G. Shapiro,et al.  Localization of Diagnostically Relevant Regions of Interest in Whole Slide Images: a Comparative Study , 2016, Journal of Digital Imaging.

[8]  Andrew H. Beck,et al.  Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer , 2017, JAMA.

[9]  Andrew H. Beck,et al.  Automated Classification of Benign and Malignant Proliferative Breast Lesions , 2017, Scientific Reports.

[10]  Gary Longton,et al.  Development of a diagnostic test set to assess agreement in breast pathology: practical application of the Guidelines for Reporting Reliability and Agreement Studies (GRRAS) , 2013, BMC Women's Health.

[11]  Linda G. Shapiro,et al.  Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks , 2018, Pattern Recognit..

[12]  Karla Kerlikowske,et al.  Pathologic findings from the Breast Cancer Surveillance Consortium , 2006, Cancer.

[13]  Linda G. Shapiro,et al.  Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images , 2018, MICCAI.

[14]  Shuiwang Ji,et al.  Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation , 2017, IEEE Transactions on Medical Imaging.

[15]  S. Jambawalikar,et al.  Accuracy of Distinguishing Atypical Ductal Hyperplasia From Ductal Carcinoma In Situ With Convolutional Neural Network-Based Machine Learning Approach Using Mammographic Image Data. , 2019, AJR. American journal of roentgenology.

[16]  Nico Karssemeijer,et al.  Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies , 2018, Modern Pathology.

[17]  Linda G. Shapiro,et al.  Multi-Instance Multi-Label Learning for Multi-Class Classification of Whole Slide Breast Histopathology Images , 2018, IEEE Transactions on Medical Imaging.

[18]  Linda G. Shapiro,et al.  A Randomized Study Comparing Digital Imaging to Traditional Glass Slide Microscopy for Breast Biopsy and Cancer Diagnosis , 2017, Journal of pathology informatics.

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

[20]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[21]  Andrew H. Beck,et al.  Computational Pathology to Discriminate Benign from Malignant Intraductal Proliferations of the Breast , 2014, PloS one.

[22]  J. Elmore,et al.  Diagnostic concordance among pathologists interpreting breast biopsy specimens. , 2015, JAMA.

[23]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[24]  Linda G. Shapiro,et al.  Multi-instance multi-label learning for whole slide breast histopathology , 2016, SPIE Medical Imaging.