Automated Classification of Benign and Malignant Proliferative Breast Lesions

被引:17
作者
Radiya-Dixit, Evani [1 ,2 ]
Zhu, David [1 ,2 ]
Beck, Andrew H. [2 ,3 ]
机构
[1] Beth Israel Deaconess Med Ctr, Dept Pathol, Harker Sch, Boston, MA 95128 USA
[2] Harvard Med Sch, Boston, MA 95128 USA
[3] Beth Israel Deaconess Med Ctr, Dept Pathol, Boston, MA 95128 USA
关键词
CANCER;
D O I
10.1038/s41598-017-10324-y
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Misclassification of breast lesions can result in either cancer progression or unnecessary chemotherapy. Automated classification tools are seen as promising second opinion providers in reducing such errors. We have developed predictive algorithms that automate the categorization of breast lesions as either benign usual ductal hyperplasia (UDH) or malignant ductal carcinoma in situ (DCIS). From diagnosed breast biopsy images from two hospitals, we obtained 392 biomarkers using Dong et al.'s (2014) computational tools for nuclei identification and feature extraction. We implemented six machine learning models and enhanced them by reducing prediction variance, extracting active features, and combining multiple algorithms. We used the area under the curve (AUC) of the receiver operating characteristic (ROC) curve for performance evaluation. Our top-performing model, a Combined model with Active Feature Extraction (CAFE) consisting of two logistic regression algorithms, obtained an AUC of 0.918 when trained on data from one hospital and tested on samples of the other, a statistically significant improvement over Dong et al.'s AUC of 0.858. Pathologists can substantially improve their diagnoses by using it as an unbiased validator. In the future, our work can also serve as a valuable methodology for differentiating between low-grade and high-grade DCIS.
引用
收藏
页数:8
相关论文
共 36 条
[1]  
[Anonymous], 2014, CNN FEATURES SHELF A
[2]   Informatics in Radiology Comparison of Logistic Regression and Artificial Neural Network Models in Breast Cancer Risk Estimation [J].
Ayer, Turgay ;
Chhatwal, Jagpreet ;
Alagoz, Oguzhan ;
Kahn, Charles E., Jr. ;
Woods, Ryan W. ;
Burnside, Elizabeth S. .
RADIOGRAPHICS, 2010, 30 (01) :13-U27
[3]   Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival [J].
Beck, Andrew H. ;
Sangoi, Ankur R. ;
Leung, Samuel ;
Marinelli, Robert J. ;
Nielsen, Torsten O. ;
van de Vijver, Marc J. ;
West, Robert B. ;
van de Rijn, Matt ;
Koller, Daphne .
SCIENCE TRANSLATIONAL MEDICINE, 2011, 3 (108)
[4]   Assessment of lesions coexisting with various grades of ductal intraepithelial neoplasia of the breast [J].
Bratthauer, GL ;
Tavassoli, FA .
VIRCHOWS ARCHIV, 2004, 444 (04) :340-344
[5]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[6]   Ductal Carcinoma in Situ at Core-Needle Biopsy: Meta-Analysis of Underestimation and Predictors of Invasive Breast Cancer [J].
Brennan, Meagan E. ;
Turner, Robin M. ;
Ciatto, Stefano ;
Marinovich, M. Luke ;
French, James R. ;
Macaskill, Petra ;
Houssami, Nehmat .
RADIOLOGY, 2011, 260 (01) :119-128
[7]  
Carvajal-Hausdorf D. E, 2014, LAB INVESTIGATION, V95
[8]   Using conditional inference forests to identify the factors affecting crash severity on arterial corridors [J].
Das, Abhishek ;
Abdel-Aty, Mohamed ;
Pande, Anurag .
JOURNAL OF SAFETY RESEARCH, 2009, 40 (04) :317-327
[9]  
Deng L., 2012, The mnist database of handwritten digit im
[10]   Computational Pathology to Discriminate Benign from Malignant Intraductal Proliferations of the Breast [J].
Dong, Fei ;
Irshad, Humayun ;
Oh, Eun-Yeong ;
Lerwill, Melinda F. ;
Brachtel, Elena F. ;
Jones, Nicholas C. ;
Knoblauch, Nicholas W. ;
Montaser-Kouhsari, Laleh ;
Johnson, Nicole B. ;
Rao, Luigi K. F. ;
Faulkner-Jones, Beverly ;
Wilbur, David C. ;
Schnitt, Stuart J. ;
Beck, Andrew H. .
PLOS ONE, 2014, 9 (12)