Multiview boosting digital pathology analysis of prostate cancer

被引:34
作者
Kwak, Jin Tae [1 ]
Hewitt, Stephen M. [2 ]
机构
[1] Sejong Univ, Dept Comp Sci & Engn, Seoul 05006, South Korea
[2] NCI, Tissue Array Res Program, Pathol Lab, Ctr Canc Res,NIH, Rockville, MD 20852 USA
基金
新加坡国家研究基金会;
关键词
Prostate cancer; Digital pathology; Multiview boosting; Multi-resolution; Machine learning; IMAGE-ANALYSIS; HISTOPATHOLOGY; CLASSIFICATION; GRADE;
D O I
10.1016/j.cmpb.2017.02.023
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Background and Objective: Various digital pathology tools have been developed to aid in analyzing tissues and improving cancer pathology. The multi-resolution nature of cancer pathology, however, has not been fully analyzed and utilized. Here, we develop an automated, cooperative, and multi-resolution method for improving prostate cancer diagnosis. Methods: Digitized tissue specimen images are obtained from 5 tissue microarrays (TMAs). The TMAs include 70 benign and 135 cancer samples (TMA1), 74 benign and 89 cancer samples (TMA2), 70 benign and 115 cancer samples (TMA3), 79 benign and 82 cancer samples (TMA4), and 72 benign and 86 cancer samples (TMA5). The tissue specimen images are segmented using intensity- and texture-based features. Using the segmentation results, a number of morphological features from lumens and epithelial nuclei are computed to characterize tissues at different resolutions. Applying a multiview boosting algorithm, tissue characteristics, obtained from differing resolutions, are cooperatively combined to achieve accurate cancer detection. Results: In segmenting prostate tissues, the multiview boosting method achieved >= 0.97 AUC using TMA1. For detecting cancers, the multiview boosting method achieved an AUC of 0.98 (95% CI: 0.97-0.99) as trained on TMA2 and tested on TMA3, TMA4, and TMA5. The proposed method was superior to single view approaches, utilizing features from a single resolution or merging features from all the resolutions. Moreover, the performance of the proposed method was insensitive to the choice of the training dataset. Trained on TMA3, TMA4, and TMA5, the proposed method obtained an AUC of 0.97 (95% CI: 0.96-0.98), 0.98 (95% CI: 0.96-0.99), and 0.97 (95% CI: 0.96-0.98), respectively. Conclusions: The multiview boosting method is capable of integrating information from multiple resolutions in an effective and efficient fashion and identifying cancers with high accuracy. The multiview boosting method holds a great potential for improving digital pathology tools and research. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:91 / 99
页数:9
相关论文
共 52 条
[1]   Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles [J].
Barker, Jocelyn ;
Hoogi, Assaf ;
Depeursinge, Adrien ;
Rubin, Daniel L. .
MEDICAL IMAGE ANALYSIS, 2016, 30 :60-71
[2]   Multi-Field-of-View Framework for Distinguishing Tumor Grade in ER plus Breast Cancer From Entire Histopathology Slides [J].
Basavanhally, Ajay ;
Ganesan, Shridar ;
Feldman, Michael ;
Shih, Natalie ;
Mies, Carolyn ;
Tomaszewski, John ;
Madabhushi, Anant .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2013, 60 (08) :2089-2099
[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]  
Belongie S., 2000, Conference on Neural Information Processing Systems, V2, P3
[5]  
Blum A., 1998, Proceedings of the Eleventh Annual Conference on Computational Learning Theory, P92, DOI 10.1145/279943.279962
[6]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[7]   New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images [J].
Chen, Jia-Mei ;
Qu, Ai-Ping ;
Wang, Lin-Wei ;
Yuan, Jing-Ping ;
Yang, Fang ;
Xiang, Qing-Ming ;
Maskey, Ninu ;
Yang, Gui-Fang ;
Liu, Juan ;
Li, Yan .
SCIENTIFIC REPORTS, 2015, 5
[8]  
CINTRA M L, 1991, International Urology and Nephrology, V23, P449, DOI 10.1007/BF02583988
[9]   Integrated morphologic analysis for the identification and characterization of disease subtypes [J].
Cooper, Lee A. D. ;
Kong, Jun ;
Gutman, David A. ;
Wang, Fusheng ;
Gao, Jingjing ;
Appin, Christina ;
Cholleti, Sharath ;
Pan, Tony ;
Sharma, Ashish ;
Scarpace, Lisa ;
Mikkelsen, Tom ;
Kurc, Tahsin ;
Moreno, Carlos S. ;
Brat, Daniel J. ;
Saltz, Joel H. .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2012, 19 (02) :317-323
[10]  
DIFRANCO M, 2008, P INT WORKSH MICR IM