PD71-09 QUANTITATIVE DIGITAL IMAGE ANALYSIS AND MACHINE LEARNING ACCURATELY CLASSIFIES PRIMARY PROSTATE TUMORS OF BONE METASTATIC DISEASE BASED ON HISTOMORPHOMETRIC FEATURES IN DIAGNOSTIC PROSTATE NEEDLE BIOPSIES

Abstract

You have accessJournal of UrologyProstate Cancer: Markers III1 Apr 2017PD71-09 QUANTITATIVE DIGITAL IMAGE ANALYSIS AND MACHINE LEARNING ACCURATELY CLASSIFIES PRIMARY PROSTATE TUMORS OF BONE METASTATIC DISEASE BASED ON HISTOMORPHOMETRIC FEATURES IN DIAGNOSTIC PROSTATE NEEDLE BIOPSIES Eric Miller, Hootan Salemi, Sergey Klimov, Michael Lewis, Isla Garraway, Beatrice Knudsen, and Arkadiusz Gertych Eric MillerEric Miller More articles by this author , Hootan SalemiHootan Salemi More articles by this author , Sergey KlimovSergey Klimov More articles by this author , Michael LewisMichael Lewis More articles by this author , Isla GarrawayIsla Garraway More articles by this author , Beatrice KnudsenBeatrice Knudsen More articles by this author , and Arkadiusz GertychArkadiusz Gertych More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2017.02.3176AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES Prostate cancer (PC) with de novo bone metastases (M1) has a 5-year survival of 28%. Pathological features of primary M1 tumors are generally indistinguishable from those of high-grade localized (M0) cases, however 5-year survival for M0 PC is nearly 100%. Digital image analysis is an evolving ″OMICS″ platform for biomarker development that can be applied to diagnostic histopathology. We hypothesize that novel software analysis tools and machine learning can systematically interrogate digitized prostate needle biopsy (PNBX) slides to extract histomorphometric features that identify discrepant architecture and nuclear texture of M0 and M1 tumors. Herein, algorithms that measure these features were developed in a training set of digital images and then validated in an independent patient cohort. METHODS We created a biorepository of diagnostic PNBX specimens from 2150 PC patients from the Greater Los Angeles VA Healthcare System between 2000 and 2016. The biorepository was mined to create a matched cohort of M0 (n=44) and M1 (n=61) cases. Slides were digitized at 40X magnification and two pathologists annotated all cancer foci. ~30 image tiles were obtained from each case (n=2857) and 88 features were extracted. Segmentation based fractal texture descriptors (SFTA), Gabor (GF), grey level run length (GLRL), and nuclear texture (CP) features were used to train a classifier to distinguish M0 from M1 tiles. RESULTS After conversion of M0 and M1 image tiles to digital nuclear masks, training features were used to classify nuclear texture or tissue architecture. The majority vote from nuclear classification was transferred to the tile level and the majority classification of tiles was used to classify each case. For tissue architecture, 45 STFA and 60 Gabor features classified M1 and M0 cases with an accuracy of 71.8% and 80%, respectively. For nuclear features, 44 GLRL and 8 CP classified M0 versus M1 cases with an accuracy of 63% and 75.4%, respectively. A classifier trained with a combined 88 features achieved 86% accuracy in distinguishing M1 from M0 cases. CONCLUSIONS We applied digital imaging technology and machine learning to extract 88 novel features that accurately differentiate high-grade M0 from M1 PC. The quantification of tissue architecture and nuclear morphology provides an orthogonal approach for biomarker development, which can be applied to prognostication and potential treatment decisions in patients with high-risk localized or metastatic PC. © 2017FiguresReferencesRelatedDetails Volume 197Issue 4SApril 2017Page: e1358-e1359 Advertisement Copyright & Permissions© 2017MetricsAuthor Information Eric Miller More articles by this author Hootan Salemi More articles by this author Sergey Klimov More articles by this author Michael Lewis More articles by this author Isla Garraway More articles by this author Beatrice Knudsen More articles by this author Arkadiusz Gertych More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...