Interactive phenotyping of large-scale histology imaging data with HistomicsML

• Type of Material: Article
• Authors: Michael Nalisnik, Emory University; Mohamed Amgad, Emory University; Sanghoon Lee, Emory University; Sameer H. Halani, Emory University; Jose Enrique Velazquez Vega, Emory University; Daniel Brat, Emory University; David Gutman, Emory University; Lee Cooper, Emory University
• Language: English
• Date: 2017-11-06
• Publisher: Nature Publishing Group: Open Access Journals - Option C
• Publication Version: Final Published Version
• Copyright Statement: © 2017 The Author(s).
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1038/s41598-017-15092-3
• Title of Journal or Parent Work: Scientific Reports
• ISSN: 2045-2322
• Volume: 7
• Issue: 1
• Start Page: 14588
• End Page: 14588
• Grant/Funding Information: This work was supported by U.S. National Institutes of Health, National Library of Medicine Career Development Award K22LM011576, and National Cancer Institute grant U24CA194362.
• Keywords: DIFFUSE; TUMOR ANGIOGENESIS; Multidisciplinary Sciences; CLASSIFICATION; GLIOBLASTOMA; Science & Technology - Other Topics; Science & Technology
• Research Categories: Biology, Neuroscience; Health Sciences, Oncology; Health Sciences, Pathology

Abstract

Whole-slide imaging of histologic sections captures tissue microenvironments and cytologic details in expansive high-resolution images. These images can be mined to extract quantitative features that describe tissues, yielding measurements for hundreds of millions of histologic objects. A central challenge in utilizing this data is enabling investigators to train and evaluate classification rules for identifying objects related to processes like angiogenesis or immune response. In this paper we describe HistomicsML, an interactive machine-learning system for digital pathology imaging datasets. This framework uses active learning to direct user feedback, making classifier training efficient and scalable in datasets containing 10 8 + histologic objects. We demonstrate how this system can be used to phenotype microvascular structures in gliomas to predict survival, and to explore the molecular pathways associated with these phenotypes. Our approach enables researchers to unlock phenotypic information from digital pathology datasets to investigate prognostic image biomarkers and genotype-phenotype associations.