A High-Resolution Tile-Based Approach for Classifying Biological Regions in Whole-Slide Histopathological Images

• Type of Material: Article
• Authors: R.A. Hoffman, Georgia Institute of Technology; S. Kothari, Georgia Institute of Technology; John Phan, Emory University; Dongmei Wang, Emory University
• Language: English
• Date: 2014-01-01
• Publisher: Springer
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2014 Springer International Publishing Switzerland
• Final Published Version (URL): http://dx.doi.org/10.1007/978-3-319-03005-0_71
• Title of Journal or Parent Work: The International Conference on Health Informatics Proceedings
• Volume: 42
• Start Page: 280
• End Page: 283
• Grant/Funding Information: This research has been supported by grants from NIH (U54CA119338, 1RC2CA148265, and R01CA163256).
• Keywords: prognosis; cancer; automated processing; indentification; histopathological whole slide images; diagnosis; WSIs; biological regions

Abstract

Computational analysis of histopathological whole slide images (WSIs) has emerged as a potential means for improving cancer diagnosis and prognosis. However, an open issue relating to the automated processing of WSIs is the identification of biological regions such as tumor, stroma, and necrotic tissue on the slide. We develop a method for classifying WSI portions (512x512-pixel tiles) into biological regions by (1) extracting a set of 461 image features from each WSI tile, (2) optimizing tile-level prediction models using nested cross-validation on a small (600 tile) manually annotated tile-level training set, and (3) validating the models against a much larger (1.7x106 tile) data set for which ground truth was available on the whole-slide level. We calculated the predicted prevalence of each tissue region and compared this prevalence to the ground truth prevalence for each image in an independent validation set. Results show significant correlation between the predicted (using automated system) and reported biological region prevalences with p < 0.001 for eight of nine cases considered.