Share Email Print
cover

Proceedings Paper

Performance assessment of automated tissue characterization for prostate H and E stained histopathology
Author(s): Matthew D. DiFranco; Hayley M. Reynolds; Catherine Mitchell; Scott Williams; Prue Allan; Annette Haworth
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Reliable automated prostate tumor detection and characterization in whole-mount histology images is sought in many applications, including post-resection tumor staging and as ground-truth data for multi-parametric MRI interpretation. In this study, an ensemble-based supervised classification algorithm for high-resolution histology images was trained on tile-based image features including histogram and gray-level co-occurrence statistics. The algorithm was assessed using different combinations of H and E prostate slides from two separate medical centers and at two different magnifications (400x and 200x), with the aim of applying tumor classification models to new data. Slides from both datasets were annotated by expert pathologists in order to identify homogeneous cancerous and non-cancerous tissue regions of interest, which were then categorized as (1) low-grade tumor (LG-PCa), including Gleason 3 and high-grade prostatic intraepithelial neoplasia (HG-PIN), (2) high-grade tumor (HG-PCa), including various Gleason 4 and 5 patterns, or (3) non-cancerous, including benign stroma and benign prostatic hyperplasia (BPH). Classification models for both LG-PCa and HG-PCa were separately trained using a support vector machine (SVM) approach, and per-tile tumor prediction maps were generated from the resulting ensembles. Results showed high sensitivity for predicting HG-PCa with an AUC up to 0.822 using training data from both medical centres, while LG-PCa showed a lower sensitivity of 0.763 with the same training data. Visual inspection of cancer probability heatmaps from 9 patients showed that 17/19 tumors were detected, and HG-PCa generally reported less false positives than LG-PCa.

Paper Details

Date Published: 27 April 2015
PDF: 9 pages
Proc. SPIE 9420, Medical Imaging 2015: Digital Pathology, 94200M (27 April 2015); doi: 10.1117/12.2081787
Show Author Affiliations
Matthew D. DiFranco, Medical Univ. of Vienna (Austria)
Hayley M. Reynolds, Peter MacCallum Cancer Ctr. (Australia)
Univ. of Melbourne (Australia)
Catherine Mitchell, Peter MacCallum Cancer Ctr. (Australia)
Scott Williams, The Univ. of Melbourne (Australia)
Peter MacCallum Cancer Ctr. (Australia)
Prue Allan, Peter MacCallum Cancer Ctr. (Australia)
Annette Haworth, Peter MacCallum Cancer Ctr. (Australia)
The Univ. of Melbourne (Australia)


Published in SPIE Proceedings Vol. 9420:
Medical Imaging 2015: Digital Pathology
Metin N. Gurcan; Anant Madabhushi, Editor(s)

© SPIE. Terms of Use
Back to Top