Medical College of Wisconsin
CTSICores SearchResearch InformaticsREDCap

Radio-pathomic mapping model generated using annotations from five pathologists reliably distinguishes high-grade prostate cancer. J Med Imaging (Bellingham) 2020 Sep;7(5):054501

Date

09/15/2020

Pubmed ID

32923510

Pubmed Central ID

PMC7479263

DOI

10.1117/1.JMI.7.5.054501

Scopus ID

2-s2.0-85096616055 (requires institutional sign-in at Scopus site)   14 Citations

Abstract

Purpose: Our study predictively maps epithelium density in magnetic resonance imaging (MRI) space while varying the ground truth labels provided by five pathologists to quantify the downstream effects of interobserver variability. Approach: Clinical imaging and postsurgical tissue from 48 recruited prospective patients were used in our study. Tissue was sliced to match the MRI orientation and whole-mount slides were stained and digitized. Data from 28 patients ( n = 33 slides) were sent to five pathologists to be annotated. Slides from the remaining 20 patients ( n = 123 slides) were annotated by one of the five pathologists. Interpathologist variability was measured using Krippendorff's alpha. Pathologist-specific radiopathomic mapping models were trained using a partial least-squares regression using MRI values to predict epithelium density, a known marker for disease severity. An analysis of variance characterized intermodel means difference in epithelium density. A consensus model was created and evaluated using a receiver operator characteristic classifying high grade versus low grade and benign, and was statistically compared to apparent diffusion coefficient (ADC). Results: Interobserver variability ranged from low to acceptable agreement (0.31 to 0.69). There was a statistically significant difference in mean predicted epithelium density values ( p < 0.001 ) between the five models. The consensus model outperformed ADC (areas under the curve = 0.80 and 0.71, respectively, p < 0.05 ). Conclusion: We demonstrate that radiopathomic maps of epithelium density are sensitive to the pathologist annotating the dataset; however, it is unclear if these differences are clinically significant. The consensus model produced the best maps, matched the performance of the best individual model, and outperformed ADC.

Author List

McGarry SD, Bukowy JD, Iczkowski KA, Lowman AK, Brehler M, Bobholz S, Nencka A, Barrington A, Jacobsohn K, Unteriner J, Duvnjak P, Griffin M, Hohenwalter M, Keuter T, Huang W, Antic T, Paner G, Palangmonthip W, Banerjee A, LaViolette PS

Authors

Anjishnu Banerjee PhD Associate Professor in the Data Science Institute department at Medical College of Wisconsin
Samuel Bobholz PhD Assistant Professor in the Radiology department at Medical College of Wisconsin
Michael O. Griffin MD, PhD Associate Professor in the Radiology department at Medical College of Wisconsin
Peter LaViolette PhD Professor in the Radiology department at Medical College of Wisconsin
Andrew S. Nencka PhD Director, Associate Professor in the Radiology department at Medical College of Wisconsin