Radio-pathomic mapping model generated using annotations from five pathologists reliably distinguishes high-grade prostate cancer

Abstract

<b>Purpose:</b> 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. <b>Approach:</b> 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 ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mi>n</mml:mi> <mml:mo>=</mml:mo> <mml:mn>33</mml:mn></mml:mrow> </mml:math> slides) were sent to five pathologists to be annotated. Slides from the remaining 20 patients ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mi>n</mml:mi> <mml:mo>=</mml:mo> <mml:mn>123</mml:mn></mml:mrow> </mml:math> 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). <b>Results:</b> 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 ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mi>p</mml:mi> <mml:mo><</mml:mo> <mml:mn>0.001</mml:mn></mml:mrow> </mml:math> ) between the five models. The consensus model outperformed ADC (areas under the curve = 0.80 and 0.71, respectively, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mi>p</mml:mi> <mml:mo><</mml:mo> <mml:mn>0.05</mml:mn></mml:mrow> </mml:math> ). <b>Conclusion:</b> 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.