Back to Search
Start Over
Radio-pathomic mapping model generated using annotations from five pathologists reliably distinguishes high-grade prostate cancer
- Source :
- Journal of Medical Imaging
- Publication Year :
- 2020
-
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
- Subjects :
- Paper
rad-path
medicine.diagnostic_test
Receiver operating characteristic
business.industry
Significant difference
Magnetic resonance imaging
medicine.disease
prostate cancer
Regression
Computer-Aided Diagnosis
030218 nuclear medicine & medical imaging
03 medical and health sciences
Prostate cancer
0302 clinical medicine
machine learning
Disease severity
030220 oncology & carcinogenesis
Biopsy
medicine
Effective diffusion coefficient
magnetic resonance imaging
Radiology, Nuclear Medicine and imaging
Nuclear medicine
business
Subjects
Details
- ISSN :
- 23294302
- Volume :
- 7
- Issue :
- 5
- Database :
- OpenAIRE
- Journal :
- Journal of medical imaging (Bellingham, Wash.)
- Accession number :
- edsair.doi.dedup.....380b7bb3614d36f5dbc31a6e45e58170