Radio-pathomic Maps of Epithelium and Lumen Density Predict the Location of High-Grade Prostate Cancer

Details

• Alternative Title:
  Int J Radiat Oncol Biol Phys
• Personal Author:
  McGarry, Sean D. ; Hurrell, Sarah L. ; Iczkowski, Kenneth A. ; Hall, William ; Kaczmarowski, Amy L. ; Banerjee, Anjishnu ; Keuter, Tucker ; Jacobsohn, Kenneth ; Bukowy, John D. ; Nevalainen, Marja T. ; Hohenwalter, Mark D. ; See, William A. ; LaViolette, Peter S.
• Description:
  Purpose:
  
  This study aims to combine multiparametric magnetic resonance imaging (MRI) and digitized pathology with machine learning to generate predictive maps of histologic features for prostate cancer localization.
  
  Methods and Materials:
  
  Thirty-nine patients underwent MRI prior to prostatectomy. After surgery, tissue was sliced according to MRI orientation using patient-specific 3-dimensionally printed slicing jigs. Whole-mount sections were annotated by our pathologist and digitally contoured to differentiate the lumen and epithelium. Slides were co-registered to the T2-weighted MRI scan. A learning curve was generated to determine the number of patients required for a stable machine-learning model. Patients were randomly stratified into 2 training sets and 1 test set. Two partial least-squares regression models were trained, each capable of predicting lumen and epithelium density. Predicted density values were calculated for each patient in the test dataset, mapped into the MRI space, and compared between regions confirmed as high-grade prostate cancer.
  
  Results:
  
  The learning-curve analysis showed that a stable fit was achieved with data from 10 patients. Maps indicated that regions of increased epithelium and decreased lumen density, generated from each independent model, corresponded with pathologist-annotated regions of high-grade cancer.
  
  Conclusions:
  
  We present a radio-pathomic approach to mapping prostate cancer. We find that the maps are useful for highlighting high-grade tumors. This technique may be relevant for dose-painting strategies in prostate radiation therapy. © 2018 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
  
  
• Subjects:
  Aged Contrast Media Epithelium False Positive Reactions Humans Image Interpretation, Computer-Assisted Learning Curve Least-Squares Analysis Machine Learning Magnetic Resonance Imaging Male Middle Aged Neoplasm Staging Printing, Three-Dimensional Prospective Studies Prostate Prostate-Specific Antigen Prostatectomy Prostatic Neoplasms Radiotherapy Regression Analysis Reproducibility Of Results ROC Curve

  More +
• Source:
  Int J Radiat Oncol Biol Phys. 101(5):1179-1187
• Pubmed ID:
  29908785
• Pubmed Central ID:
  PMC6190585
• Document Type:
  Journal Article
• Funding:
  R01 CA113580/CA/NCI NIH HHSUnited States/ ; TL1 TR001437/TR/NCATS NIH HHSUnited States/ ; U01 CE002944/CE/NCIPC CDC HHSUnited States/ ; R01 CA218144/CA/NCI NIH HHSUnited States/ ; UL1 TR001436/TR/NCATS NIH HHSUnited States/ ; U01 NS088034/NS/NINDS NIH HHSUnited States/
• Volume:
  101
• Issue:
  5
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha256:bc906bdf1231beecc1da1646c1ac09c1ca1e7ebf9d321e4b5b5edc33d5432814
• Download URL:
  https://stacks.cdc.gov/view/cdc/119161/cdc_119161_DS1.pdf
• File Type:
  [PDF - 2.54 MB ]