Dooman Arefan1, Ryan M Hausler2, Jules H Sumkin1, Min Sun3, Shandong Wu4,5,6,7. 1. Department of Radiology, University of Pittsburgh School of Medicine, 4200 Fifth Ave, Pittsburgh, PA, 15260, USA. 2. Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Blvd, Pittsburgh, PA, 15206, USA. 3. Division of Oncology, University of Pittsburgh Medical Center Hillman Cancer Center at St. Margaret, 200 Delafield Rd, Pittsburgh, PA, 15215, USA. 4. Department of Radiology, University of Pittsburgh School of Medicine, 4200 Fifth Ave, Pittsburgh, PA, 15260, USA. wus3@upmc.edu. 5. Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Blvd, Pittsburgh, PA, 15206, USA. wus3@upmc.edu. 6. Department of Bioengineering, University of Pittsburgh, 4200 Fifth Ave, Pittsburgh, PA, 15260, USA. wus3@upmc.edu. 7. Intelligent Systems Program, University of Pittsburgh, 4200 Fifth Ave, 15260, PA, Pittsburgh, USA. wus3@upmc.edu.
Abstract
BACKGROUND: The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. METHODS: We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. "high" vs "low") prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models' performance was measured via area under the receiver operating characteristic curve (AUC). RESULTS: Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. CONCLUSIONS: On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor's microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed.
BACKGROUND: The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. METHODS: We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. "high" vs "low") prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models' performance was measured via area under the receiver operating characteristic curve (AUC). RESULTS: Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. CONCLUSIONS: On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor's microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed.
Authors: Christoph A Karlo; Pier Luigi Di Paolo; Joshua Chaim; A Ari Hakimi; Irina Ostrovnaya; Paul Russo; Hedvig Hricak; Robert Motzer; James J Hsieh; Oguz Akin Journal: Radiology Date: 2013-10-28 Impact factor: 11.105
Authors: Kenneth Clark; Bruce Vendt; Kirk Smith; John Freymann; Justin Kirby; Paul Koppel; Stephen Moore; Stanley Phillips; David Maffitt; Michael Pringle; Lawrence Tarbox; Fred Prior Journal: J Digit Imaging Date: 2013-12 Impact factor: 4.056
Authors: John N Weinstein; Eric A Collisson; Gordon B Mills; Kenna R Mills Shaw; Brad A Ozenberger; Kyle Ellrott; Ilya Shmulevich; Chris Sander; Joshua M Stuart Journal: Nat Genet Date: 2013-10 Impact factor: 38.330
Authors: Roger Sun; Elaine Johanna Limkin; Maria Vakalopoulou; Laurent Dercle; Stéphane Champiat; Shan Rong Han; Loïc Verlingue; David Brandao; Andrea Lancia; Samy Ammari; Antoine Hollebecque; Jean-Yves Scoazec; Aurélien Marabelle; Christophe Massard; Jean-Charles Soria; Charlotte Robert; Nikos Paragios; Eric Deutsch; Charles Ferté Journal: Lancet Oncol Date: 2018-08-14 Impact factor: 41.316
Authors: H R Ali; E Provenzano; S-J Dawson; F M Blows; B Liu; M Shah; H M Earl; C J Poole; L Hiller; J A Dunn; S J Bowden; C Twelves; J M S Bartlett; S M A Mahmoud; E Rakha; I O Ellis; S Liu; D Gao; T O Nielsen; P D P Pharoah; C Caldas Journal: Ann Oncol Date: 2014-06-09 Impact factor: 32.976