Glioma Survival Prediction with Combined Analysis of In Vivo C-MET PET Features, Ex Vivo Features, and Patient Features by Supervised Machine Learning.
Journal:
Journal of nuclear medicine : official publication, Society of Nuclear Medicine
PMID:
29175980
Abstract
Gliomas are the most common type of tumor in the brain. Although the definite diagnosis is routinely made ex vivo by histopathologic and molecular examination, diagnostic work-up of patients with suspected glioma is mainly done using MRI. Nevertheless, l--methyl-C-methionine (C-MET) PET holds great potential in the characterization of gliomas. The aim of this study was to establish machine-learning-driven survival models for glioma built on in vivo C-MET PET characteristics, ex vivo characteristics, and patient characteristics. The study included 70 patients with a treatment-naïve glioma that was C-MET-positive and had histopathology-derived ex vivo feature extraction, such as World Health Organization 2007 tumor grade, histology, and isocitrate dehydrogenase 1 R132H mutational status. The C-MET-positive primary tumors were delineated semiautomatically on PET images, followed by the extraction of tumor-to-background-based general and higher-order textural features by applying 5 different binning approaches. In vivo and ex vivo features, as well as patient characteristics (age, weight, height, body mass index, Karnofsky score), were merged to characterize the tumors. Machine-learning approaches were used to identify relevant in vivo, ex vivo, and patient features and their relative weights for predicting 36-mo survival. The resulting feature weights were used to establish 3 predictive models per binning configuration: one model based on a combination of in vivo, ex vivo, and clinical patient information (M36); another based on in vivo and patient information only (M36); and a third based on in vivo information only (M36). In addition, a binning-independent model based on ex vivo and patient information only (M36) was created. The established models were validated in a Monte Carlo cross-validation scheme. The most prominent machine-learning-selected and -weighted features were patient-based and ex vivo-based, followed by in vivo-based. The highest areas under the curve for our models as revealed by the Monte Carlo cross-validation were 0.9 for M36, 0.87 for M36, 0.77 for M36, and 0.72 for M36 Prediction of survival in amino acid PET-positive glioma patients was highly accurate using computer-supported predictive models based on in vivo, ex vivo, and patient features.