Glioblastoma and primary central nervous system lymphoma: differentiation using MRI derived first-order texture analysis - a machine learning study.

Autor:	Priya S; Department of Radiology, University of Iowa Hospitals and Clinics, USA., Ward C; Department of Biostatistics, University of Iowa, USA., Locke T; Department of Radiology, University of Iowa Hospitals and Clinics, USA., Soni N; Department of Radiology, University of Iowa Hospitals and Clinics, USA., Maheshwarappa RP; Department of Radiology, University of Iowa Hospitals and Clinics, USA., Monga V; Department of Medicine, University of Iowa Hospitals and Clinics, USA., Agarwal A; Department of Radiology, University of South Western Medical Center, USA., Bathla G; Department of Radiology, University of Iowa Hospitals and Clinics, USA.
Jazyk:	angličtina
Zdroj:	The neuroradiology journal [Neuroradiol J] 2021 Aug; Vol. 34 (4), pp. 320-328. Date of Electronic Publication: 2021 Mar 03.
DOI:	10.1177/1971400921998979
Abstrakt:	Objectives: To evaluate the diagnostic performance of multiple machine learning classifier models derived from first-order histogram texture parameters extracted from T1-weighted contrast-enhanced images in differentiating glioblastoma and primary central nervous system lymphoma. Methods: Retrospective study with 97 glioblastoma and 46 primary central nervous system lymphoma patients. Thirty-six different combinations of classifier models and feature selection techniques were evaluated. Five-fold nested cross-validation was performed. Model performance was assessed for whole tumour and largest single slice using receiver operating characteristic curve. Results: The cross-validated model performance was relatively similar for the top performing models for both whole tumour and largest single slice (area under the curve 0.909-0.924). However, there was a considerable difference between the worst performing model (logistic regression with full feature set, area under the curve 0.737) and the highest performing model for whole tumour (least absolute shrinkage and selection operator model with correlation filter, area under the curve 0.924). For single slice, the multilayer perceptron model with correlation filter had the highest performance (area under the curve 0.914). No significant difference was seen between the diagnostic performance of the top performing model for both whole tumour and largest single slice. Conclusions: T1 contrast-enhanced derived first-order texture analysis can differentiate between glioblastoma and primary central nervous system lymphoma with good diagnostic performance. The machine learning performance can vary significantly depending on the model and feature selection methods. Largest single slice and whole tumour analysis show comparable diagnostic performance.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu