Few studies have addressed radiomics based differentiation of Glioblastoma (GBM) and intracranial metastatic disease (IMD). However, the effect of different tumor masks, comparison of single versus multiparametric MRI (mp-MRI) or select combination of sequences remains undefined. We cross-compared multiple radiomics based machine learning (ML) models using mp-MRI to determine optimized configurations. Our retrospective study included 60 GBM and 60 IMD patients. Forty-five combinations of ML models and feature reduction strategies were assessed for features extracted from whole tumor and edema masks using mp-MRI [T1W, T2W, T1-contrast enhanced (T1-CE), ADC, FLAIR], individual MRI sequences and combined T1-CE and FLAIR sequences. Model performance was assessed using receiver operating characteristic curve. For mp-MRI, the best model was LASSO model fit using full feature set (AUC 0.953). FLAIR was the best individual sequence (LASSO-full feature set, AUC 0.951). For combined T1-CE/FLAIR sequence, adaBoost-full feature set was the best performer (AUC 0.951). No significant difference was seen between top models across all scenarios, including models using FLAIR only, mp-MRI and combined T1-CE/FLAIR sequence. Top features were extracted from both the whole tumor and edema masks. Shape sphericity is an important discriminating feature.
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.
Spinal sarcoidosis, referring to involvement of the spine in sarcoidosis, is relatively rare and may mimic other neurological disease affecting the spine. The authors present a clinic radiological review of 18 spinal sarcoidosis patients who presented to a tertiary hospital, with emphasis on initial imaging and radiological response to treatment. Materials and methods: We retrospectively reviewed our departmental imaging archives over a 15-year period and found 49 cases of neurosarcoidosis out of which 18 patients had spinal magnetic resonance imaging. Results: Approximately 72% (13/18) of the neurosarcoidosis patients showed some form of spinal involvement. The clinical, epidemiological and imaging data were reviewed for these 13 patients at presentation and follow-up. The findings on magnetic resonance imaging included leptomeningeal enhancement (61%), pachymeningeal (23%), intramedullary enhancing lesions (38%) and bony involvement (15%). The cervical segment was most frequently involved followed by the thoracic segment. Involvement was often long segment (4.2 spinal segments) with proclivity for the dorsal cord. Mean follow-up was 23.2 months. A complete or near-complete radiological response occurred in 66% while partial response was seen in 25% patients. Four patients had isolated central nervous system involvement including one with isolated spinal cord involvement. On diffusion-weighted imaging, the apparent diffusion coefficient of intramedullary lesions was increased compared to normal-appearing cord on baseline and subsequent follow-up scans. Conclusions: Spinal sarcoidosis was previously considered uncommon but is being increasingly recognized with widespread use of magnetic resonance imaging. Proclivity for dorsal surface involvement is characteristic, although not necessarily pathognomonic. Also, quantitative diffusion studies may serve as a biomarker for the disease activity and parenchymal injury.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.