Developing a Radiomics Signature for Supratentorial Extra-Ventricular Ependymoma Using Multimodal MR Imaging

Abstract

Rationale and Objectives: To build a machine learning-based diagnostic model that can accurately distinguish adult supratentorial extraventricular ependymoma (STEE) from similarly appearing high-grade gliomas (HGG) using quantitative radiomic signatures from a multi-parametric MRI framework.Materials and Methods: We computed radiomic features on the preprocessed and segmented tumor masks from a pre-operative multimodal MRI dataset [contrast-enhanced T1 (T1ce), T2, fluid-attenuated inversion recovery (FLAIR), apparent diffusion coefficient (ADC)] from STEE (n = 15), HGG-Grade IV (HGG-G4) (n = 24), and HGG-Grade III (HGG-G3) (n = 36) patients, followed by an optimum two-stage feature selection and multiclass classification. Performance of multiple classifiers were evaluated on both unimodal and multimodal feature sets and most discriminative radiomic features involved in classification of STEE from HGG subtypes were obtained.Results: Multimodal features demonstrated higher classification performance over unimodal feature set in discriminating STEE and HGG subtypes with an accuracy of 68% on test data and above 80% on cross validation, along with an overall above 90% specificity. Among unimodal feature sets, those extracted from FLAIR demonstrated high classification performance in delineating all three tumor groups. Texture-based radiomic features particularly from FLAIR were most important in discriminating STEE from HGG-G4, whereas first-order features from T2 and ADC consistently ranked higher in differentiating multiple tumor groups.Conclusions: This study illustrates the utility of radiomics-based multimodal MRI framework in accurately discriminating similarly appearing adult STEE from HGG subtypes. Radiomic features from multiple MRI modalities could capture intricate and complementary information for a robust and highly accurate multiclass tumor classification.

Malignant transformation of desmoplastic infantile tumors in a non-infant: a case report

“…PNET is often located in the deep brain, and tumors are mainly presented as solid masses with cystic degeneration, necrosis, and bleeding, with a poor prognosis ( 15 ). Supratentorial ependymoma is usually located next to the lateral ventricle triangle, and calcification is common ( 16 ). Ganglioglioma often involves the temporal lobe, and the clinical manifestations are complex epilepsy.…”

Multinodular intraventricular lymphoplasmacyte-rich meningioma with significant calcification: a case description

“…Fine granular mixed signals visible inside the choroid plexus papilloma constitute its more characteristic imaging manifestations ( 13 ). Ependymoma tends to occur in the lateral ventricle body, the tumor shape is irregular; the border is not clear; it can invade the surrounding brain parenchyma; cystic changes, necrosis, and calcification signs are common; intratumor hemorrhage may occur; and the enhanced scan is mostly uneven and strengthened ( 14 ). Primary lymphoma of the brain is more common in middle-aged and older adult individuals, and the lesions are mostly located around the ventricles and often distributed near the midline, with a clear outline and mild edema being apparent around the lesion ( 15 ).…”