Predicting outcome in childhood diffuse midline gliomas using magnetic resonance imaging based texture analysis

Abstract

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

MRI-based radiomics for prognosis of pediatric diffuse intrinsic pontine glioma: an international study

“…Using a software for MRI-based texture analysis on a single 2D image slice of DIPG tumors, one study of 32 patients suggested “homogeneous” texture may have worse outcome. 40 In this study, we conducted a 3D image analysis and applied a discovery-driven approach in search of significant computational features to create a prognostic machine learning model. Combined gadolinium-enhanced T1-MRI and T2-MRI outperformed either MRI sequence alone.…”

Pediatric Brain Tumors: From Modern Classification System to Current Principles of Management

“…The best-characterized mutation is that of the NF2 gene, with other molecular mechanisms in the pediatric age group poorly characterized. Tumors in this age group are genetically distinct from their adult counterparts [78].…”

“…They are rare in children, representing only 2-3% of pediatric CNS tumors [77]. Their incidence is markedly greater in syndromes like Neurofibromatosis 2, Schwannomatosis, Gorlin syndrome, and familial meningioma syndrome [77,78]. Exposure to irradiation in childhood predisposes to the development of meningiomas [77,78].…”

“…Mostly, they present in the second decade of life [78] The most common presenting symptoms are headache, seen in almost half, followed by seizures, seen in almost 30%. Focal findings such as visual deficits, cranial nerve signs may also be present.…”

“…It is isointense or hypointense to gray matter on T1 and isointense or hyperintense on T2-weighted images [77]. Contrast enhancement is strong and uniform on both CT and MRI [78]. On histology, most are WHO Grade I.…”