SPectroscOpic prediction of bRain Tumours (SPORT): study protocol of a prospective imaging trial

Abstract

Background The revised 2016 WHO-Classification of CNS-tumours now integrates molecular information of glial brain tumours for accurate diagnosis as well as for the development of targeted therapies. In this prospective study, our aim is to investigate the predictive value of MR-spectroscopy in order to establish a solid preoperative molecular stratification algorithm of these tumours. We will process a 1H MR-spectroscopy sequence within a radiomics analytics pipeline. Methods Patients treated at our institution with WHO-Grade II, III and IV gliomas will receive preoperative anatomical (T2- and T1-weighted imaging with and without contrast enhancement) and proton MR spectroscopy (MRS) by using chemical shift imaging (MRS) (5 × 5 × 15 mm3 voxel size). Tumour regions will be segmented and co-registered to corresponding spectroscopic voxels. Raw signals will be processed by a deep-learning approach for identifying patterns in metabolic data that provides information with respect to the histological diagnosis as well patient characteristics obtained and genomic data such as target sequencing and transcriptional data. Discussion By imaging the metabolic profile of a glioma using a customized chemical shift 1H MR spectroscopy sequence and by processing the metabolic profiles with a machine learning tool we intend to non-invasively uncover the genetic signature of gliomas. This work-up will support surgical and oncological decisions to improve personalized tumour treatment. Trial registration This study was initially registered under another name and was later retrospectively registered under the current name at the German Clinical Trials Register (DRKS) under DRKS00019855.

MRI radiomics and potential applications to glioblastoma

“…Liu and colleagues accomplished this in patients with low-grade gliomas, showing that T2-weighted radiomics features of progression-free survival were significantly associated with apoptosis, immune response, cell proliferation, and vascular development (51). A 2020 paper by Franco and colleagues outlined a future study that aims to use machine learning to analyze magnetic resonance spectroscopy (MRS) metabolite profiles in order to predict tumor types (52). Thus, by linking the abstract semantic features of radiomics to a tangible biologic basis, such endeavors could in turn improve understanding and acceptance of the technology.…”

Added value of magnetic resonance spectroscopy for diagnosing childhood cerebellar tumours

“…Some studies go further, aiming to correlate MRS profiles and the genetic profiles of adult gliomas. 22 Specific classifiers are required for childhood brain tumours, as the common paediatric tumour types differ from those occurring in adults. 2 Both single and multicentre studies of MRS for classifying childhood brain tumours have been reported for the three main tumour types: pilocytic astrocytoma (PA), medulloblastoma (MB) and ependymoma (EP).…”

“…Diagnostic classifiers, based on MRS, for brain tumours in adults, have been evaluated both retrospectively and prospectively, 18–21 showing good accuracy for discriminating between certain common tumour types. Some studies go further, aiming to correlate MRS profiles and the genetic profiles of adult gliomas 22 . Specific classifiers are required for childhood brain tumours, as the common paediatric tumour types differ from those occurring in adults 2 .…”