Dataset Information

Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy.

ABSTRACT: JUSTIFICATION: Automatic brain tumor classification by MRS has been under development for more than a decade. Nonetheless, to our knowledge, there are no published evaluations of predictive models with unseen cases that are subsequently acquired in different centers. The multicenter eTUMOUR project (2004-2009), which builds upon previous expertise from the INTERPRET project (2000-2002) has allowed such an evaluation to take place. MATERIALS AND METHODS: A total of 253 pairwise classifiers for glioblastoma, meningioma, metastasis, and low-grade glial diagnosis were inferred based on 211 SV short TE INTERPRET MR spectra obtained at 1.5 T (PRESS or STEAM, 20-32 ms) and automatically pre-processed. Afterwards, the classifiers were tested with 97 spectra, which were subsequently compiled during eTUMOUR. RESULTS: In our results based on subsequently acquired spectra, accuracies of around 90% were achieved for most of the pairwise discrimination problems. The exception was for the glioblastoma versus metastasis discrimination, which was below 78%. A more clear definition of metastases may be obtained by other approaches, such as MRSI + MRI. CONCLUSIONS: The prediction of the tumor type of in-vivo MRS is possible using classifiers developed from previously acquired data, in different hospitals with different instrumentation under the same acquisition protocols. This methodology may find application for assisting in the diagnosis of new brain tumor cases and for the quality control of multicenter MRS databases.

SUBMITTER: Garcia-Gomez JM

PROVIDER: S-EPMC2797843 | biostudies-other | 2009 Feb

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Medulloblastoma (MB) is the most common malignant brain tumor occurring in childhood and rarely found in adult. Based on transcriptome profile MB are currently classified into four major molecular groups reflecting a considerable biological heterogeneity: WNT-activated, SHH-activated, group 3 and group 4. Recently, DNA methylation profiling allowed the identification of additional subgroups within the four major molecular groups associated with different clinic-pathological and molecular features. Isocitrate Dehydrogenase-1 (IDH1) mutations have been described in several tumours, including gliomas, while in MB are exceptionally reported and not routinely investigated. By mean of magnetic resonance spectroscopy (MRS) we unequivocally assessed the presence the oncometabolite D-2-Hydroxyglutarate (2HG), a marker of IDH1 and IDH2 mutation, in a case of adult MB. Immunophenotypical work-up and methylation profiling assigned the diagnosis of MB, subclass SHH-A, and molecular testing revealed the presence of the non-canonical somatic IDH1(p.R132C) mutation and an additional GNAS mutation, also exceptionally described in MB. To our knowledge this is the first reported case of MB harboring both mutations together. Of note, tumour exhibited a heterogeneous phenotype with a tumour component displaying glial differentiation, with robust GFAP expression, and a component with conventional MB features and selective presence of GNAS mutation, suggesting coexistence of two different major tumour clones. These findings draw attention to the need of a deeper genetic characterization of MB in order to get insights into their biology and improve stratification and clinical management of the patients. Moreover, reported data underling the importance of performing MRS for the identification of IDH mutations in non-glial tumours. The use of throughput molecular profiling analysis and advanced medical imaging technology will certainly increase the frequency with which rare tumour entities will be identified. Whether they have any particular therapeutic implications or prognostic relevance requires further investigations.

Dataset Information

Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets