naa a22 4500 510808107 CHVBK 20180411083427.0 cr unu---uuuuu 180411e20130901xx s 000 0 eng 10.1007/s11548-012-0808-0 doi (NATIONALLICENCE)springer-10.1007/s11548-012-0808-0 Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data [Elektronische Daten] [Evangelia Tsolaki, Patricia Svolos, Evanthia Kousi, Eftychia Kapsalaki, Konstantinos Fountas, Kyriaki Theodorou, Ioannis Tsougos] PurposeDifferentiation of glioblastomas from metastases is clinical important, but may be difficult even for expert observers. To investigate the contribution of machine learning algorithms in the differentiation of glioblastomas multiforme (GB) from metastases, we developed and tested a pattern recognition system based on 3T magnetic resonance (MR) data. Materials and MethodsSingle and multi-voxel proton magnetic resonance spectroscopy (1H-MRS) and dynamic susceptibility contrast (DSC) MRI scans were performed on 49 patients with solitary brain tumors (35 glioblastoma multiforme and 14 metastases). Metabolic (NAA/Cr, Cho/Cr, (Lip $$+$$ Lac)/Cr) and perfusion (rCBV) parameters were measured in both intratumoral and peritumoral regions. The statistical significance of these parameters was evaluated. For the classification procedure, three datasets were created to find the optimum combination of parameters that provides maximum differentiation. Three machine learning methods were utilized: Naïve-Bayes, Support Vector Machine (SVM) and $$k$$ -nearest neighbor (KNN). The discrimination ability of each classifier was evaluated with quantitative performance metrics. ResultsGlioblastoma and metastases were differentiable only in the peritumoral region of these lesions ( $$p<0.05$$ ). SVM achieved the highest overall performance (accuracy 98%) for both the intratumoral and peritumoral areas. Naïve-Bayes and KNN presented greater variations in performance. The proper selection of datasets plays a very significant role as they are closely correlated to the underlying pathophysiology. ConclusionThe application of pattern recognition techniques using 3T MR-based perfusion and metabolic features may provide incremental diagnostic value in the differentiation of common intraaxial brain tumors, such as glioblastoma versus metastasis. CARS, 2013 Classification nationallicence DSC-MRI nationallicence Glioblastoma nationallicence 1H-MRS nationallicence KNN nationallicence Metastasis nationallicence Naïve Bayes nationallicence Pattern recognition nationallicence SVM nationallicence Tsolaki Evangelia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Svolos Patricia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Kousi Evanthia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Kapsalaki Eftychia Department of Radiology, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Fountas Konstantinos Department of Neurosurgery, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Theodorou Kyriaki Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut Tsougos Ioannis Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/5(2013-09-01), 751-761 1861-6410 8:5<751 2013 8 11548 https://doi.org/10.1007/s11548-012-0808-0 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11548-012-0808-0 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Tsolaki Evangelia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Svolos Patricia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Kousi Evanthia Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Kapsalaki Eftychia Department of Radiology, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Fountas Konstantinos Department of Neurosurgery, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Theodorou Kyriaki Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 700 1- Tsougos Ioannis Medical Physics Department, Medical School, University of Thessaly, 41110, Biopolis, Larissa, Greece aut NATIONALLICENCE 773 0- International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/5(2013-09-01), 751-761 1861-6410 8:5<751 2013 8 11548 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer