Radiophysiomics: Brain Tumors Classification by Machine Learning and Physiological MRI Data

Stadlbauer A, Marhold F, Oberndorfer S, Heinz G, Buchfelder M, Kinfe TM, Meyer-Bäse A (2022)

Publication Type: Journal article

Publication year: 2022

Journal

Cancers MDPI

Book Volume: 14

Article Number: 2363

Journal Issue: 10

DOI: 10.3390/cancers14102363

Abstract

The precise initial characterization of contrast-enhancing brain tumors has significant con-sequences for clinical outcomes. Various novel neuroimaging methods have been developed to in-crease the specificity of conventional magnetic resonance imaging (cMRI) but also the increased complexity of data analysis. Artificial intelligence offers new options to manage this challenge in clinical settings. Here, we investigated whether multiclass machine learning (ML) algorithms applied to a high-dimensional panel of radiomic features from advanced MRI (advMRI) and physiological MRI (phyMRI; thus, radiophysiomics) could reliably classify contrast-enhancing brain tu-mors. The recently developed phyMRI technique enables the quantitative assessment of microvas-cular architecture, neovascularization, oxygen metabolism, and tissue hypoxia. A training cohort of 167 patients suffering from one of the five most common brain tumor entities (glioblastoma, ana-plastic glioma, meningioma, primary CNS lymphoma, or brain metastasis), combined with nine common ML algorithms, was used to develop overall 135 classifiers. Multiclass classification performance was investigated using tenfold cross-validation and an independent test cohort. Adaptive boosting and random forest in combination with advMRI and phyMRI data were superior to human reading in accuracy (0.875 vs. 0.850), precision (0.862 vs. 0.798), F-score (0.774 vs. 0.740), AUROC (0.886 vs. 0.813), and classification error (5 vs. 6). The radiologists, however, showed a higher sensitivity (0.767 vs. 0.750) and specificity (0.925 vs. 0.902). We demonstrated that ML-based radiophys-iomics could be helpful in the clinical routine diagnosis of contrast-enhancing brain tumors; how-ever, a high expenditure of time and work for data preprocessing requires the inclusion of deep neural networks.

Authors with CRIS profile

Michael Buchfelder Lehrstuhl für Neurochirurgie Thomas Mehari Kinfe Professur für Neurochirurgie mit dem Schwerpunkt Funktionelle Stereotaktische Neurochirurgie

Involved external institutions

Karl Landsteiner Privatuniversität für Gesundheitswissenschaften GmbH

Austria (AT) Florida State University (FSU)

United States (USA) (US)

How to cite

APA:

Stadlbauer, A., Marhold, F., Oberndorfer, S., Heinz, G., Buchfelder, M., Kinfe, T.M., & Meyer-Bäse, A. (2022). Radiophysiomics: Brain Tumors Classification by Machine Learning and Physiological MRI Data. Cancers, 14(10). https://doi.org/10.3390/cancers14102363

MLA:

Stadlbauer, Andreas, et al. "Radiophysiomics: Brain Tumors Classification by Machine Learning and Physiological MRI Data." Cancers 14.10 (2022).

BibTeX: Download