Does Whole Brain Radiomics on Multimodal Neuroimaging Make Sense in Neuro-Oncology? A Proof of Concept Study.

Authors

Danilov G,Kalaeva D,Vikhrova N,Shugay S,Telysheva E,Goraynov S,Kosyrkova A,Pavlova G,Pronin I,Usachev D

Affiliations (6)

  • Laboratory of Biomedical Informatics and Artificial Intelligence.
  • Department of Neuroimaging.
  • Department of Pathology.
  • Department of Neurotrauma.
  • Laboratory of molecular and cellular neurogenetics.
  • Director, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.

Abstract

Employing a whole-brain (WB) mask as a region of interest for extracting radiomic features is a feasible, albeit less common, approach in neuro-oncology research. This study aims to evaluate the relationship between WB radiomic features, derived from various neuroimaging modalities in patients with gliomas, and some key baseline characteristics of patients and tumors such as sex, histological tumor type, WHO Grade (2021), IDH1 mutation status, necrosis lesions, contrast enhancement, T/N peak value and metabolic tumor volume. Forty-one patients (average age 50 ± 15 years, 21 females and 20 males) with supratentorial glial tumors were enrolled in this study. A total of 38,720 radiomic features were extracted. Cluster analysis revealed that whole-brain images of biologically different tumors could be distinguished to a certain extent based on their imaging biomarkers. Machine learning capabilities to detect image properties like contrast-enhanced or necrotic zones validated radiomic features in objectifying image semantics. Furthermore, the predictive capability of imaging biomarkers in determining tumor histology, grade and mutation type underscores their diagnostic potential. Whole-brain radiomics using multimodal neuroimaging data appeared to be informative in neuro-oncology, making research in this area well justified.

Topics

NeuroimagingBrain NeoplasmsGliomaMultimodal ImagingBrainJournal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.