7 Tesla magnetic resonance spectroscopic imaging predicting IDH status and glioma grading.

Cornelius CadrienSukrit SharmaPhilipp LazenRoxane LicandroJulia FurtnerAlexandra LipkaEva NiessLukas HingerlStanislav MotykaStephan GruberBernhard StrasserBarbara KieselMario MischkulnigMatthias PreusserThomas Roetzer-PejrimovskyAdelheid WöhrerMichael WeberChristian DorferSiegfried TrattnigKarl RösslerWolfgang BognerGeorg WidhalmGilbert J Hangel

Published in: Cancer imaging : the official publication of the International Cancer Imaging Society (2024)

We successfully classified IDH mutation status and high- versus low-grade gliomas preoperatively based on 7 T MRSI and clinical tumor segmentation. With this approach, we demonstrated imaging based tumor marker predictions at least as accurate as comparable studies, highlighting the potential application of MRSI for pre-operative tumor classifications.

Keyphrases

low grade
high grade
magnetic resonance
high resolution
deep learning
molecular docking
magnetic resonance imaging
machine learning
photodynamic therapy
risk assessment
contrast enhanced
case control