Technical University of Munich, Germany
Posters & Accepted Abstracts: J Neurol Disord
This projects is proposing a novel machine learning algorithm based on Generative Method to characterize intra-tumor heterogeneity of glioma. The algorithm was applied on dynamic [18F] FET-PET, [18F] Fmiso PET, rOEF, MRI T1, T2, T1W, T2W, FLAIR, DCE MRI and so on. This probabilistic model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities. Classification result shows partly distributed feature maps in order to be able to select relevant features amongst wide patient data. The identified parts with different malignancy were discussed and validated according to first, the manual segmentations by clinical experts to investigate the performance on the tumor borders and second, graph maps to investigate the performance on the intra tumor regions. The main aim of the project is focused on the extraction of the additive information from PET and combining it with the MRI images information for each patient and relating them to the grade of malignancy.
Neurological Disorders received 1123 citations as per Google Scholar report