Marko Grahovac, MSc
Department of Biomedical Imaging and Image-guided Therapy (Division of Nuclear Medicine)
Position: PHD Student
ORCID: 0000-0002-3323-778X
T +43 1 40400-55850
marko.grahovac@meduniwien.ac.at
Keywords
Artificial Intelligence; Data Mining; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted
Research group(s)
- Christian Doppler Laboratory for Applied Metabolomics
Head:
Research Area: We investigate ways to better characterize tumors using non-invasive imaging techniques. This is important because tumours are constantly changing through mutations. In this way, an individual therapy should be possible and its success should be continuously monitored.
Members:
Research interests
Machine learning, image processing, personalized medicine, tumour characterization
Techniques, methods & infrastructure
Techniques, Methods: In vivo feature engineering, Radiomics, Feature selection, Ensemble learning, Monte Carlo cross-validation
Infrastructure: high-performance computing (ITSC), Microsoft Azure cloud computing
Selected publications
- Papp, L. et al., 2018. Optimized Feature Extraction for Radiomics Analysis of 18F-FDG PET Imaging. Journal of Nuclear Medicine, 60(6), pp.864–872. Available at: http://dx.doi.org/10.2967/jnumed.118.217612.
- Papp, L. et al., 2017. Glioma Survival Prediction with Combined Analysis of In Vivo11C-MET PET Features, Ex Vivo Features, and Patient Features by Supervised Machine Learning. Journal of Nuclear Medicine, 59(6), pp.892–899. Available at: http://dx.doi.org/10.2967/jnumed.117.202267.
- Papp, L. et al., 2018. Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis. Frontiers in Physics, 6. Available at: http://dx.doi.org/10.3389/fphy.2018.00051.
- Grubmüller, B. et al., 2018. PSMA Ligand PET/MRI for Primary Prostate Cancer: Staging Performance and Clinical Impact. Clinical Cancer Research, 24(24), pp.6300–6307. Available at: http://dx.doi.org/10.1158/1078-0432.ccr-18-0768.
- Papp, L. et al., 2019. Comparison of machine learning-driven lesion classifiers in prostate PET/MRI cases over different repeatability categories of radiomic features. 57. Jahrestagung der Deutschen Gesellschaft für Nuklearmedizin. Available at: http://dx.doi.org/10.1055/s-0039-1683672.