Biography

Matthias is a postdoctoral researcher at the EPICenter of the Medical University of Innsbruck. He has a background in computer science and medical image analysis. His research centres around advancements of machine learning methods with a focus on the specific requirements of medical data, particularly those of radiological and histo-pathological imaging.

He holds a MSc in Medical Informatics from the Technical University of Vienna and a PhD in Medical Imaging from the Medical University of Vienna. Before joining the Medical University of Innsbruck, he gained valuable industry experience working as a Machine Learning Engineer.

Selected publications

• Hofmanninger, J.*, Perkonigg, M.*, Brink, J. A., Pianykh, O., Herold, C., & Langs, G. (2020). Dynamic memory to alleviate catastrophic forgetting in continuous learning settings. In International Conference on Medical Image Computing and Computer-Assisted Intervention. MICCAI 2020 (pp. 359-368). Springer, Cham. * equal contribution
• Perkonigg, M., Hofmanninger, J., Herold, C., Brink, J. A., Pianykh O., Prosch H., & Langs, G. (2021). Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. Nature communications, 12, 5678.
• Perkonigg, M., Hofmanninger, J., Herold, C., Prosch, H., & Langs, G. (2022). Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics. The Journal of Machine Learning for Biomedical Imaging (MELBA).
• Fürböck, C., Perkonigg, M., Helbich, T., Pinker, K., Romeo, V., & Langs, G. (2022). Identifying phenotypic concepts discriminating molecular breast cancer sub-types. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 276-286). Cham: Springer Nature Switzerland.
• Bastati, N., Perkonigg, M., Sobotka, D., Poetter-Lang, S., Fragner, R., Beer, A., Messner, A., Watzenboeck, M., Pochepnia, S., Kittinger, J., Herold, A., Kristic, A., Hodge, J.C., Traussnig, S., Trauner, M., Ba-Ssalamah, A. & Langs, G. (2023). Correlation of histologic, imaging, and artificial intelligence features in NAFLD patients, derived from Gd-EOB-DTPA-enhanced MRI: a proof-of-concept study. European Radiology, 1-15.