Artificial Intelligence Group

Artificial Intelligence research is becoming ubiquitous in radiology. We develop algorithms that assist radiologists in their clinical duties by making their work faster, less error-prone and helping them make the right treatment decisions.

We are an interdisciplinary team of machine learning researchers and clinicians developing algorithms for image reconstruction, automatic medical image segmentation, prediction of molecular and metabolic tumour subtypes, patient survival and therapy response prediction and image-aided treatment planning.

Our key areas of focus are 3-dimensional computer vision, probabilistic modelling of complex and heterogenous datasets, secure and private artificial intelligence and the clinical deployment of AI algorithms.

Kaissis, G.A., Makowski, M.R., Rückert, D. et al. Secure, privacy-preserving and federated machine learning in medical imaging. Nat Mach Intell 2, 305–311 (2020). https://doi.org/10.1038/s42256-020-0186-1(link is external)

Dantes Z, Yen HY, Pfarr N, et al. Implementing cell-free DNA of pancreatic cancer patient-derived organoids for personalized oncology. JCI Insight. 2020;137809. doi:10.1172/jci.insight.137809

Burian E, Jungmann F, Kaissis GA, et al. Intensive Care Risk Estimation in COVID-19 Pneumonia Based on Clinical and Imaging Parameters: Experiences from the Munich Cohort. J Clin Med. 2020;9(5):1514. Published 2020 May 18. doi:10.3390/jcm9051514

Kaissis GA, Jungmann F, Ziegelmayer S, et al. Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters. J Clin Med. 2020;9(5):1250. Published 2020 Apr 25. doi:10.3390/jcm9051250

Kaissis G, Ziegelmayer S, Lohöfer F, et al. A machine learning model for the prediction of survival and tumor subtype in pancreatic ductal adenocarcinoma from preoperative diffusion-weighted imaging. Eur Radiol Exp. 2019;3(1):41. Published 2019 Oct 17. doi:10.1186/s41747-019-0119-0

Kaissis G, Ziegelmayer S, Lohöfer F, et al. A machine learning algorithm predicts molecular subtypes in pancreatic ductal adenocarcinoma with differential response to gemcitabine-based versus FOLFIRINOX chemotherapy. PLoS One. 2019;14(10):e0218642. Published 2019 Oct 2. doi:10.1371/journal.pone.0218642

Christ PF, Ettlinger F, Grün F, Ezzeldin M Lipkova J, Schlecht S, Ahmaddy F, Tatavarty S, Bickel M, Bilic P, Rempfler M, Hofmann F, D Anastasi M, Ahmadi S, Kaissis G, Holch J, Sommer W, Braren R, Heinemann V, Menze B. Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks, MICCAI 2017

Christ PF, Ettlinger F, Kaissis G, Schlecht S, Ahmaddy F, Grün F, Valentinitsch A, Ahmadi S, Braren R, Menze B. SurvivalNet: Predicting patient survival from diffusion weighted magnetic resonance images using cascaded fully convolutional and 3D convolutional neural networks, ISBI 2017

Bilic P, Christ PF, Vorontsov E, Chlebus G, Chen H, Dou Q, Fu CW, Han X, Heng PA, Hesser J, Kadoury S. The liver tumor segmentation benchmark (LITS). arXiv:1901.04056. 2019 Jan 13.

Kaissis GA, Lohöfer FK, Ziegelmayer S, et al. Borderline-resectable pancreatic adenocarcinoma: Contour irregularity of the venous confluence in pre-operative computed tomography predicts histopathological infiltration. PLoS One. 2019;14(1):e0208717. Published 2019 Jan 2. doi:10.1371/journal.pone.0208717