Clinical Data Science
The clinical data science group employs advanced statistics, machine learning and computer vision techniques in the context of clinical radiology to enable fast and precise AI-supported diagnosis and prognostication.
Our direct embedding into the Department of Radiology provides close cooperation and interdisciplinary interaction with radiologists.
This gives us the opportunity to identify and address clinical needs and to develop and evaluate AI solutions directly in the clinical context.
Core Topics
Image data is the most natural type of data in every radiology department. Consequently, a great part of our research is dedicated to image analysis. In particular, we use state-of-the-art deep learning methods to analyze CT and MR images in 2D or 3D.
Computer vision in the field of medicine differs from other application areas since medical image data is typically sparse and labels are very expensive (time and money-wise). This makes computer vision in medicine a challenging, but also very fascinating branch of deep learning research.
Our ongoing computer vision research includes - but is not limited to - the following topics:
- Analyzing medical time series data by feeding CT perfusion images into complex deep neural network architectures
- Predicting the character of potentially cancerous lesions on sparse 3D image datasets without additional information, e.g. segmentation masks or laboratory findings
- Predicting clinical endpoints for 2D and 3D CT images using established convolutional neural network architectures
Our group aims at solving a wide range of problems in the context of clinical radiology. Each task comes with different data and needs to be tackled with different tools. Among the tools we used most often are: classical machine learning algorithms (e.g. random forest), radiomics and classical statistics.
Typically, we apply classical machine learning algorithms and statistics to tabular data in order to solve a clinical task, predict a clinical endpoint or visualize complex data structures.
Radiomics extracts standardized image features from medical images, e.g. CT or MR images, thereby transforming complex information stored in 2D or 3D images into tabular data. The latter can then be analyzed with classical machine learning algorithms and classical statistics.
Recent projects include:
- Radiomics project in which we predict the character of potentially cancerous lesions detected in CT scans
- Survival analysis to study the effects of a reduced chest x-ray volume on intensive care units
As a clinical data science team working in the field of radiology, we utilize advanced and specialized tools to analyze complex data and address department-specific needs.
Our focus is on utilizing the most recent and innovative methods to answer clinical questions and generate insights from rich, heterogeneous data sources. We develop, deploy and maintain the tools and infrastructure needed for these tasks.
Our recent efforts include:
- Structured acquisition of patient data, used for an exploratory analysis of Covid-19 patients undergoing radiological imaging
- Retrieval and pseudonymization of radiological images from our PACS (Picture Archiving and Communication System) for a large dataset for supervised deep learning
- Monitoring, visualization and evaluation of the imaging activity of the radiology department
Group Leader
Prof. Dr. rer. nat. Michael Ingrisch
Head of Clinical Data Science.
Research Staff
Dr. rer. nat. Balthasar Schachtner
Balthasar received his PhD for his research in the field of experimental particle physics. The focus of his postdoctoral research is the facilitation of machine learning in radiology and the development of imaging biomarkers for lung pathologies.
Dr. rer. nat. Katharina Jeblick, MA phil.
Katharina received her Phd in Physics in the field of computational physics for quantum materials and holds an additional master degree in Philosophy of Science and Technology focussing on ethical and social implications of technology.
Her postdoctoral research scope includes the application and advancement of deep learning for lung imaging to support clinical decision making.
PhD Students
Jakob Dexl, M.Sc.
Jakob has a Master's degree in medical engineering with a focus on image and data processing. Before joining the group, he worked as a research assistant at the Fraunhofer IIS and applied various deep learning approaches to pathological tasks. In his doctoral research, he is developing active learning algorithms for radiology.
Andreas Mittermeier, M.Sc.
Andreas has a master’s degree in physics and was interested in medical imaging since his undergraduate studies. His doctoral research project comprises perfusion imaging analysis in the context of novel machine learning methods.
Theresa Stüber, M.Sc.
Theresa got her master's degree in (bio-)statistics and pursued her great interest for machine learning in medicine already during university studies. In her doctoral research she develops a framework for the combinaton of deep learning with classical statistical modeling.
Johanna Topalis, M.Sc.
Johanna has a Master's degree in physics and specialized in medical physics during her studies. Her doctoral research project concerns the development of AI-based tools to support decision-making in lung cancer screening.
Tobias Weber, M.Sc.
Tobias has a master's degree in computer science with a focus on data analysis and machine learning. His doctoral research project concerns with the practical application of deep learning on large medical data.
Philipp Wesp, M.Sc.
Philipp has a medical physics background and focused primarily on proton computed tomography as a Master student. Today he analyzes CT images using modern machine learning techniques in order to predict valuable clinical endpoints, e.g. the character of potentially malignant lesions.
Master Students
Matthias Bock, B.Sc.
Matthias holds a bachelor’s degree in physics and specializes in medical physics during his master’s studies. His master’s project concerns the analysis and development of robust deep learning-based lung segmentation models and the extraction of quantitative imaging biomarkers based on radiomics.
Marvin Weber, B.Sc.
Marvin has a bachelor's degree in computer science. His master's project focuses on uncertainty quantification in deep learning-based forensic age estimation. Different uncertainty quantification methods are compared to the model test error and standard age assessment methods.
Medical Advisor Radiology
Associated Clinical Researchers
Dr. med. Nicola Fink
Dr. med Jan Rudolph
Boj Hoppe
Dr. med Johannes Rückel, B.Sc.
2022
Jeblick K, Schachtner B, Dexl J, Mittermeier A, Stüber AT, Topalis J, Weber T, Wesp P, Sabel B, Ricke J, Ingrisch M. ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports. arXiv preprint. 2022 Dec;30. doi: 10.48550/arXiv.2212.14882. arxiv: 2212.14882
Gresser E, Schachtner B, Stüber AT, Solyanik O, Schreier A, Huber T, Froelich MF, Magistro G, Kretschmer A, Stief C, Ricke J, Ingrisch M, Nörenberg D. Performance variability of radiomics machine learning models for the detection of clinically significant prostate cancer in heterogeneous MRI datasets. Quant Imaging Med Surg. 2022 Nov;12(11):4990-5003. doi: 10.21037/qims-22-265. PMID: 36330197; PMCID: PMC9622454.
Feuerecker B, Heimer MM, Geyer T, Fabritius MP, Gu S, Schachtner B, Beyer L, Ricke J, Gatidis S, Ingrisch M, Cyran CC. Artificial Intelligence in Oncological Hybrid Imaging. Rofo. 2022 Sep 28. English. doi: 10.1055/a-1909-7013. PMID: 36170852.
Weber T, Ingrisch M, Bischl B, Rügamer D. Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs. MICCAI 2022, Medical Applications with Disentanglement. 2022 Sep;22.
Wesp P, Schachtner B, Grosu S, Mittermeier A, Stueber A, Stadler K, Cyran C, Ricke J, Ingrisch M. Allowing machine learning models to say “I don’t know”: Improving automated clinical decision-making by balancing performance against abstention. ECR 2022. doi: 10.26044/ecr2022/C-14829
Nadjiri J, Schachtner B, Bücker A, Heuser L, Morhard D, Mahnken AH, Hoffmann RT, Berlis A, Katoh M, Reimer P, Ingrisch M, Paprottka PM, Landwehr P. Nationwide Provision of Radiologically-guided Interventional Measures for the Supportive Treatment of Tumor Diseases in Germany - An Analysis of the DeGIR Registry Data. Rofo. 2022 Sep;194(9):993-1002. English, German. doi: 10.1055/a-1735-3615. Epub 2022 Mar 10. PMID: 35272356.
Radosa CG, Nadjiri J, Mahnken AH, Bücker A, Heuser LJ, Morhard D, Landwehr P, Berlis A, Katoh M, Reimer P, Schachtner B, Ingrisch M, Paprottka P, Hoffmann RT. Availability of Interventional Oncology in Germany in the Years 2018 and 2019 - Results from a Nationwide Database (DeGIR Registry Data). Rofo. 2022 Jul;194(7):755-761. English, German. doi: 10.1055/a-1729-0951. Epub 2022 Feb 24. PMID: 35211926.
Mittermeier A, Reidler P, Fabritius MP, Schachtner B, Wesp P, Ertl-Wagner B, Dietrich O, Ricke J, Kellert L, Tiedt S, Kunz WG, Ingrisch M. End-to-End Deep Learning Approach for Perfusion Data: A Proof-of-Concept Study to Classify Core Volume in Stroke CT. Diagnostics. 2022. doi: 10.3390/diagnostics12051142
Matic A, Monnet M, Lorenz JM, Schachtner B, Messerer T. Quantum-classical convolutional neural networks in radiological image classification. arXiv. 2022 Apr. doi: 10.48550/ARXIV.2204.12390
Wesp P, Grosu S, Graser A, Maurus S, Schulz C, Knösel T, Fabritius MP, Schachtner B, Yeh BM, Cyran CC, Ricke J, Kazmierczak PM, Ingrisch M. Deep learning in CT colonography: differentiating premalignant from benign colorectal polyps. European Radiology. 2022 Jan. doi: 10.1007/s00330-021-08532-2
Öcal O, Ingrisch M, Ümütlü MR, Peynircioglu B, Loewe C, van Delden O, Vandecaveye V, Gebauer B, Zech CJ, Sengel C, Bargellini I, Iezzi R, Benito A, Pech M, Malfertheiner P, Ricke J, Seidensticker M. Prognostic value of baseline imaging and clinical features in patients with advanced hepatocellular carcinoma. Br J Cancer. 2022 Feb;126(2):211-218. doi: 10.1038/s41416-021-01577-6. Epub 2021 Oct 22. PMID: 34686780.
2021
Weber T, Ingrisch M, Fabritius M, Bischl B, Rügamer D. Survival-oriented embeddings for improving accessibility to complex data structures. NeurIPS 2021 Bridging the Gap: From Machine Learning Research to Clinical Practice. 2021 Oct 28;abs/2110.11303. DBLP: https://dblp.uni-trier.de/rec/journals/corr/abs-2110-11303.html
Weber T, Ingrisch M, Bischl B, Rügamer D. Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation. NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications. 2021 Oct 19;abs/2110.11312. DBLP: https://dblp.uni-trier.de/rec/journals/corr/abs-2110-11312.html
Fabritius MP, Seidensticker M, Rueckel J, Heinze C, Pech M, Paprottka KJ, Paprottka PM, Topalis J, Bender A, Ricke J, Mittermeier A, Ingrisch M. Bi-Centric Independent Validation of Outcome Prediction after Radioembolization of Primary and Secondary Liver Cancer. Journal of Clinical Medicine. 2021 Aug 19. doi: 10.3390/jcm10163668
Mahnken AH, Nadjiri J, Schachtner B, Bücker A, Heuser LJ, Morhard D, Landwehr P, Hoffmann RT, Berlis A, Katoh M, Reimer P, Ingrisch M, Paprottka P. Availability of interventional-radiological revascularization procedures in Germany - an analysis of the DeGIR Registry Data 2018/19. Rofo. 2021 Aug 4. English, German. doi: 10.1055/a-1535-2774. Epub ahead of print. PMID: 34348401.
Grosu S, Wesp P, Graser A, Maurus S, Schulz C, Knösel T, Cyran CC, Ricke J, Ingrisch M, Kazmierczak PM. Machine Learning-based Differentiation of Benign and Premalignant Colorectal Polyps Detected with CT Colonography in an Asymptomatic Screening Population: A Proof-of-Concept Study. Radiology. 2021 Feb 23;202363. doi: 10.1148/radiol.2021202363. Epub ahead of print. PMID: 33620287.
2020
Scherer J, Nolden M, Kleesiek J, Metzger J, Kades K, Schneider V, Bach M, Sedlaczek O, Bucher AM, Vogl TJ, Grünwald F, Kühn JP, Hoffmann RT, Kotzerke J, Bethge O, Schimmöller L, Antoch G, Müller HW, Daul A, Nikolaou K, la Fougère C, Kunz WG, Ingrisch M, Schachtner B, Ricke J, Bartenstein P, Nensa F, Radbruch A, Umutlu L, Forsting M, Seifert R, Herrmann K, Mayer P, Kauczor HU, Penzkofer T, Hamm B, Brenner W, Kloeckner R, Düber C, Schreckenberger M, Braren R, Kaissis G, Makowski M, Eiber M, Gafita A, Trager R, Weber WA, Neubauer J, Reisert M, Bock M, Bamberg F, Hennig J, Meyer PT, Ruf J, Haberkorn U, Schoenberg SO, Kuder T, Neher P, Floca R, Schlemmer HP, Maier-Hein K. Joint Imaging Platform for Federated Clinical Data Analytics. JCO Clin Cancer Inform. 2020 Nov;4:1027-1038. doi: 10.1200/CCI.20.00045. PMID: 33166197; PMCID: PMC7713526.
Rueckel J, Kunz WG, Hoppe BF, Patzig M, Notohamiprodjo M, Meinel FG, Cyran CC, Ingrisch M, Ricke J, Sabel BO. Artificial Intelligence Algorithm Detecting Lung Infection in Supine Chest Radiographs of Critically Ill Patients With a Diagnostic Accuracy Similar to Board-Certified Radiologists. Crit Care Med. 2020 Jul;48(7):e574-e583. doi: 10.1097/CCM.0000000000004397. PMID: 32433121.
Rueckel J, Trappmann L, Schachtner B, Wesp P, Hoppe BF, Fink N, Ricke J, Dinkel J, Ingrisch M, Sabel BO. Impact of Confounding Thoracic Tubes and Pleural Dehiscence Extent on Artificial Intelligence Pneumothorax Detection in Chest Radiographs. Invest Radiol. 2020 Jul 15. doi: 10.1097/RLI.0000000000000707. Epub ahead of print. PMID: 32694453.
Nadjiri J, Schachtner B, Bücker A, Heuser L, Morhard D, Landwehr P, Mahnken A, Hoffmann RT, Berlis A, Katoh M, Reimer P, Ingrisch M, Paprottka PM. Availability of Transcatheter Vessel Occlusion Performed by Interventional Radiologists to Treat Bleeding in Germany in the Years 2016 and 2017 - An Analysis of the DeGIR Registry Data. Rofo. 2020 Oct;192(10):952-960. English, German. doi: 10.1055/a-1150-8087. Epub 2020 Jul 7. PMID: 32634837.
2019
Mittermeier A, Ertl-Wagner B, Ricke J, Dietrich O, Ingrisch M. Bayesian pharmacokinetic modeling of dynamic contrast-enhanced magnetic resonance imaging: validation and application. Phys Med Biol. 2019 Sep 17;64(18):18NT02. doi: 10.1088/1361-6560/ab3a5a
Fasler DA, Ingrisch M, Nanz D, Weckbach S, Kyburz D, Fischer DR, Guggenberger R, Andreisek G. Rheumatoid cervical pannus: feasibility of volume and perfusion quantification using dynamic contrast enhanced time resolved MRI. Acta Radiol. 2020 Feb;61(2):227-235. doi: 10.1177/0284185119854200. Epub 2019 Jun 6. PMID: 31169411.
Smith EE, Biessels GJ, De Guio F, de Leeuw FE, Duchesne S, Düring M, Frayne R, Ikram MA, Jouvent E, MacIntosh BJ, Thrippleton MJ, Vernooij MW, Adams H, Backes WH, Ballerini L, Black SE, Chen C, Corriveau R, DeCarli C, Greenberg SM, Gurol ME, Ingrisch M, Job D, Lam BYK, Launer LJ, Linn J, McCreary CR, Mok VCT, Pantoni L, Pike GB, Ramirez J, Reijmer YD, Romero JR, Ropele S, Rost NS, Sachdev PS, Scott CJM, Seshadri S, Sharma M, Sourbron S, Steketee RME, Swartz RH, van Oostenbrugge R, van Osch M, van Rooden S, Viswanathan A, Werring D, Dichgans M, Wardlaw JM. Harmonizing brain magnetic resonance imaging methods for vascular contributions to neurodegeneration. Alzheimers Dement (Amst). 2019 Feb 26;11:191-204. doi: 10.1016/j.dadm.2019.01.002. PMID: 30859119; PMCID: PMC6396326.
Debus C, Floca R, Ingrisch M, Kompan I, Maier-Hein K, Abdollahi A, Nolden M. MITK-ModelFit: A generic open-source framework for model fits and their exploration in medical imaging - design, implementation and application on the example of DCE-MRI. BMC Bioinformatics. 2019 Jan 16;20(1):31. doi: 10.1186/s12859-018-2588-1. PMID: 30651067; PMCID: PMC6335810.
Suchorska B, Schüller U, Biczok A, Lenski M, Albert NL, Giese A, Kreth FW, Ertl-Wagner B, Tonn JC, Ingrisch M. Contrast enhancement is a prognostic factor in IDH1/2 mutant, but not in wild-type WHO grade II/III glioma as confirmed by machine learning. Eur J Cancer. 2019
The Clinical Data Science group gratefully acknowledges research funding by:
Bundesministerium für Gesundheit
Deutsches Zentrum für Lungenforschung (DZL)
Siemens Healthineers
RACOON, Netzwerk Universitätsmedizin
Schwerpunktprogramm Radiomics, DFG Deutsche Forschungsgemeinschaft
Research training group GRK 2274 of the DFG, Deutsche Forschungsgemeinschaft
Theses
We can regularly offer projects for Bachelor (3 months) and Master Theses (6 months / 1 year) in the field of Data Science and Machine Learning applied in the context of clinical radiology. Projects are assigned either after applying for a specific project proposal (see below) or upon qualified request. If you would like to join us for a PhD Thesis, please contact Prof. Michael Ingrisch (michael.ingrisch@med.uni-muenchen.de).
If you are curious about our group and wish to learn more about our work, do not hesitate to get in touch with us!
Open Projects
There are no thesis project proposals at the moment.
Working Student Job Offerings
Besides projects targeted at students wo wish to complete a thesis (Bacherlor, Master or PhD), we regularly offer paid working student jobs. These jobs are excellent if you wish to learn more about clinical data science, machine learning in radiology, our to get to know our group.
There are no job offerings at the moment.
Last edited: 23 September 2022
