Machine learning
Artificial intelligence (AI) and machine learning are promising innovative approaches for analyzing histology images of tumors due to their ability to recognize intricate patterns and features that might not be easily discernible by human observers. By leveraging these technologies, researchers and clinicians can achieve higher accuracy in tumor identification, classification, and prognosis, leading to more effective and personalized treatment strategies.
Our group is working on AI-based histology image analysis with the focus on identifying different molecular tumor subtypes with clinical implications. Central focus of our current activities is the development and refinement of AI algorithms for diagnostics of Lynch syndrome and prostate cancer.
Together with the Department of General Pathology, Heidelberg University Hospital, our group is part of the Consortial Project Clinic 5.1 coordinated by the Department of Urology, Heidelberg University Hospital. More information on the project is available here.
Prof. Albrecht Stenzinger
Dr. Constantin Schwab
Prof. David Bonekamp
Dr. Magdalena Görtz
Prof. Markus Hohenfellner
Prof. Jakob Nikolas Kather
Engineering Mathematics and Computing Lab (EMCL)
Prof. Dr. Vincent Heuveline, IWR, Heidelberg University
Saskia Haupt, IWR, Heidelberg University
Alexander Zeilmann, IWR, Heidelberg University
https://emcl.iwr.uni-heidelberg.de/research/projects/mathematical-oncology



Colorectal cancer incidences in Lynch syndrome: a comparison of results from the prospective lynch syndrome database and the international mismatch repair consortium. Hered Cancer Clin Pract. 2022 Oct 1;20(1):36. PMID: 36182917
S. Haupt, N. Gleim, A. Ahadova, H. Bläker, M. Knebel Doeberitz, M. Kloor, V. Heuveline: A computational model for investigating the evolution of colonic crypts during Lynch syndrome carcinogenesis. Computational and Systems Oncology, June 2021.
Mathematical modeling of multiple pathways in colorectal carcinogenesis using dynamical systems with Kronecker structure. PLoS Comput Biol. 2021 May 18;17(5):e1008970. PMID: 34003820
The shared frameshift mutation landscape of microsatellite-unstable cancers suggests immunoediting during tumor evolution. Nat Commun. 2020 Sep 21;11(1):4740. PMID: 32958755
Age-dependent performance of BRAF mutation testing in Lynch syndrome diagnostics. Int J Cancer. 2020 Nov 15;147(10):2801-2810. PMID: 32875553
.Involved researchers