More information
Portrait Jakob Nikolas Kather

We are the research group Clinical Artificial Intelligence: a young, diverse, and interdisciplinary group of scientists. We use computational methods to extract actionable knowledge from clinical routine data. Our main tools are Artificial Intelligence and Computational Modeling. We combine these tools with a clinical perspective on health and disease. Our main area of expertise is precision oncology of solid tumors, including immunotherapy. We are global thought leaders in the area of predicting clinically actionable properties of tumors directly from routinely available histopathology slides.

The amount of routinely available data in oncology is massively increasing. Currently, we are not using this data for clinical decision making. At the same time, in data science, we are witnessing an exponential increase of state-of-the-art deep learning (DL), especially self-supervised models, transformers and generative models. In just five years, these algorithms have massively pushed the boundary of what was technically feasible to completely new levels. However, as the fields of medicine and data science evolve faster and faster, they are becoming increasingly disconnected. Without structured efforts, it is hard to keep up to date in both fields. Our lab’s mission is to build an interdisciplinary space in which young biologists, medical doctors and computer scientists collaborate and co-develop ideas and methods for improved clinical decision making in cancer.

Future Projects and Goals

Developing multi-modal Artificial Intelligence systems for new biomarkers in precision oncology. We focus on histopathology and radiology image data and routinely integrate it with other data types, e.g. genomic data. We are also actively using new technologies in non-medical fields and using them to solve unsolved medical research questions.

Methodological and Technical Expertise

  • Computer Vision
  • Computational Pathology
  • Machine Learning
  • Artificial Intelligence
  • Radiomics

CV

since 2022
Full Professorship (W3) for “Clinical Artificial Intelligence” at Technical University of Dresden, Germany

2021–2022
Junior (Assistant) Professorship (W1 with tenure track to W2) at the Medical Faculty of RWTH University Aachen, Germany

since 2021
Visiting Associate Professor in the School of Medicine, Leeds Institute of Medical Research at St James’s, University of Leeds, United Kingdom

since 2020
Additional affiliation as a Research Scientist at the National Center of Tumor Diseases (NCT), Heidelberg, Germany

2019–2022
Research Group Leader “Computational Oncology” at University Hospital RWTH Aachen, Aachen, Germany

2016–2018
Postdoctoral Researcher, German Cancer Research Center (DKFZ, “Applied Tumor Immunity”, PI: Prof. Dr. Dirk Jaeger)

2013–2016
Doctoral Thesis, „Vascular Biology and Tumor Angiogenesis“, German Cancer Research Center (DKFZ), Heidelberg

More Information

www.kather.ai

Selected Publications

Saldanha OL, Quirke P, West NP, … Kather JN
Swarm learning for decentralized artificial intelligence in cancer histopathology
Nature Medicine 28, 1232–1239 (2022)

Kather JN, Heij LR, Grabsch HI, … Luedde T
Pan-cancer image-based detection of clinically actionable genetic alterations
Nature Cancer 1, 789–799 (2020)

Echle A, Grabsch HI, Quirke P, … Kather JN
Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning
Gastroenterology 159:1406–1416 (2020)

Kather JN, Calderaro J
Development of AI-based pathology biomarkers in gastrointestinal and liver cancer
Nat Rev Gastroenterol Hepatol 17, 591–592 (2020)

Kather JN, Pearson AT, Halama N, … Luedde T
Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer
Nature Medicine 25, 1054–1056 (2019)

Contact

Else Kröner Fresenius Center for Digital Health
Faculty of Medicine and Faculty of Computer Science
Technical University Dresden
Fetscherstraße 74, 01062 Dresden, Germany