Jeroen van der Laak
15:00-16:15 - session: Artificial intelligence
Jeroen van der Laak is principle investigator and associate professor of computational Pathology at the department of Pathology of the Radboud University Medical Center in Nijmegen, The Netherlands and guest professor at the Center for Medical Image Science and Visualization (CMIV) in Linköping, Sweden. Dr van der Laak holds an MSc in computer science and acquired his PhD from the Radboud University in Nijmegen. His research focuses on the use of deep learning for analysis of digitized histopathological images. He coordinated the CAMELYON grand challenges: worldwide competitions resulting in the first publication showing that deep learning can perform on par with pathologists for specific tasks. The CAMELYON data set is among the largest and most studied in computational Pathology.
Dr van der Laak co-authored over 120 peer-reviewed publications and is member of the editorial boards of Modern Pathology, Laboratory Investigation and the Journal of Pathology Informatics. He is member of the board of directors of the Digital Pathology Association and organizer of sessions at the European Congress of Pathology, MICCAI and the Pathology Visions conference. Dr van der Laak is leading the ‘AI in Pathology’ taskforce of the European Society of Pathology. Dr van der Laak is USCAP Nathan Kaufman laureate 2019.
The remarkable potential of deep learning for histopathology: studies in breast cancer
Deep learning is a state-of-the-art pattern recognition technique that has been found extremely powerful for analysis of digitized histopathological slides. In our research we study different applications of this technique for improved diagnostics and prognostics of breast cancer patients. The most straightforward application is automated assessment of the lymph node status, which may support tumor staging. Current algorithms for this task perform equally well as trained pathologists, making them suitable for large scale routine validation and implementation. We also developed algorithms for fully automated recognition and counting of mitotic figures, which aids breast cancer grading. As a result of these techniques, routine diagnostics becomes more efficient and reproducible. More advanced techniques are developed to identify novel prognostic biomarkers. We study the tumor to stroma ratio, the presence of tumor infiltrating lymphocytes and the appearance of the tumor stroma as possible future prognosticators. Potentially these may aid the development of personalized medicine.
Health-RI Conference 2020Registration website for Health-RI Conference 2020
Health-RI Conference 2020Health-RI Conference 20200.00EUROnlineOnly2019-01-01T00:00:00ZTo be announcedTo be announced