Please enter the lecture room with the following link:
Precision oncology requires molecular and genetic testing of tumor tissue. For many tests, universal implementation in clinical practice is limited because these biomarkers are costly, require significant expertise and are limited by tissue availability. However, virtually every cancer patient gets a biopsy as part of the diagnostic workup and this tissue is routinely stained with hematoxylin and eosin (H&E). Recently, we and others have demonstrated that deep learning can infer tumor genotype, prognosis and treatment response directly from routine H&E histology images. This talk will summarize the state of the art of deep learning in oncology, demonstrate emerging use cases and discuss the clinical implications of these novel biomarkers.
Jakob Nikolas Kather conducts research in the newly established field of computer-based methods in clinical imaging. The results of his work help further develop the evaluation and interpretation of complex image data, thereby enabling the enhancement diagnosis and treatment in oncology in particular, for example in the prevention of colon cancer. This makes Kather one of the few scientists and physicians able to develop IT solutions that are considered highly recognised contributions in the field of medicine. He acquired the necessary knowledge base for this by taking a master’s degree in medical physics, which he completed alongside his medical studies. The findings of the research group led by Kather at the University Medical Center at RWTH Aachen have been published in high-ranking journals. Since 2019, he has also been a member of the Junges Kolleg (Young Academy) of the North Rhine-Westphalian Academy of Sciences, Humanities and the Arts.