Posts
Our lab is moving to Dresden
Exciting news - our research group is moving from Aachen to Dresden, Germany! At Technical University (TU) in Dresden, we will be part of the Else Kroener Fresenius Center for Digital Health (EKFZ). EKFZ is a joint cross-faculty initiative at the TU Dresden.
Our vision at EKFZ is to do research that goes beyond the medical disciplines and collaboration in everyday care – physicians learn programming and researchers from computer science or technical subjects learn in return to identify and solve relevant problems in the clinic.
Posts
Towards targeted treatment of cancer with Artificial Intelligence
In a recent article published in the research magazine of University Hospital Aachen (AC-forscht), the mission of our group was described in detail:
Digitization and artificial intelligence are a topic of the future - also and especially in medicine. They have the potential to revolutionize healthcare, make diagnoses more precise and therapies better. Computer-based methods could in the future contribute to improved therapy management for patients with cancer. The young doctor and scientist Jun.
Posts
Survey on AI applications in pathology
The use of Artificial Intelligence (AI) in digital pathology is steadily increasing. Since 2016, our team and many other groups have built an ecosystem of AI tools with potential clinical applicability. In addition to clinical implementation of these existing tools, we are actively shaping future applications of AI in histopathology - but which are the most relevant research questions? Which are the most promising and interesting approaches? What should we as a research community focus on in the next years?
Posts
Our research featured in the news
Four female and six male researchers have received the Heinz Maier-Leibnitz Prize this year, the top award for early career investigators in Germany. This was the result of a decision made by a selection committee appointed by the DFG and the Federal Ministry of Education and Research (BMBF). The prizes are each worth €20,000 and were handed over at a virtual event on 4 May. Jakob Nikolas Kather was one of the awardees in 2021: He conducts research in the newly established field of computer-based methods in clinical imaging.
Posts
How to develop AI biomarkers for the clinic
In a recent comment article published in Nature Reviews Gastroenterology and Hepatology, we describe how interdisciplinary research can result in clinically useful artificial intelligence (AI) systems:
Deep learning can mine clinically useful information from histology. In gastrointestinal and liver cancer, such algorithms can predict survival and molecular alterations. Once pathology workflows are widely digitized, these methods could be used as inexpensive biomarkers. However, clinical translation requires training interdisciplinary researchers in both programming and clinical applications.
Posts
New job opportunity in our group
Please note that this particular job offer has expired. However, we are always open to applications at any level - please reach out by email or on Twitter to learn more.
Original post:
We are looking for a new member of our group - this is a copy of the official job opening: The Clinic for Gastroenterology, Metabolic Diseases and Internal Intensive Care Medicine of RWTH Aachen University is looking for a Scientist, PostDoc or PhD level (m/w/d) for Artificial Intelligence (AI) The position is initially limited to one year with an option of extension.
Posts
Our research featured in the news
Our research was featured on the news portal of RWTH Aachen University hospital (German only): Mittels künstlicher Intelligenz (Deep Learning) soll Krebs besser und zielgerichteter behandelt werden können: Daran forscht ein Team rund um Dr. med. Jakob Nikolas Kather (r.), Arzt und Wissenschaftler in unserer Klinik für Gastroenterologie, Stoffwechselerkrankungen und Internistische Intensivmedizin (Med. Klinik III). 💻👨⚕️ Für seine kürzlich im renommierten Wissenschaftsmagazin „Nature Medicine“ veröffentlichte Studie hat Dr. Kather den diesjährigen Theodor-Frerichs-Preis der Deutschen Gesellschaft für Innere Medizin (DGIM) erhalten.
Posts
Large international consortium for deep learning-based genotyping of colorectal cancer: MSIDETECT
Recently, we have founded an international consortium MSIDETECT. Together with multiple project partners in and beyond Europe, we are aiming to perform a large multicenter validation of deep learning based methods to detect microsatellite instability (MSI) in colorectal cancer directly from routine histological images. Stay tuned for publications from our consortium and find more information on the consortium partners at http://www.msidetect.eu. If you would like to join our consortium, please get in touch!
Posts
New publication: Pan-cancer image-based detection of clinically actionable genetic alterations
Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular biology assays. These tests can be a bottleneck in oncology workflows because of high turnaround time, tissue usage and costs. Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures directly from routine histological images of tumor tissue. We developed and systematically optimized a one-stop-shop workflow and applied it to more than 4000 patients with breast, colon and rectal, head and neck, lung, pancreatic, prostate cancer, melanoma and gastric cancer.
Posts
New preprint: Deep learning detects virus presence in cancer histology
Oncogenic viruses like human papilloma virus (HPV) or Epstein Barr virus (EBV) are a major cause of human cancer. Viral oncogenesis has a direct impact on treatment decisions because virus-associated tumors can demand a lower intensity of chemotherapy and radiation or can be more susceptible to immune check-point inhibition. However, molecular tests for HPV and EBV are not ubiquitously available.
We hypothesized that the histopathological features of virus-driven and non-virus driven cancers are sufficiently different to be detectable by artificial intelligence (AI) through deep learning-based analysis of images from routine hematoxylin and eosin (HE) stained slides.