We create an AI based software suite for histopathological diagnostics.
Microscopic evaluation of tissue samples performed by pathologists is the basis of diagnosing cancer as well as many degenerative, infectious and inflammatory diseases. Given our ageing population, the increase in numbers and complexity of cancer cases worldwide, a global shortage of pathologists is imminent. As a result, the capacity of healthcare systems to perform histological diagnostics and determine the right therapy is under increasing pressure. To address this challenge, team AIgnostics has developed an AI-based image analysis system to assist pathologists in standardised and quantitative automated tissue diagnostics. This solution promises to be more accurate and faster than today’s manual gold standard. The system can also be applied to drug development, where pharmaceutical companies depend on accurate assessments of histological tissue samples in preclinical animal studies or in clinical trials to stratify patients in drug efficacy and toxicity analyses.
In the future, AI will seamlessly integrate into the diagnostic workflow by providing the pathologist with real-time augmented reality information on quantitative properties rendering diagnostics faster, more accurate, quantitative and reliable. This will guide precision therapies and increase patient safety.
The Future of Pathology
Pathologists are rare experts who have developed an elaborate system of identifying subtle changes in tissue morphology and diagnose diseases over the last 100 and more years. However, high demands of precision medicine lead to an increasing complexity of cases which requires more and more quantitative evaluation of tissue features for patient stratification. This calls for novel diagnostic support tools.
We developed an AI based histological image analysis system as a diagnostics support tool that overcomes "black-box" limitations of conventional AI and renders diagnostic results explainable in form of heatmaps, thus allowing pathologists to check computational results for plausibility and integrate them into diagnostic reports.
This technique can be used to detect tumors and count tumor-infiltrating lymphocytes, but can be flexibly applied to basically any other diagnostic question.
We are looking for partners to further develop and take our approach to clinical practice.
Prof. Dr. Frederick Klauschen
Prof. Dr. Klaus-Robert Müller
Prof. Dr. Alexander Binder
Dr. Bruno Sinn
Dr. Alexander Arnold
M. Sc. Ann-Kathrin Dombrowski
Dr. Stephan Wienert
Senior Software Engineer
We are an interdisciplinary team of AI scientists, digital pathologists, surgical pathologists and software engineers dedicated to taking explainable AI to pathological routine diagnostics.