Thomas J. Fuchs, DSc, is a scientist in the groundbreaking field of Computational Pathology, focused on the use of artificial intelligence to analyze images of tissue samples to identify disease, recommend treatment and predict outcome. In October 2020, he has been appointed Co-Director of the Hasso Plattner Institute for Digital Health at Mount Sinai, Dean of Artificial Intelligence (AI) and Human Health, and Professor of Computational Pathology and Computer Science at the Icahn School of Medicine at Mount Sinai. In this role, he will lead the next generation of scientists and clinicians to use artificial intelligence and machine learning to develop novel diagnostics and treatments for acute and chronic disease. Dr. Fuchs’s work includes developing novel methods for analysis of digital microscopy slides to better understand genetic mutations and their influence on changes in tissues. He has been recognized for developing large-scale systems for mapping the pathology, origins, and progress of cancer. This breakthrough was achieved by building a high-performance compute cluster to train deep neural networks at petabyte scale.
Before joining Mount Sinai, Dr. Fuchs was Director of the Warren Alpert Center for Digital and Computational Pathology at Memorial Sloan Kettering Cancer Center (MSK) and Associate Professor at Weill Cornell Graduate School for Medical Sciences. At MSK he led a laboratory focused on computational pathology and medical machine learning. Dr. Fuchs co-founded Paige.AI in 2017 and led its initial growth to the leading AI company in pathology. He is a former research technologist at NASA’s Jet Propulsion Laboratory and visiting scientist at the California Institute of Technology. Dr. Fuchs holds a Doctor of Sciences from ETH Zurich in Machine Learning and an MS in Technical Mathematics from Graz Technical University in Austria.
Our laboratory focuses on research in the novel field of Computational Pathology. We develop and apply quantitative methods for the analysis of digital microscopy slides and relate the resulting statistical descriptors to patient outcomes.
Computational Pathology - Learning from histopathology images Computational Pathology comprises automated cell and cell nucleus detection, segmentation and staining estimation. Modern random forest models are capable to learn from expert annotated images the differences between various kinds of cancer related outcomes. We collaborate with outstanding institutions in several projects to learn how pathologists understand the images and which apects are important for reliable, repoducible and more objective diagnostics.
Machine Learning - How to learn from petabytes of data? Deep learning experiences a tremendous rise in attention in the machine learning community. The increasing amount of available data allows for the learning of highly accurate patterns with various kinds of neural networks. We explore the potential of deep learning algorithms on histopathologic images for cancer diagnosis and grading, where conventional machine learning methods are usually limited.
Medical Statistics - Find Distinctive Patterns in High Dimensional Expression Profiles Medical statistics and machine learning techniques are incorporated to find distinctive expression profiles in high dimensional genetic or proteomic medical data. Found biomarker candidates are then subject for validation on large patient cohorts.
Computational Radiology and Crohn's Disease - Can we detect and grade CD in MRI automatically? Crohn's disease (CD) is a chronic inflammatory bowel disease, which affects one or more parts of the terminal ileum and/or colon. Longterm monitoring of the disease is necessary for appropriate treatment and also research. Automatic detection and scoring of CD with magnetic resonance imaging would substantially facilate and improve personalized and objective screening