Postdoctoral fellows
Lead methods development and translation across imaging, genomics, and radiotherapy modeling.
Join / Collaborate
Mentoring and training talented researchers is an explicit goal of the lab — not an afterthought. We are recruiting, and we welcome collaborations.
Opportunities
We welcome postdoctoral fellows, graduate students, and clinical fellows with backgrounds in mathematics, physics, computer science, engineering, statistics, or medicine. Trainees work at the interface of mathematics and medicine, with access to world-class imaging, genomic, and clinical data and to collaborators across MSK and Weill Cornell Medicine. We are especially interested in people excited by optimal transport and geometric methods, radiobiological modeling and digital twins, imaging AI, and treatment-planning optimization.
Lead methods development and translation across imaging, genomics, and radiotherapy modeling.
Rotations and thesis projects at the interface of applied mathematics and cancer medicine.
Physicians and physicists bringing clinical questions to quantitative modeling.
Collaboration
We actively seek research collaborations — including data-sharing and methods collaborations through consortia such as the VALIDATE effort on toxicity-model validation and the ROBIN U54 center on radiation and immune response. If your group has imaging, genomic, pathology, or outcomes data and a question that quantitative modeling could help answer, we'd like to hear from you.
Teaching
Prospective students may be interested in the M.S. in Biomedical Imaging offered through the Weill Cornell Medicine Graduate School of Medical Sciences and managed jointly by Weill Cornell and MSK — an interdisciplinary program with Laboratory and Clinical tracks and coursework in imaging physics, machine learning, and imaging modalities. Dr. Deasy leads the course "Machine Learning on Images."
Contact
Department of Medical Physics
Memorial Sloan Kettering Cancer Center
New York, NY
Email: deasyj@mskcc.org
ORCID: 0000-0002-9437-266X
Software: github.com/cerr/CERR