The Pathology Departmentat MSK is seeking an outstanding faculty candidate at the level of Associate or full Member to fill a position dedicated to digital and computational pathology research. Expertise in the areas of machine learning, computer vision applied to digital image analysis or direct-from-tissue microscopic imaging technologies is required, and prior exposure to the analysis of medical images, particularly digital pathology images, is preferred. Applicants must have a PhD, MD or equivalent degree. The ability to conduct independent research is required and a history of obtaining competitive grant funding is desirable. Led by Dr. David Klimstra,the Pathology Departmentat MSK is one of the largest clinical practices in the United States dedicated to the diagnosis of cancer. The department employs over 100 pathologists supported by a dedicated team of over 600 allied health staff and state of the art laboratory infrastructure including surgical pathology, immunohistochemistry, cytology, hematopathology, flow cytometry, proteomics, cytogenetics and molecular pathology laboratories.
The Department has made a significant investment in digital pathology, with routine scanning of diagnostic slides both prospectively and from the archives of 25 million slides. There is a wealth of image data with accompanying clinical and genomic annotation, allowing for highly impactful research in computational pathology and advanced imaging technologies. The Department has committed to exploring novel technologies for the analysis of pathology specimens and supports a wide range of research using machine learning and computationally assisted imaging platforms. Collaborations are available with members of the diagnostic pathology faculty and with computational faculty within the Department and other institutional programs (Computational Biology, Computational Oncology, Medical Physics, Radiology, etc.). Joint appointment in one or more of these collaborating programs is possible. Opportunities exist to conduct highly impactful research that will influence the practice of pathology and improve patient care as novel technologies pervade the discipline.
The Warren Alpert Center for Digital and Computational Pathology (WAC) was established in 2017, with a generous support from The Warren Alpert Foundation. Since the inception of the WAC, the Department of Pathology at MSKCC has assumed a leadership role in digital pathology, technology development, computational innovation, and the operational integration of digital pathology into clinical practice. Through the WAC, we have established an infrastructure for deep learning, which includes a high-performance compute cluster; custom-developed, scanner-agnostic digital slide viewer software; and development of the Honest Broker for Bioinformatics Technology (HoBBIT) database and application, allowing for the management of our growing archive of pathology images and associated data by enabling queries, de-identification for research, and the transfer of digital images and data for user review.
We are seeking candidates to develop novel research programs to drive translational computational methods in Pathology, serving as a liaison between Pathology faculty and Computational Oncology, Clinical Bioinformatics, Medical Physics, and Radiology informatics. The candidate will plan and execute research projects with a focus on precision pathology and cancer care. In addition to conducting primary and collaborative research, the faculty member will have educational responsibilities for medical and graduate students, post-doctoral students, and fellows. Faculty will be eligible to hold appointments in the Gerstner Sloan Kettering Graduate School of Biomedical Sciences, the Weill Cornell Medical College (WCMC) Graduate School and/or the Tri-Institutional Computational Biology for Medicine program across MSK and WCMC, providing access to exceptional graduate students.
MSK offers competitive compensation package with exceptional benefits based on experience and accomplishments.
In this role, you will:
The ideal candidate should: