Overview

*Applications will be reviewed on a rolling-basis.

A research opportunity is currently available with the Center for Devices and Radiological Health, Division of Imaging, Diagnostics, and Software Reliability, U.S. Food and Drug Administration (FDA), located in Silver Spring, Maryland.

The participant will learn skills and gain experiences in research on development of assessment methods and tools for AI/ML algorithms applied to digital pathology image analysis. Specifically, the research project involves assessment of the robustness of AI/ML models across whole slide image (WSI) scanners in the task of predicting response to hormonal treatment of women with endometrial hyperplasia.

The learning objectives include (1) color normalization methods for reducing color variations of WSI images (2) assessment of color normalization methods with color fidelity metrics, and (3) assessment of impact of color normalization methods on AI/ML models.

Anticipated Appointment Start Date: 2022; start date is flexible

This program, administered by ORAU through its contract with the U.S. Department of Energy to manage the Oak Ridge Institute for Science and Education, was established through an interagency agreement between DOE and FDA. The initial appointment is for one year but may be renewed upon recommendation of FDA contingent on the availability of funds. The participant will receive a monthly stipend commensurate with educational level and experience. Proof of health insurance is required for participation in this program. The appointment is full-time at FDA in the Silver Spring, Maryland area. Participants do not become employees of FDA, DOE or the program administrator, and there are no employment-related benefits.

Completion of a successful background investigation by the Office of Personnel Management is required for an applicant to be on-boarded at FDA. OPM can complete a background investigation only for individuals, including non-US Citizens, who have resided in the US for a total of three of the past five years.

FDA requires ORISE participants to read and sign their FDA Education and Training Agreement within 30 days of his/her start date, setting forth the conditions and expectations for his/her educational appointment at the agency. This agreement covers such topics as the following:

Non-employee nature of the ORISE appointment
Prohibition on ORISE Fellows performing inherently governmental functions
Obligation of ORISE Fellows to convey all necessary rights to the FDA regarding intellectual property conceived or first reduced to practice during their fellowship
The fact that research materials and laboratory notebooks are the property of the FDA
ORISE fellow’s obligation to protect and not to further disclose or use non-public information

Qualifications

The qualified candidate should have received a doctoral degree in one of the relevant fields (e.g., Biomedical Engineering, Computer Science) with research experience in artificial intelligence and digital pathology whole slide image analysis. Degree must have been received within the past five years.

Candidates with research experience in artificial intelligence and digital pathology whole slide image analysis are encouraged to apply.

Preferred skills:

Python programming
Pathology whole slide image analysis
Machine learning, especially generative adversarial networks
Oral presentations and writing research papers