Pre-Doctoral Fellow

Mass General Brigham•Boston, MA

13d•$37,440 - $68,640•Onsite

About The Position

The Brigham Health Artificial Intelligence in Medicine (AIM) program and Harvard Medical School in Boston, MA is seeking a pre-doctoral researcher. Applicants with an interest in the application of computational techniques to medical imaging and at least 1-2 years of experience in Deep Learning and Artificial Intelligence are encouraged to apply. This is a 3-4 year position. The work conducted by the researcher will be in the area of applied Artificial Intelligence/ Deep Learning to develop automated segmentation and planning algorithms for radiation therapy and implementation of existing algorithms into the clinic. Additional work will include imaging-based risk prediction and response assessment tools in cancer including application of deep learning methods to tumor phenotype on serial medical imaging, patient photographs (e.g. facial health recognition algorithms) and patient-specific characteristics such as identifying imaging phenotype of co-morbid illnesses (e.g. lung and cardiac disease) and treatment side effects. Additional projects include application of vision-language models and LLMs to synthesize data from the electronic medical record. The applicant will join the team at the Mass General Brigham AIM program led by Dr. Hugo Aerts and a group of clinical-translational oncologists led by Dr. Raymond Mak in the Department of Radiation Oncology, and is expected to conduct research leading to peer-reviewed publications and presentations at international meetings with guidance from our faculty. Under the supervision of the Principal Investigator, independently carries out and designs highly sophisticated and independent experiments. The candidate will be enrolled through our lab in the Maastricht University PhD program and is expected to complete and defend their PhD thesis at the completion of their fellowship. The Fellow works under the supervision of a Faculty Mentor in the institution, and is allowed to and encouraged to publish the results of his or her research or scholarship and receive credit for such during the appointment period. The Fellow will receive training, professional development and mentorship during the appointment period. The appointment is time limited, and should be for a term of no longer than 3 years. The Fellow will work in a laboratory space dedicated to a Principal Investigator with additional potential to establish successful project-specific collaborations in a variety-of directions.

Requirements

Interest in the application of computational techniques to medical imaging
At least 1-2 years of experience in Deep Learning and Artificial Intelligence
Doctoral degree in Data Sciences, Computer Science, Physics or related field
Experience with Artificial Intelligence/Deep Learning techniques and analyses
Track record of scholarship in these fields
Strong data science/computer science background with skills and experience in deep learning
Strong research design and analytical skills
Strong database statistical skills
In-depth knowledge of field of research
Excellent time management/organizational skills
Strong written and verbal presentation skills

Responsibilities

Develop AI methods specific for clinical tasks including but not limited to oncology and oncologic imaging.
Participate in research and development projects under supervision and direction of Raymond Mak, MD (Director, Clinical Innovation for Radiation Oncology) and Hugo Aerts, PhD (Director, AIM).
Develop analysis plans for the defined projects with support from the scientists within AIM.
Evaluate the performance of AI technologies in independent validation cohorts.
Present results at national and international conferences.
Publish results in peer-reviewed manuscripts.
Independently carries out and designs highly sophisticated and independent experiments.
Complete and defend their PhD thesis at the completion of their fellowship.
Publish the results of his or her research or scholarship and receive credit for such during the appointment period.