Postdoctoral research fellow at Harvard Medical School - Machine learning for mapping fiber architectures in the brain
We are seeking a talented and driven postdoctoral fellow to develop ML tools for segmenting fibers in histological data or for inferring fiber architectures from diffusion MRI. The position offers the opportunity to collaborate with the Martinos Center’s leading experts in MRI analysis, acquisition, and clinical applications, and to join the vibrant neuroimaging community of Boston.
The fellows will have access to unique datasets that include post mortem diffusion MRI and microscopic-resolution optical imaging in humans or tracer injections in macaques. Potential projects include:
- Algorithms for high-throughput, automated analysis of histological data to build databases of ground-truth fiber bundles and their microstructural properties
- Models trained on the post mortem MRI/optical/histological data that can be used to infer fiber architectures from in vivo diffusion MRI scans
- Tractography algorithms that take advantage of such models to improve mapping of connectional anatomy, ex vivo or in vivo
Strong programming skills, and a Ph.D. in electrical engineering, biomedical engineering, computer science, applied math, or related field are required. Research experience in diffusion MRI (e.g., tractography or microstructural modeling) is an asset but not required. Candidates with a strong background in computer vision/machine learning are encouraged to apply, regardless of prior experience with diffusion MRI. Creativity, initiative, proven ability to publish, and excellent oral and written communication skills are key.
The position is full-time with benefits and available immediately. Salary will be based on qualifications and experience. The Massachusetts General Hospital is an Equal Opportunity/Affirmative Action Employer.
Applicants should submit a curriculum vitae, the contact information of two references, and a cover letter describing their research background, interests, and professional goals by email to Dr. Anastasia Yendiki (ayendiki [at] mgh.harvard.edu).