Skip to main content

Machine learning for brain MRI pre-processing

Primary Investigators:
Ipek Oguz
Brief Description of Project:
A common task for analyzing brain MRIs is to reconstruct the surfaces of the brain from images and compute the thickness of the gray matter tissue, which is an important marker of brain maturation as well as various diseases. Current methods rely on traditional image processing approaches. Recent advances in deep learning suggest that a deep learning approach may outperform these traditional methods. In this project, the goal is to train a deep neural network to potentially replace portions of the current image processing pipeline. I expect this project to lead to a submission to the SPIE Medical Imaging Conference by the end of the summer.

Desired Qualifications:
Nature of Supervision:
I will meet with the student weekly. I have additional meetings as needed (e.g., near conference deadlines, etc). Both me and the other senior lab members (grad students/postdocs) are available for more frequent help as needed. 

A Brief Research Plan (period is for 10 weeks):
1 week - project overview and plan development
6 weeks - project implementation
1 week - statistical evaluation
2 week - project write-up  

Number of Open Slots: 2
Contact Information:
Name: Ipek Oguz
Department: Electrical Engineering & Computer Science