Polina Golland received her BSc and Masters in Computer Science from Technion, Israel in 1993 and 1995, and a PhD in Electrical Engineering and Computer Science from MIT in 2001. Then in 2003, Golland joined MIT as a professor in the EECS Department and a principal investigator in the Computer Science and Artificial Intelligence Laboratory (CSAIL). Golland’s current research focuses on developing statistical analysis methods for characterization of biological processes based on image information. Some of her awards include: a Faculty Research Innovation Fellowship (2015), Electrical and Computer Engineering Department Heads Association Diversity Award (2014), Medical Image Computing and Computer Assisted Intervention Society: Young Investigator Award (2007,2010,2011).
Industry Impact
The goal is to build computational models of anatomical and functional variability from medical images and develop methods for making predictions for new subjects based on images and prior information. We collaborate extensively with practicing clinicians, clinical researchers and neuroscientists to apply these methods in surgical planning and navigation, population studies and basic neuroscience.
Recent Works
Clincial Neuroimaging
This project focuses on building statistical models of brain anatomical and functional structures from large collections of neuroimages. The approach is to integrate image-derived phenotypes with genetic and clinical indicators. The results of the algorithms provide descriptors of normal anatomy and physiology, disease effects on the brain, and predictions of disease trajectory and recovery.
Cardiac MRI Analysis
The aim of this study is to develop computer vision and machine learning methods for segmentation and interpretation of cardiac MRI in patients with congenital heart disease (CHD), to support simulation and surgical planning. For example, the resulting heart surface models can be a 3D-print to visualize each patient’s individual cardiac anatomy or be used for dynamic functional analysis of the cardiac cycle. The goal is to focus on overcoming challenges of dramatic anatomical variability on the heart in CHD patients.
Monitoring Fetal Health
This research develops algorithms to enable tracking and segmentation of the fetus and placenta in dynamic MRI series. Signal inhomogeneity correction and subsequent analysis of the MRI signal provides measures of placental function and fetal development, which promises to yield novel biomarkers of fetal health for monitoring during pregnancy.