Polina Golland

photo courtesy Allegra Boverman
32 Vassar Street 32-D470
Cambridge, MA 02139
tel: 617-253-8005
email: polina at csail.mit.edu
Directions to my office







Last updated
Aug 15, 2018

Research Areas

Representation and Analysis of Anatomical Variability

The problem of shape representation and modeling of shape variability is central to computer vision. My work focuses on learning the models of shape variability within a population or across different populations, with applications to biomedical problems.
Selected Papers
C. Wachinger, P. Golland, W. Kremen, B. Fischl, and M. Reuter. BrainPrint: A discriminative characterization of brain morphology. NeuroImage, 109:232-248, 2015. PMC4340729

A.V. Dalca, R. Sridharan, L. Cloonan, K.M. Fitzpatrick, A. Kanakis, K.L. Furie, J. Rosand, O. Wu, M. Sabuncu, N.S. Rost, and P. Golland. Segmentation of Cerebrovascular Pathologies in Stroke Patients with Spatial and Shape Priors. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 8674:773-780, 2014. PMC4260817

For a complete list of papers, see Publications.

back to the top

Joint Modeling of Images and Genetics

Imaging provides rich descriptors of anatomy and function. Using such descriptors to improve sensitivity of genetic studies of disease is our current research goal. We mainly focus on developing methods to extract image-based phenotypes associated with genetic variation and clinical phenotypes, as well as building statistical models of joint variation in image-based features and genetic code.
Selected Papers
N.K. Batmanghelich, A.V. Dalca, M.R. Sabuncu, and P. Golland. Joint Modeling of Imaging and Genetics. In Proc. IPMI: International Conference on Information Processing and Medical Imaging, LNCS 7917:766-777, 2013.

For a complete list of papers, see Publications.

back to the top

Joint Modeling of Anatomy and Function

One of my current interests is developing computational methods for modeling the relationship between anatomy and function, particularly in application to neuroimaging. Examples include using anatomical information to improve modeling and detection of functional areas, anatomically-motivated representations of functional co-activation and others.
Selected Papers
A. Venkataraman, M. Kubicki, and P. Golland. From Connectivity Models to Region Labels: Identifying Foci of a Neurological Disorder. IEEE Transactions on Medical Imaging, 32(11):2078-2098, 2013.

A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.

For a complete list of papers, see Publications.

back to the top

Functional Detection and Analysis (fMRI/MEG/EEG)

My work in analysis of brain function focuses on statistical modeling of the activation signals in situations where the traditional parametric models do not necessarily apply. Examples include clustering of fMRI signals to explain the organization of the activity over the entire cortex, joint modeling of activation and anatomical structure, non-parametric tests to estimate statistical significance in multi-variate pattern analysis and others.
Selected Papers
G. Langs, A. Sweet, D. Lashkari, Y. Tie, L. Rigolo, A.J. Golby, and P. Golland. Decoupling function and anatomy in atlases of functional connectivity patterns: Language mapping in tumor patients. NeuroImage, 103:462-475, 2014. PMC4401430

E. Vul, D. Lashkari, P.-J. Hsieh, P. Golland, and N.G. Kanwisher. Data-driven functional clustering reveals dominance of face, place, and body selectivity in the ventral visual pathway. Journal of Neurophysiology, 108:2306-2322, 2012.

D. Lashkari, R. Sridharan, E. Vul, P.-J. Hsieh, N.G. Kanwisher, and P. Golland. Search for Patterns of Functional Specificity in the Brain: A Nonparametric Hierarchical Bayesian Model for Group fMRI Data. NeuroImage, 59(2):1348-1368, 2012.

For a complete list of papers, see Publications.

back to the top

Microscopy Image Analysis

The goal of this work is to detect and characterize variability in cell and other organism appearance in high throughput genetic experiments from microscopy images. Detecting genes that significantly affect the cellular phenotype can serve as a guide in functional mapping of previously uncharacterized genes.

CellProfiler is an open source image analysis platform we created in this project. It includes functions for illumination correction, cell segmentation and measurement, statistical analysis of variability in cell phenotypes, and visualization.

Also, see Ray Jones' PhD Thesis.

Selected Papers
C. Wahlby, L. Kamentsky, Z.H. Liu, T. Riklin-Raviv, A.L. Conery, E.J. O'Rourke, K.L. Sokolnicki O. Visvikis, V. Ljosa, J.E. Irazoqui, P. Golland, G. Ruvkun, F.M. Ausubel and A.E. Carpenter. An Image Analysis Toolbox for High-throughput C. Elegans Assays. Nature Methods, 9:714-718, 2012.

T.R. Jones, A.E. Carpenter, M.R. Lamprecht, J. Moffat, S.J. Silver, J.K. Grenier, A.B. Castoreno, U.S. Eggert, D.E. Root, P. Golland, and D.M. Sabatini. Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning. PNAS, A 106(6):1826-1831, 2009.

A.E. Carpenter, T.R. Jones, M.R. Lamprecht, C. Clarke, I.H. Kang, O. Friman, D.A. Guertin, J.H. Chang, R.A. Lindquist, J. Moffat, P. Golland and D.M. Sabatini. CellProfiler: image analysis software for identifying and quantifying cell phenotypes. Genome Biology 7(10):R100, 2006.

For a complete list of papers, see Publications.

back to the top

Visualization of Anatomy and Its Variation

Visualization of the individual anatomy and variability of anatomical shape within and across populations relates anatomical information to other sources of data available on the relevant structures. My work in this area includes building tools for visualizing anatomy and developing analysis methods for extracting explicit representations of shape variability from the statistical models trained on shape examples.

Selected Papers
A.V. Dalca, R. Sridharan, N. Rost, and P. Golland. tipiX: Rapid Visualization of Large Image Collections. In Proc. MICCAI Workshop on Interactive Medical Image Computing, 2014.

P. Golland, W.E.L. Grimson, M.E. Shenton, R. Kikinis. Detection and Analysis of Statistical Differences in Anatomical Shape. Medical Image Analysis, 9(1):69-86, 2005.

P. Golland, R. Kikinis, M. Halle, C. Umans, W.E.L. Grimson, M.E. Shenton, J.A. Richolt. AnatomyBrowser: A Novel Approach to Visualization and Integration of Medical Information. Journal of Computer Assisted Surgery, 4:129-143, 1999.

For a complete list of papers, see Publications.

back to the top

General Computer Vision

I have done research in several areas of general computer vision, including motion estimation, stereo reconstruction, color and shape representation. I am still interested in general topics of object representation and estimation from images, but my primary focus has shifted to modeling biological phenomena.
Selected Papers
B.T.T. Yeo, W. Ou and P. Golland. On the Construction of Invertible Filter Banks on the 2-Sphere. IEEE Transactions on Image Processing, 17(3):283-300, 2008.

P. Golland and W.E.L. Grimson. Fixed Topology Skeletons. In Proceedings of CVPR: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 10-17, 2000.

R. Szeliski and P. Golland. Stereo Matching with Transparency and Matting. International Journal of Computer Vision, 32(1):45-61, 1999.

P. Golland and A.M. Bruckstein. Motion from Color. CVIU: Computer Vision and Image Understanding, 68(3):346-362, 1997.

P. Golland and A.M. Bruckstein. Why RGB? Or How to Design Color Displays for Martians. GMIP: Graphical Models and Image Processing, 58(5):405-412, 1996.

For a complete list of papers, see Publications.

back to the top

General Machine Learning

While my primary interest is in biomedical image analysis, some of my work resulted in general learning methods applicable in a variety of domains.
Selected Papers
D. Lashkari and P. Golland. Co-Clustering with Generative Models. MIT CSAIL Technical Report, MIT-CSAIL-TR-2009-054, 2009.

D. Lashkari and P. Golland. Convex Clustering with Exemplar-Based Models. Advances in Neural Information Processing Systems, 20:825-832, 2008.

P. Golland. Discriminative Direction for Kernel Classifiers. Proceedings of NIPS: Advances in Neural Information Processing Systems 14, 745-752, 2002.

For a complete list of papers, see Publications.

back to the top