MIT CSAIL
32 Vassar Street 32-D470
Cambridge, MA 02139
tel: 617-253-8005
email: polina at csail.mit.edu
Directions to my office
Assistant:
Fern DeOliveira
tel: 617-253-5860
email: fern at csail.mit.edu
|
|
Contact: MIT CSAIL 32 Vassar Street 32-D470 Cambridge, MA 02139 tel: 617-253-8005 email: polina at csail.mit.edu Directions to my office
Assistant:
Fern DeOliveira |
|
Home
Last updated |
Research AreasJoint Modeling of Shape/Anatomy and FunctionOne 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 PapersP. Golland, Y. Golland, R. Malach. Detection of Spatial Activation Patterns As Unsupervised Segmentation of fMRI Data. In Proceedings of MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, 110-118, 2007.B.T.T. Yeo, M.R. Sabuncu, H. Mohlberg, K. Amuntsfferent, K. Zilles, P. Golland, B. Fischl. What Data to Co-register for Computing Atlases. In Proceedings of MMBIA: IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis, 2007. W. Ou, P. Golland. From Spatial Regularization to Anatomical Priors in fMRI Analysis. In Proceedings of IPMI: International Conference on Information Processing and Medical Imaging, LNCS 3565:88-100, 2005. For a complete list of papers, see Publications. 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 PapersD. Lashkari, N. Kanwisher, and P. Golland. Discovering Structure in the Space of Activation Profiles in fMRI. Accepted to MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, 2008.W. Ou, M.S. Hamäläinen, and P. Golland. A Distributed Spatio-Temporal EEG/MEG Inverse Solver. Accepted to NeuroImage, 2008. Y. Golland, P. Golland, S. Bentin, R. Malach. Data-driven clustering reveals a fundamental subdivision of the human cortex into two global systems. Neuropsychologia, 46(2):540-553, 2008. For a complete list of papers, see Publications. Shape/Anatomy Representation and AnalysisThe 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 PapersM.R. Sabuncu, S.K. Balci and P. Golland. Discovering Modes of an Image Population through Mixture Modeling. Accepted to MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, 2008.K. Van Leemput, A. Bakkour, T. Benner, G. Wiggins, L.L. Wald, J. Augustinack, B.C. Dickerson, P. Golland, and B. Fischl. Model-Based Segmentation of Hippocampal Subfields in Ultra-High Resolution In Vivo MRI. Accepted to MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, 2008. B.T.T. Yeo, M.R. Sabuncu, R. Desikan, B. Fischl, P. Golland. Effects of registration regularization and atlas sharpness on segmentation accuracy. Accepted to Medical Image Analysis, 2008. 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, 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. For a complete list of papers, see Publications. Population Analysis of Cell ImagesThe goal of this work is to detect and characterize variability in cell 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.
T. R. Jones, A. E. Carpenter, D. M. Sabatini, P. Golland. Methods for High-Content, High-Throughput Image-Based Cell Screening. In Proceedings of the First MICCAI Workshop on Microscopic Image Analysis with Applications in Biology, 65-72, 2006. T.R. Jones, A. E. Carpenter, and P. Golland. Voronoi-based segmentation of cells on image manifolds. In Proceedings of ICCV Workshop on Computer Vision for Biomedical Image Applications, LNCS 3765:535-543, 2005. For a complete list of papers, see Publications. Visualization of Anatomy and Its VariationVisualization 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.AnatomyBrowser is an interactive tool we created for visualization of anatomical atlases. It integrates images, surface models, anatomical hierarchies and textual information to provide a unified view of the anatomy. Selected PapersP. 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. General Computer VisionI 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 PapersB.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. General Machine LearningWhile my primary interest is in biomedical image analysis, some of my work resulted in general learning methods applicable in a variety of domains.Selected PapersD. Lashkari and P. Golland. Convex Clustering with Exemplar-Based Models. Advances in Neural Information Processing Systems, 20:825-832, 2008.P. Golland, F. Liang, S. Mukherjee, D. Panchenko. Permutation Tests for Classification. In Proceedings of COLT: Annual Conference on Learning Theory, LNCS 3559:501-515, 2005. 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. |
