Paramveer Dhillon


I am a Ph.D student in Computer & Information Science. My research interests lie at the intersection of Machine Learning and Brain Imaging. In particular, I am interested in using Spectral Learning techniques e.g. PCA, CCA to better understand the structural and functional brain imaging data.

For details on my work on other aspects of Machine Learning please visit my personal page.


Journal and conference publications

  • [DOI] P. Dhillon, J. C. Gee, L. Ungar, and B. Avants, “Anatomically-Constrained PCA for Image Parcellation,” in Pattern Recognition in Neuroimaging (PRNI), 2013 International Workshop on, 2013, p. 25–28.
    author = {Dhillon, Paramveer and Gee, James C and Ungar, Lyle and Avants, Brian},
    title = {{A}natomically-{C}onstrained {PCA} for {I}mage {P}arcellation},
    booktitle = {{P}attern {R}ecognition in {N}euroimaging {(PRNI)}, 2013 {I}nternational
    {W}orkshop on},
    year = {2013},
    pages = {25--28},
    doi = {10.1109/PRNI.2013.16},
    owner = {paramveerdhillon},
    timestamp = {2014.02.14},
    url = {}
  • [DOI] P. Dhillon, B. Avants, L. Ungar, and J. Gee, “Partial Sparse Canonical Correlation Analysis (PSCCA) for population studies in Medical Imaging,” in Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on, 2012, p. 1132–1135.
    author = {Paramveer Dhillon and Brian Avants and Lyle Ungar and James Gee},
    title = {{P}artial {S}parse {C}anonical {C}orrelation {A}nalysis {(PSCCA)}
    for population studies in {M}edical {I}maging},
    booktitle = {{B}iomedical {I}maging {(ISBI)}, 2012 9th {IEEE} {I}nternational
    {S}ymposium on},
    year = {2012},
    pages = {1132--1135},
    doi = {10.1109/ISBI.2012.6235759},
    timestamp = {2014.02.14},
    url = {}
  • B. Avants, P. Dhillon, B. M. Kandel, P. A. Cook, C. T. McMillan, M. Grossman, and J. C. Gee, “Eigenanatomy improves detection power for longitudinal cortical change.,” Med Image Comput Comput Assist Interv, vol. 15, iss. Pt 3, p. 206–213, 2012.
    author = {Avants, Brian and Dhillon, Paramveer and Kandel, Benjamin M. and
    Cook, Philip A. and McMillan, Corey T. and Grossman, Murray and Gee,
    James C.},
    title = {{E}igenanatomy improves detection power for longitudinal cortical
    journal = {{M}ed {I}mage {C}omput {C}omput {A}ssist {I}nterv},
    year = {2012},
    volume = {15},
    pages = {206--213},
    number = {Pt 3},
    abstract = {We contribute a novel and interpretable dimensionality reduction strategy,
    eigenanatomy, that is tuned for neuroimaging data. The method approximates
    the eigendecomposition of an image set with basis functions (the
    eigenanatomy vectors) that are sparse, unsigned and are anatomically
    clustered. We employ the eigenanatomy vectors as anatomical predictors
    to improve detection power in morphometry. Standard voxel-based morphometry
    (VBM) analyzes imaging data voxel-by-voxel--and follows this with
    cluster-based or voxel-wise multiple comparisons correction methods
    to determine significance. Eigenanatomy reverses the standard order
    of operations by first clustering the voxel data and then using standard
    linear regression in this reduced dimensionality space. As with traditional
    region-of-interest (ROI) analysis, this strategy can greatly improve
    detection power. Our results show that eigenanatomy provides a principled
    objective function that leads to localized, data-driven regions of
    interest. These regions improve our ability to quantify biologically
    plausible rates of cortical change in two distinct forms of neurodegeneration.
    We detail the algorithm and show experimental evidence of its efficacy.},
    institution = {{P}hiladelphia, {PA} 19104, {USA}.},
    keywords = {Aging, physiology; Algorithms; Brain, anatomy /&/ histology/physiology;
    Humans; Image Enhancement, methods; Image Interpretation, Computer-Assisted,
    methods; Information Storage and Retrieval, methods; Longitudinal
    Studies; Magnetic Resonance Imaging, methods; Pattern Recognition,
    Automated, methods; Reproducibility of Results; Sensitivity and Specificity},
    language = {eng},
    medline-pst = {ppublish},
    owner = {pcook},
    pmid = {23286132},
    timestamp = {2013.02.19}