Significant anatomy detection through sparse classification: a comparative study

dc.contributor.authorZhang, Li
dc.contributor.authorCobzas, Dana
dc.contributor.authorWilman, Alan H.
dc.contributor.authorKong, Linglong
dc.date.accessioned2020-10-05
dc.date.accessioned2022-05-31T01:15:23Z
dc.date.available2022-05-31T01:15:23Z
dc.date.issued2018
dc.description.abstractWe present a comparative study for discriminative anatomy detection in high dimensional neuroimaging data. While most studies solve this problem using mass univariate approaches, recent works show better accuracy and variable selection using a sparse classification model. Two types of image-based regularization methods have been proposed in the literature based on either a Graph Net (GN) model or a total variation (TV) model. These studies showed increased classification accuracy and interpretability of results when using image-based regularization, but did not look at the accuracy and quality of the recovered significant regions. In this paper, we theoretically prove bounds on the recovered sparse coefficients and the corresponding selected image regions in four models (two based on GN penalty and two based on TV penalty). Practically, we confirm the theoretical findings by measuring the accuracy of selected regions compared with ground truth on simulated data. We also evaluate the stability of recovered regions over cross-validation folds using real MRI data. Our findings show that the TV penalty is superior to the GN model. In addition, we showed that adding an l2 penalty improves the accuracy of estimated coefficients and selected significant regions for the both types of models.
dc.description.urihttps://library.macewan.ca/full-record/edseee/edseee.8000400
dc.identifierhttps://doi.org/10.1109/TMI.2017.2735239
dc.identifier.citationZhang L, Cobzas D, Wilman AH, Kong L. , Significant Anatomy Detection Through Sparse Classification: A Comparative Study. , IEEE Trans Med Imaging. 2018 Jan;37(1):128-137
dc.identifier.urihttps://hdl.handle.net/20.500.14078/1751
dc.languageEnglish
dc.language.isoen
dc.rightsAll Rights Reserved
dc.subjectsparse classification
dc.subjectlogistic regression
dc.subjectvoxel based analysis
dc.subjectlocalized statistics
dc.subjectMRI
dc.subjectl₁ optimization
dc.titleSignificant anatomy detection through sparse classification: a comparative study
dc.typeArticle
dspace.entity.type
Files