December 2023
·
1 Read
·
1 Citation
What is this page?
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
Publications (4)
January 2021
·
15 Reads
Sparse inverse covariance estimation (i.e., edge de-tection) is an important research problem in recent years, wherethe goal is to discover the direct connections between a set ofnodes in a networked system based upon the observed nodeactivities. Existing works mainly focus on unimodal distributions,where it is usually assumed that the observed activities aregenerated from asingleGaussian distribution (i.e., one graph).However, this assumption is too strong for many real-worldapplications. In many real-world applications (e.g., brain net-works), the node activities usually exhibit much more complexpatterns that are difficult to be captured by one single Gaussiandistribution. In this work, we are inspired by Latent DirichletAllocation (LDA) [4] and consider modeling the edge detectionproblem as estimating a mixture ofmultipleGaussian distribu-tions, where each corresponds to a separate sub-network. Toaddress this problem, we propose a novel model called GaussianMixture Graphical Lasso (MGL). It learns the proportionsof signals generated by each mixture component and theirparameters iteratively via an EM framework. To obtain moreinterpretable networks, MGL imposes a special regularization,called Mutual Exclusivity Regularization (MER), to minimize theoverlap between different sub-networks. MER also addresses thecommon issues in read-world data sets,i.e., noisy observationsand small sample size. Through the extensive experiments onsynthetic and real brain data sets, the results demonstrate thatMGL can effectively discover multiple connectivity structuresfrom the observed node activities
December 2020
·
8 Reads
·
6 Citations
January 2020
·
21 Reads
·
4 Citations
Citations (3)
... In the literature, related tasks in brain imaging analysis have been extensively studied. Conventional methods primarily focus on designing methods for brain extraction (Kleesiek et al. 2016;Lucena et al. 2019), registration (Sokooti et al. 2017;Su et al. 2022a), segmentation (Akkus et al. 2017;Kamnitsas et al. 2017;Chen et al. 2018), parcellation (Thyreau and Taki 2020;Lim et al. 2022Lim et al. ), network generation (Škoch et al. 2022Yin et al. 2023) and classification Kawahara et al. 2017;Kan et al. 2022b) separately under supervised settings. However, in brain imaging studies, the collection of voxel-level annotations, transformations between images, and task-specific brain networks often prove to be expensive, as it demands extensive expertise, effort, and time to produce accurate labels, especially for high-dimensional neuroimaging data, e.g., 3D MRI. ...
- Citing Conference Paper
December 2023
... Brain extraction (a.k.a. skull stripping), registration and segmentation serve as preliminary yet indispensable steps in many neuroimaging studies, such as anatomical and functional analysis [4,33,50,52], brain networks discovering [11,24,27,28,53,54], multi-modality fusion [6,26], diagnostic assistance [18,46], and brain region studies [8,25]. The brain extraction targets the removal of non-cerebral tissues (e.g., skull, dura, and scalp) from a patient's head scan; the registration step aims to align the extracted brain with a standard brain template; the segmentation step intends to label the anatomical brain regions in the raw imaging scan. ...
- Citing Conference Paper
December 2020
... State-of-the-Art. The literature extensively explores brain extraction, registration, and segmentation problems [1,7,12,22,23,29,42]. Conventional approaches primarily emphasize the development of separate methods for extraction [23,29], registration [12,42], and segmentation [1,7,22] under supervised settings. ...
- Citing Chapter
January 2020