Filters








2,381 Hits in 5.2 sec

Spatial and anatomical regularization of SVM for brain image analysis

Rémi Cuingnet, Marie Chupin, Habib Benali, Olivier Colliot
2010 Neural Information Processing Systems  
This paper introduces a framework to spatially regularize SVM for brain image analysis.  ...  The results demonstrate that the proposed method enables natural spatial and anatomical regularization of the classifier.  ...  ADNI data are disseminated by the Laboratory of Neuro Imaging at the University of California, Los Angeles.  ... 
dblp:conf/nips/CuingnetCBC10 fatcat:meopw4oo6japjmisz2ae7auxji

Spatial and Anatomical Regularization of SVM: A General Framework for Neuroimaging Data

R. Cuingnet, Joan Alexis Glaunes, M. Chupin, H. Benali, O. Colliot
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper presents a framework to introduce spatial and anatomical priors in SVM for brain image analysis based on regularization operators.  ...  A notion of proximity based on prior anatomical knowledge between the image points is defined by a graph (e.g. brain connectivity graph) or a metric (e.g. Fisher metric on statistical manifolds).  ...  DISCUSSION In this contribution, we proposed to use regularization operators to add spatial and anatomical priors into SVM for brain image analysis.  ... 
doi:10.1109/tpami.2012.142 pmid:22732664 fatcat:gapx5chj6be6hfm3i2zph733r4

Anatomical Regularization on Statistical Manifolds for the Classification of Patients with Alzheimer's Disease [chapter]

Rémi Cuingnet, Joan Alexis Glaunès, Marie Chupin, Habib Benali, Olivier Colliot
2011 Lecture Notes in Computer Science  
This paper introduces a continuous framework to spatially regularize support vector machines (SVM) for brain image analysis based on the Fisher metric.  ...  Based on this metric, replacing the standard SVM regularization with a Laplace-Beltrami regularization operator allows integrating to the classifier various types of constraints based on spatial and anatomical  ...  Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904).  ... 
doi:10.1007/978-3-642-24319-6_25 fatcat:mo6jua5aqnedxesomwnhxbdija

Spatial and Anatomical Regularization Based on Multiple Kernel Learning for Neuroimaging Classification

YingJiang WU, BenYong LIU
2016 IEICE transactions on information and systems  
minimal optimization (SMO) training algorithm is adopted, for brain image analysis.  ...  However, to satisfy the optimization conditions required in the single kernel case, it is unreasonably assumed that the spatial regularization parameter is equal to the anatomical one.  ...  For the purpose of introducing anatomical and spatial priors into SVM, we should combine the two regularization terms and solve the following optimization problem: (w opt , b opt ) = arg min w∈Ω, b∈R 1  ... 
doi:10.1587/transinf.2015edl8163 fatcat:6tfprzvuijbkjhgnvuunufx3rq

Spatially Regularized SVM for the Detection of Brain Areas Associated with Stroke Outcome [chapter]

Rémi Cuingnet, Charlotte Rosso, Stéphane Lehéricy, Didier Dormont, Habib Benali, Yves Samson, Olivier Colliot
2010 Lecture Notes in Computer Science  
This paper introduces a new method to detect group differences in brain images based on spatially regularized support vector machines (SVM).  ...  First, we propose to spatially regularize the SVM using a graph encoding the voxels' proximity. Two examples of regularization graphs are provided.  ...  We then propose a statistical analysis based on the spatially regularized SVM to detect brain regions which are significantly different between two groups of subjects.  ... 
doi:10.1007/978-3-642-15705-9_39 fatcat:eant7pkgyjef3nzmknpudg3uqu

Recognition of Schizophrenia with Regularized Support Vector Machine and Sequential Region of Interest Selection using Structural Magnetic Resonance Imaging

Rowena Chin, Alex Xiaobin You, Fanwen Meng, Juan Zhou, Kang Sim
2018 Scientific Reports  
To this end, Cuingnet et al. 37 introduced a framework that takes into account the spatial and anatomical information in brain images with the supplementation of a brain atlas.  ...  These findings demonstrate the utility of spatial and anatomical priors in SVM for neuroimaging analyses in conjunction with sequential ROI selection in the recognition of schizophrenia.  ...  All authors reviewed and edited manuscript drafts for intellectual content.  ... 
doi:10.1038/s41598-018-32290-9 pmid:30218016 pmcid:PMC6138658 fatcat:3qi4osf32fa4hlyi7nz2ml3nzm

Integrating spatial-anatomical regularization and structure sparsity into SVM: Improving interpretation of Alzheimer's disease classification

Zhuo Sun, Yuchuan Qiao, Boudewijn P.F. Lelieveldt, Marius Staring
2018 NeuroImage  
Acknowledgments This project is funded by the Joint Scientific Thematic Research Programme (JSTP) between The Netherlands and China (Project 116350001).  ...  SR and SAR stand for spatial regularization and spatial-anatomical regularization, respectively.  ...  Cuingnet et al. (2013) proposed to use two independent terms for spatial and anatomical regularization in a linear SVM.  ... 
doi:10.1016/j.neuroimage.2018.05.051 pmid:29802968 fatcat:7ivw56eex5hsbn65xdpp6gsx6a

Tree-Guided Sparse Coding for Brain Disease Classification [chapter]

Manhua Liu, Daoqiang Zhang, Pew-Thian Yap, Dinggang Shen
2012 Lecture Notes in Computer Science  
Spatial relationships of the image structures are imposed during sparse coding with a tree-guided regularization.  ...  One of the major problems in brain image analysis involves learning the most relevant features from a huge set of raw imaging features, which are far more numerous than the training samples.  ...  Recently, many machine learning and pattern recognition technologies, e.g., support vector machines (SVM), have been investigated for analysis of brain images to assist the diagnosis of brain diseases  ... 
doi:10.1007/978-3-642-33454-2_30 fatcat:hym47igdijgszhhwogrpq4fhlq

Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome

Rémi Cuingnet, Charlotte Rosso, Marie Chupin, Stéphane Lehéricy, Didier Dormont, Habib Benali, Yves Samson, Olivier Colliot
2011 Medical Image Analysis  
In this paper, we propose a new method to detect differences at the group level in brain images based on spatially regularized support vector machines (SVM).  ...  We propose to spatially regularize the SVM using a graph Laplacian. This provides a flexible approach to model different types of proximity between voxels.  ...  Regularization and priors in SVM Linear SVM In this contribution, we consider any feature computed at each voxel of a 3D brain image.  ... 
doi:10.1016/j.media.2011.05.007 pmid:21752695 fatcat:5wjjk6q7sbgzjm6ayw6qrcrw5u

Social-sparsity brain decoders: faster spatial sparsity

Gael Varoquaux, Matthieu Kowalski, Bertrand Thirion
2016 2016 International Workshop on Pattern Recognition in Neuroimaging (PRNI)  
Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions.  ...  We find that, on brain imaging classification problems, social-sparsity performs almost as well as total-variation models and better than graph-net, for a fraction of the computational cost.  ...  Spatial and sparse penalties, using total variation (TV) [8] or graph-net [9] , help the decoder capture full regions [5] . TV and its variants are state-of-the-art regularizers for brain images.  ... 
doi:10.1109/prni.2016.7552352 dblp:conf/prni/VaroquauxKT16 fatcat:g5emvsfolbet7ob32p2tlma2ou

Social-sparsity brain decoders: faster spatial sparsity [article]

Gaël Varoquaux, Matthieu Kowalski (PARIETAL, L2S), Bertrand Thirion
2016 arXiv   pre-print
Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions.  ...  We find that, on brain imaging classification problems, social-sparsity performs almost as well as total-variation models and better than graph-net, for a fraction of the computational cost.  ...  Spatial and sparse penalties, using total variation (TV) [8] or graph-net [9] , help the decoder capture full regions [5] . TV and its variants are state-of-the-art regularizers for brain images.  ... 
arXiv:1606.06439v1 fatcat:taa5wndawvfonp5egu5cmxfqcy

Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation

Gerard Sanroma, Oualid M. Benkarim, Gemma Piella, Karim Lekadir, Nadine Hahner, Elisenda Eixarch, Miguel A. González Ballester
2018 Computerized Medical Imaging and Graphics  
Segmentation of brain structures during the pre-natal and early post-natal periods is the first step for subsequent analysis of brain development.  ...  The second family, denoted as learning-based techniques, relate imaging (and spatial) features to their corresponding anatomical labels.  ...  Segmentation of brain structures is the first step required for such analyses, which is usually done with T1 and/or T2 MRI modalities since they of-20 fer good anatomical contrast.  ... 
doi:10.1016/j.compmedimag.2018.08.007 pmid:30176518 fatcat:lcffq6joingr7cxevgsaretw2q

Anatomical Pattern Analysis for decoding visual stimuli in human brains [article]

Muhammad Yousefnezhad, Daoqiang Zhang
2017 arXiv   pre-print
Methods: In overcoming mentioned challenges, this paper proposes Anatomical Pattern Analysis (APA) for decoding visual stimuli in the human brain.  ...  A universal unanswered question in neuroscience and machine learning is whether computers can decode the patterns of the human brain.  ...  L1/L2 regularized SVM, the Elastic Net, and the Graph Net, for predicting different responses in the human brain.  ... 
arXiv:1710.02113v1 fatcat:xtl7wksovbgxfc77xv3cgixndq

A hybrid SVM–GLM approach for fMRI data analysis

Ze Wang
2009 NeuroImage  
This hybrid SVM-GLM concept is to use the power of SVM to obtain a dataderived reference function and enter it into the conventional GLM for statistical inference.  ...  With real fMRI data, SVM-GLM showed better sensitivity than regular GLM for detecting the sensorimotor activations.  ...  High resolution 3D T1weighted anatomical images using the MPRAGE (TR/TE/TI = 1630/3/1100msec) sequence were obtained for each subject for spatial image normalization.  ... 
doi:10.1016/j.neuroimage.2009.03.016 pmid:19303449 pmcid:PMC2711446 fatcat:gzfvjyhgtreuzbtssjd62ev7wi

Alzheimer's Disease Classification by Extracting Salient Brain Patterns

Dinbin Sunny, Meekha Merina George
2015 International Journal of Engineering Research and  
Neuroimaging is the process of producing images of the structure or function of the brain; it is used for the diagnosis of neurodegenerative diseases.  ...  In bottom-up approach, information comes from a multiscale analysis of different image features. And the topdown approach includes learning and fusion.  ...  Performance analysis of SVM and NN In table 1 shows the performance analysis of SVM and NN, in which measure accuracy, sensitivity, specificity and error rate values.  ... 
doi:10.17577/ijertv4is110500 fatcat:4bhvvkf3vjhclom22xv7ip2vjq
« Previous Showing results 1 — 15 out of 2,381 results