Discovering brain regions relevant to obsessive–compulsive disorder identification through bagging and transduction

Parrado-Hernández, Emilio; Gómez-Verdejo, Vanessa; Martínez‐Ramón, Manel; Shawe‐Taylor, John; Alonso, Pino; Pujol, Jesús; Menchón, José M.; Cardoner, Narcı́s; Soriano‐Mas, Carles

doi:10.1016/j.media.2014.01.006

Cited by 31 publications

(32 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results presented in this paper build on our previous work on variable selection (Parrado-Hernández et al 2014) and thoroughly extend a preliminary conference paper focused on assessing variable relevance (Gomez-Verdejo et al 2016). In particular, the main novel contributions of this paper over (Parrado-Hernández et al 2014) and (Gomez-Verdejo et al 2016) are:…”

Section: Introductionsupporting

confidence: 76%

Sign-consistency based variable importance for machine learning in brain imaging

Gómez-Verdejo

Parrado-Hernández

Tohka

2017

Preprint

Self Cite

View full text Add to dashboard Cite

An important problem that hinders the use of supervised classification algorithms for brain imaging is that the number of variables for single subject far exceeds the number of training subjects available. Deriving multivariate measures of variable importance becomes a challenge in such scenarios. This paper proposes a new measure of variable importance termed sign-consistency bagging (SCB). The SCB captures variable importance by analyzing the sign consistency of the corresponding weights in an ensemble of linear support vector machine (SVM) classifiers. Further, the SCB variable importances are enhanced by means of transductive conformal analysis. This extra step is important when the data can be assumed to be heterogeneous.Finally, the proposal of these SCB variable importance measures is completed with the derivation of a parametric hypothesis test of variable importance. Preprint submitted to ElsevierApril 5, 2017. CC-BY-NC-ND 4.0 International license peer-reviewed) is the author/funder. It is made available under a The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/124453 doi: bioRxiv preprint first posted online The new importance measures were compared with a t-test based univariate and an SVM-based multivariate variable importances using anatomical and functional magnetic resonance imaging data. The obtained results demonstrated that the new SCB based importance measures were superior to the compared methods in terms of reproducibility and classification accuracy.

show abstract

Section: Introductionsupporting

confidence: 76%

Sign-consistency based variable importance for machine learning in brain imaging

Gómez-Verdejo

Parrado-Hernández

Tohka

2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ensemble learning, such as bagging and boosting, is thus an intuitive option to fuse the classification outputs from different weak classifiers to obtain more accurate results. The weak classifiers can be of any type, including SVM [14], decision tree [5], [15], [22], [46]- [48], and logistic regression [21]. Sparse representation classifiers have also been integrated into the boosting model as weak classifiers based on random subsets of reference images [37], [49].…”

Section: A Related Workmentioning

confidence: 99%

“…Sparse representation classifiers have also been integrated into the boosting model as weak classifiers based on random subsets of reference images [37], [49]. The combination of weak classifiers is normally based on a predefined weighting scheme, such as the majority voting or averaging of probabilities in bagging [5], [14], [15], [22], [47], [48], or choosing the best performing weak classifier at each training iteration with error-based weight computation in boosting [21], [37], [46], [49]. While these weighting schemes are often effective, they are however predefined, greedy, and and might not reflect the best adaptation to the dataset.…”

Section: A Related Workmentioning

confidence: 99%

Large Margin Local Estimate With Applications to Medical Image Classification

Song¹,

Cai²,

Huang

et al. 2015

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Medical images usually exhibit large intra-class variation and inter-class ambiguity in the feature space, which could affect classification accuracy. To tackle this issue, we propose a new Large Margin Local Estimate (LMLE) classification model with sub-categorization based sparse representation. We first sub-categorize the reference sets of different classes into multiple clusters, to reduce feature variation within each subcategory compared to the entire reference set. Local estimates are generated for the test image using sparse representation with reference subcategories as the dictionaries. The similarity between the test image and each class is then computed by fusing the distances with the local estimates in a learning-based large margin aggregation construct to alleviate the problem of inter-class ambiguity. The derived similarities are finally used to determine the class label. We demonstrate that our LMLE model is generally applicable to different imaging modalities, and applied it to three tasks: interstitial lung disease (ILD) classification on high-resolution computed tomography (HRCT) images, phenotype binary classification and continuous regression on brain magnetic resonance (MR) imaging. Our experimental results show statistically significant performance improvements over existing popular classifiers.

show abstract

“…6 We aimed to compare structural brain abnormalities between patients with OCD with and without SP and the association between SP scores and the voxel-wise grey matter measurements from the sensorimotor cortex. Regional grey matter measurements provide a relatively stable marker of brain abnormality, thus allowing the identification of structural correlates of OCD [16][17][18][19] or specific clinical features. [20][21][22][23] We analyzed structural MRI data from 2 independent research centres located in São Paulo, Brazil, and Barcelona, Spain.…”

Section: Introductionmentioning

confidence: 99%

Brain structural correlates of sensory phenomena in patients with obsessive–compulsive disorder

Subirà

Sato

Alonso

et al. 2015

jpn

Self Cite

View full text Add to dashboard Cite

Discovering brain regions relevant to obsessive–compulsive disorder identification through bagging and transduction

Cited by 31 publications

References 33 publications

Sign-consistency based variable importance for machine learning in brain imaging

Sign-consistency based variable importance for machine learning in brain imaging

Large Margin Local Estimate With Applications to Medical Image Classification

Brain structural correlates of sensory phenomena in patients with obsessive–compulsive disorder

Contact Info

Product

Resources

About