Optimal model-free approach based on MDL and CHL for active brain identification in fMRI data analysis

buir.contributor.authorAlgın, Oktay
buir.contributor.orcidAlgın, Oktay|0000-0002-3877-8366
dc.citation.epage365en_US
dc.citation.issueNumber3en_US
dc.citation.spage352en_US
dc.citation.volumeNumber17en_US
dc.contributor.authorJaber, H. A.
dc.contributor.authorÇankaya, I.
dc.contributor.authorAljobouri, H. K.
dc.contributor.authorKoçak, O. M.
dc.contributor.authorAlgın, Oktay
dc.date.accessioned2022-02-21T10:39:17Z
dc.date.available2022-02-21T10:39:17Z
dc.date.issued2020-07-30
dc.departmentNational Magnetic Resonance Research Center (UMRAM)en_US
dc.description.abstractBackground: Cluster analysis is a robust tool for exploring the underlining structures in data and grouping them with similar objects. In the researches of Functional Magnetic Resonance Imaging (fMRI), clustering approaches attempt to classify voxels depending on their time-course signals into a similar hemodynamic response over time. Objective: In this work, a novel unsupervised learning approach is proposed that relies on using Enhanced Neural Gas (ENG) algorithm in fMRI data for comparison with Neural Gas (NG) method, which has yet to be utilized for that aim. The ENG algorithm depends on the network structure of the NG and concentrates on an efficacious prototype-based clustering approach. Methods: The comparison outcomes on real auditory fMRI data show that ENG outperforms the NG and statistical parametric mapping (SPM) methods due to its insensitivity to the ordering of input data sequence, various initializations for selecting a set of neurons, and the existence of extreme values (outliers). The findings also prove its capability to discover the exact and real values of a cluster number effectively. Results: Four validation indices are applied to evaluate the performance of the proposed ENG method with fMRI and compare it with a clustering approach (NG algorithm) and model-based data analysis (SPM). These validation indices include the Jaccard Coefficient (JC), Receiver Operating Characteristic (ROC), Minimum Description Length (MDL) value, and Minimum Square Error (MSE). Conclusion: The ENG technique can tackle all shortcomings of NG application with fMRI data, identify the active area of the human brain effectively, and determine the locations of the cluster center based on the MDL value during the process of network learning.en_US
dc.identifier.doi10.2174/1573405616999200730174700en_US
dc.identifier.eissn1875-6603
dc.identifier.issn1573-4056
dc.identifier.urihttp://hdl.handle.net/11693/77537
dc.language.isoEnglishen_US
dc.publisherBentham Science Publishers Ltd.en_US
dc.relation.isversionofhttps://doi.org/10.2174/1573405616999200730174700en_US
dc.source.titleCurrent Medical Imagingen_US
dc.subjectEnhanced Neural Gas (ENG)en_US
dc.subjectFMRI clustering techniqueen_US
dc.subjectMinimum Description Length (MDL)en_US
dc.subjectNeural Gas (NG)en_US
dc.subjectPrototype-Based Clustering (PBC)en_US
dc.subjectStatistical Parametric Mapping (SPM)en_US
dc.titleOptimal model-free approach based on MDL and CHL for active brain identification in fMRI data analysisen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Bilkent-research-paper.pdf
Size:
262.66 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections