ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Density-based clustering of static and dynamic functional MRI connectivity features obtained from subjects with cognitive impairment

Rangaprakash, D and Odemuyiwa, T and Narayana Dutt, D and Deshpande, G (2020) Density-based clustering of static and dynamic functional MRI connectivity features obtained from subjects with cognitive impairment. In: Brain Informatics, 7 (1).

Bra-Inf-7-1.pdf - Published Version

Download (1MB) | Preview
ADDITIONAL FILE.pdf - Published Version

Download (413kB) | Preview
Official URL: https://dx.doi.org/10.1186/s40708-020-00120-2


Various machine-learning classification techniques have been employed previously to classify brain states in healthy and disease populations using functional magnetic resonance imaging (fMRI). These methods generally use supervised classifiers that are sensitive to outliers and require labeling of training data to generate a predictive model. Density-based clustering, which overcomes these issues, is a popular unsupervised learning approach whose utility for high-dimensional neuroimaging data has not been previously evaluated. Its advantages include insensitivity to outliers and ability to work with unlabeled data. Unlike the popular k-means clustering, the number of clusters need not be specified. In this study, we compare the performance of two popular density-based clustering methods, DBSCAN and OPTICS, in accurately identifying individuals with three stages of cognitive impairment, including Alzheimer�s disease. We used static and dynamic functional connectivity features for clustering, which captures the strength and temporal variation of brain connectivity respectively. To assess the robustness of clustering to noise/outliers, we propose a novel method called recursive-clustering using additive-noise (R-CLAN). Results demonstrated that both clustering algorithms were effective, although OPTICS with dynamic connectivity features outperformed in terms of cluster purity (95.46) and robustness to noise/outliers. This study demonstrates that density-based clustering can accurately and robustly identify diagnostic classes in an unsupervised way using brain connectivity. © 2020, The Author(s).

Item Type: Journal Article
Publication: Brain Informatics
Publisher: Springer Science and Business Media Deutschland GmbH
Additional Information: Copyright to this article belongs to Springer Science and Business Media Deutschland GmbH
Keywords: Additive noise; Classification (of information); Diagnosis; Functional neuroimaging; Magnetic resonance imaging; Predictive analytics; Statistics, Cognitive impairment; Density-based Clustering; Functional connectivity; Functional magnetic resonance imaging; Machine learning classification; Predictive modeling; Robustness to noise; Supervised classifiers, K-means clustering
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 05 Jan 2021 11:24
Last Modified: 05 Jan 2021 11:24
URI: http://eprints.iisc.ac.in/id/eprint/67172

Actions (login required)

View Item View Item