On comparison of manifold learning techniques for dendritic spine classification

Warning The system is temporarily closed to updates for reporting purpose.

Ghani, Muhammad Usman and Argunşah, Ali Özgür and Israely, Inbal and Ünay, Devrim and Taşdizen, Tolga and Çetin, Müjdat (2016) On comparison of manifold learning techniques for dendritic spine classification. In: IEEE International Symposium on Biomedical Imaging, Prague, Czech Republic

This is the latest version of this item.

[thumbnail of Manifold_based_classification_submitted.pdf] PDF
Restricted to Repository staff only

Download (211kB) | Request a copy
[thumbnail of ghani_ISBI16_manifold.pdf] PDF

Download (211kB)


Dendritic spines are one of the key functional components of neurons. Their morphological changes are correlated with neuronal activity. Neuroscientists study spine shape variations to understand their relation with neuronal activity. Currently this analysis performed manually, the availability of reliable automated tools would assist neuroscientists and accelerate this research. Previously, morphological features based spine analysis has been performed and reported in the literature. In this paper, we explore the idea of using and comparing manifold learning techniques for classifying spine shapes. We start with automatically segmented data and construct our feature vector by stacking and concatenating the columns of images. Further, we apply unsupervised manifold learning algorithms and compare their performance in the context of dendritic spine classification. We achieved 85.95% accuracy on a dataset of 242 automatically segmented mushroom and stubby spines. We also observed that ISOMAP implicitly computes prominent features suitable for classification purposes.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Dendritic Spines, Classification, Manifold Learning, ISOMAP, Microscopic Imaging, Neuroimaging
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Q Science > QP Physiology
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Müjdat Çetin
Date Deposited: 14 Jun 2016 14:26
Last Modified: 26 Apr 2022 09:22
URI: https://research.sabanciuniv.edu/id/eprint/29330

Available Versions of this Item

Actions (login required)

View Item
View Item