West Virginia University
Multimodal Neuron Classification based on Morphology and Electrophysiology
Abstract
dc:description.abstractCategorizing neurons into different types to understand neural circuits and ultimately brain function is a major challenge in neuroscience. While electrical properties are critical in defining a neuron, its morphology is equally important. Advancements in single-cell analysis methods have allowed neuroscientists to simultaneously capture multiple data modalities from a neuron. We propose a method to classify neurons using both morphological structure and electrophysiology. Current approaches are based on a limited analysis of morphological features. We propose to use a new graph neural network to learn representations that more comprehensively account for the complexity of the shape of neuronal structures. In addition, we design a self-supervised approach for learning representations of electrophysiology data with a convolutional neural network. Morphological and electrophysiology representations are then fused in different ways in an end-to-end approach. Our methods are tested on multiple datasets, and we show a performance that exceeds the state of the art in the single modalities, while we also establish the first baseline for the combined modalities.
Degree
thesis:*- Name thesis:degree_name
- MS
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Lane Department of Computer Science and Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ahmad, Aqib
- Contributors dc:contributor
-
- Gianfranco Doretto
- Donald Adjeroh
- Katerina Goseva-Popstojanova
Subjects
dc:subject × 14Identifiers
dc:identifier.*- Identifier
-
<p><a href="https://orcid.org/0000-0001-6335-8155">https://orcid.org/0000-0001-6335-8155</a></p>
https://researchrepository.wvu.edu/etd/11808