Classifying GABAergic interneurons with semi-supervised projected model-based clustering

Mihaljevic, Bojan and Larrañaga Mugica, Pedro María and Bielza Lozoya, María Concepción and Benavides-Piccione, Ruth and Guerra, Luis and Felipe Oroquieta, Javier de (2015). Classifying GABAergic interneurons with semi-supervised projected model-based clustering. "Artificial Intelligence in Medicine", v. 65 (n. 1); pp. 49-59. ISSN 0933-3657. https://doi.org/10.1016/j.artmed.2014.12.010.

Description

Title: Classifying GABAergic interneurons with semi-supervised projected model-based clustering
Author/s:
  • Mihaljevic, Bojan
  • Larrañaga Mugica, Pedro María
  • Bielza Lozoya, María Concepción
  • Benavides-Piccione, Ruth
  • Guerra, Luis
  • Felipe Oroquieta, Javier de
Item Type: Article
Título de Revista/Publicación: Artificial Intelligence in Medicine
Date: September 2015
ISSN: 0933-3657
Volume: 65
Subjects:
Freetext Keywords: Keywords:Semi-supervised projected clustering, Gaussian mixture models, Automatic neuron classification, Cerebral cortex
Faculty: E.T.S.I. de Sistemas Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (12MB) | Preview

Abstract

ABSTRACT Objectives: Arecently introduced pragmatic scheme promises to be a useful catalog of interneuron names. We sought to automatically classify digitally reconstructed interneuronal morphologies according to this scheme. Simultaneously, we sought to discover possible subtypes of these types that might emerge during automatic classification (clustering). We also investigated which morphometric properties were most relevant for this classification. Materials and methods: A set of 118 digitally reconstructed interneuronal morphologies classified into the common basket (CB), horse-tail (HT), large basket (LB), and Martinotti (MA) interneuron types by 42 of the world's leading neuroscientists, quantified by five simple morphometric properties of the axon and four of the dendrites. We labeled each neuron with the type most commonly assigned to it by the experts. We then removed this class information for each type separately, and applied semi-supervised clustering to those cells (keeping the others' cluster membership fixed), to assess separation from other types and look for the formation of new groups (subtypes). We performed this same experiment unlabeling the cells of two types at a time, and of half the cells of a single type at a time. The clustering model is a finite mixture of Gaussians which we adapted for the estimation of local (per-cluster) feature relevance. We performed the described experiments on three different subsets of the data, formed according to ho w many experts agreed on type membership: at least 18 experts (the full data set), at least 21 (73 neurons), and at least 26(47 neurons). Results: Interneurons with more reliable type labels were classified more accurately. We classified HT accuracy, and CB and LB cells with 56% and 58% accuracy, respectively. We identified three subtypes of the MA type, one subtype of CB and LB types each, and no subtypes of HT (it was a single, homogeneous type). We got máximum (adapted) Silhouette width and ARI valúes of 1, 0.83, 0.79, and 0.42, when unlabeling the HT, CB, LB, and MA types, respectively, confirming the quality of the formed cluster solutions. The subtypes identified when unlabeling a single type also emerged when unlabeling two types at a time, confirming their validity. Axonal morphometric properties were more relevant that dendritic ones, with the axonal polar histogram length in the [ jr, 2JT) angle interval being particularly useful. Conclusions: The applied semi-supervised clustering method can accurately discrimínate among CB, HT, LB, and MA interneuron types while discovering potential subtypes, and is therefore useful for neuronal classification. The discovery of potential subtypes suggests that some of these types are more heterogeneous that previously thought. Finally, axonal variables seem to be more relevant than dendritic ones for distinguishing among the CB, HT, LB, and MA interneuron types.

Funding Projects

TypeCodeAcronymLeaderTitle
Madrid Regional GovernmentS2013/ICE-2845CASI-CAM CMUnspecifiedUnspecified
FP7604102HBPUnspecifiedThe Human Brain Project
Government of SpainTIN2013-41592-PUnspecifiedUnspecifiedUnspecified
Government of SpainBFU2012-34963UnspecifiedUnspecifiedUnspecified

More information

Item ID: 41019
DC Identifier: http://oa.upm.es/41019/
OAI Identifier: oai:oa.upm.es:41019
DOI: 10.1016/j.artmed.2014.12.010
Official URL: https://www.sciencedirect.com/science/article/pii/S0933365714001481?via%3Dihub
Deposited by: Memoria Investigacion
Deposited on: 01 Jun 2017 15:57
Last Modified: 06 Jun 2019 13:28
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM