Muhammad Usman Ghani1, Fitsum Mesadi2, Sümeyra Demir Kanık3, Ali Özgür Argunşah4, Anna Felicity Hobbiss5, Inbal Israely6, Devrim Ünay7, Tolga Taşdizen2, Müjdat Çetin3. 1. Signal Processing and Information Systems Lab., Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey. Electronic address: mughani@bu.edu. 2. Electrical and Computer Engineering Department, University of Utah, Salt Lake City, UT, USA. 3. Signal Processing and Information Systems Lab., Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey. 4. Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal. Electronic address: argunsah@hifo.uzh.ch. 5. Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal. 6. Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal. Electronic address: ii2176@cumc.columbia.edu. 7. Biomedical Engineering Department, Faculty of Engineering, Izmir University of Economics, Izmir, Turkey.
Abstract
BACKGROUND: Neuronal morphology and function are highly coupled. In particular, dendritic spine morphology is strongly governed by the incoming neuronal activity. The first step towards understanding the structure-function relationships is to classify spine shapes into the main spine types suggested in the literature. Due to the lack of reliable automated analysis tools, classification is mostly performed manually, which is a time-intensive task and prone to subjectivity. NEW METHOD: We propose an automated method to classify dendritic spines using shape and appearance features based on challenging two-photon laser scanning microscopy (2PLSM) data. Disjunctive Normal Shape Models (DNSM) is a recently proposed parametric shape representation. We perform segmentation of spine images by applying DNSM and use the resulting representation as shape features. Furthermore, we use Histogram of oriented gradients (HOG) to extract appearance features. In this context, we propose a kernel density estimation (KDE) based framework for dendritic spine classification, which uses these shape and appearance features. RESULTS: Our shape and appearance features based approach combined with Neural Network (NN) correctly classifies 87.06% of spines on a dataset of 456 spines. COMPARISON WITH EXISTING METHODS: Our proposed method outperforms standard morphological feature based approaches. Our KDE based framework also enables neuroscientists to analyze the separability of spine shape classes in the likelihood ratio space, which leads to further insights about nature of the spine shape analysis problem. CONCLUSIONS: Results validate that performance of our proposed approach is comparable to a human expert. It also enable neuroscientists to study shape statistics in the likelihood ratio space.
BACKGROUND: Neuronal morphology and function are highly coupled. In particular, dendritic spine morphology is strongly governed by the incoming neuronal activity. The first step towards understanding the structure-function relationships is to classify spine shapes into the main spine types suggested in the literature. Due to the lack of reliable automated analysis tools, classification is mostly performed manually, which is a time-intensive task and prone to subjectivity. NEW METHOD: We propose an automated method to classify dendritic spines using shape and appearance features based on challenging two-photon laser scanning microscopy (2PLSM) data. Disjunctive Normal Shape Models (DNSM) is a recently proposed parametric shape representation. We perform segmentation of spine images by applying DNSM and use the resulting representation as shape features. Furthermore, we use Histogram of oriented gradients (HOG) to extract appearance features. In this context, we propose a kernel density estimation (KDE) based framework for dendritic spine classification, which uses these shape and appearance features. RESULTS: Our shape and appearance features based approach combined with Neural Network (NN) correctly classifies 87.06% of spines on a dataset of 456 spines. COMPARISON WITH EXISTING METHODS: Our proposed method outperforms standard morphological feature based approaches. Our KDE based framework also enables neuroscientists to analyze the separability of spine shape classes in the likelihood ratio space, which leads to further insights about nature of the spine shape analysis problem. CONCLUSIONS: Results validate that performance of our proposed approach is comparable to a human expert. It also enable neuroscientists to study shape statistics in the likelihood ratio space.
Authors: Elma S Frias; Mahmood S Hoseini; Karen Krukowski; Maria Serena Paladini; Katherine Grue; Gonzalo Ureta; Kira D A Rienecker; Peter Walter; Michael P Stryker; Susanna Rosi Journal: Proc Natl Acad Sci U S A Date: 2022-10-13 Impact factor: 12.779
Authors: V Javier Traver; Filiberto Pla; Marta Miquel; Maria Carbo-Gas; Isis Gil-Miravet; Julian Guarque-Chabrera Journal: Neuroinformatics Date: 2019-07
Authors: Ana Peñalver; José A Campos-Sandoval; Eduardo Blanco; Carolina Cardona; Laura Castilla; Mercedes Martín-Rufián; Guillermo Estivill-Torrús; Raquel Sánchez-Varo; Francisco J Alonso; Mercedes Pérez-Hernández; María I Colado; Antonia Gutiérrez; Fernando Rodríguez de Fonseca; Javier Márquez Journal: Front Mol Neurosci Date: 2017-09-05 Impact factor: 5.639
Authors: Peter Verstraelen; Michiel Van Dyck; Marlies Verschuuren; Nachiket D Kashikar; Rony Nuydens; Jean-Pierre Timmermans; Winnok H De Vos Journal: Front Neurosci Date: 2018-06-26 Impact factor: 4.677