Dendritic spine classification using shape and appearance features based on two-photon microscopy

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.

[1]  Xiaoyin Xu,et al.  Optical microscopic image processing of dendritic spines morphology , 2006, IEEE Signal Process. Mag..

[2]  Müjdat Çetin,et al.  Dendritic spine shape analysis using disjunctive normal shape models , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[3]  Kristen M Harris,et al.  Structure, development, and plasticity of dendritic spines , 1999, Current Opinion in Neurobiology.

[4]  U. Nägerl,et al.  Spine neck plasticity regulates compartmentalization of synapses , 2014, Nature Neuroscience.

[5]  W. Greenough,et al.  Transient and enduring morphological correlates of synaptic activity and efficacy change in the rat hippocampal slice , 1984, Brain Research.

[6]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[7]  G. Ellis‐Davies,et al.  Structural basis of long-term potentiation in single dendritic spines , 2004, Nature.

[8]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[9]  R. Yuste.  Dendritic Spines , 2010 .

[10]  Susumu Tonegawa,et al.  The Dendritic Branch Is the Preferred Integrative Unit for Protein Synthesis-Dependent LTP , 2011, Neuron.

[11]  Subhadip Basu,et al.  2dSpAn: semiautomated 2-d segmentation, classification and analysis of hippocampal dendritic spine plasticity , 2016, Bioinform..

[12]  Jakub Wlodarczyk,et al.  Sampling issues in quantitative analysis of dendritic spines morphology , 2012, BMC Bioinformatics.

[13]  Alan S. Willsky,et al.  Nonparametric shape priors for active contour-based image segmentation , 2005, 2005 13th European Signal Processing Conference.

[14]  J Son,et al.  Morphological change tracking of dendritic spines based on structural features , 2011, Journal of microscopy.

[15]  Müjdat Çetin,et al.  Dendritic spine shape classification from two-photon microscopy images , 2015, 2015 23nd Signal Processing and Communications Applications Conference (SIU).

[16]  Mark F Bear,et al.  A Morphological Correlate of Synaptic Scaling in Visual Cortex , 2022 .

[17]  J W Wallis,et al.  Three-dimensional display in nuclear medicine. , 1989, IEEE transactions on medical imaging.

[18]  Ertunc Erdil,et al.  A joint classification and segmentation approach for dendritic spine segmentation in 2-photon microscopy images , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[19]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[20]  J. Peacock.  Two-dimensional goodness-of-fit testing in astronomy , 1983 .

[21]  W. Brent Lindquist,et al.  An Image Analysis Algorithm for Dendritic Spines , 2002, Neural Computation.

[22]  R. Yuste,et al.  Morphological changes in dendritic spines associated with long-term synaptic plasticity. , 2001, Annual review of neuroscience.

[23]  Müjdat Çetin,et al.  Disjunctive Normal Shape and Appearance Priors with Applications to Image Segmentation , 2015, MICCAI.

[24]  Darren J. Kerbyson,et al.  Size invariant circle detection , 1999, Image Vis. Comput..

[25]  B R Masters,et al.  Two-photon excitation fluorescence microscopy. , 2000, Annual review of biomedical engineering.

[26]  Douglas B. Ehlenberger,et al.  Automated Three-Dimensional Detection and Shape Classification of Dendritic Spines from Fluorescence Microscopy Images , 2008, PloS one.

[27]  A. Peters,et al.  The small pyramidal neuron of the rat cerebral cortex. The perikaryon, dendrites and spines. , 1970, The American journal of anatomy.

[28]  Rafael Yuste,et al.  Ultrastructure of Dendritic Spines: Correlation Between Synaptic and Spine Morphologies , 2007, Front. Neurosci..

[29]  Müjdat Çetin,et al.  On comparison of manifold learning techniques for dendritic spine classification , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[30]  Müjdat Çetin,et al.  Dendritic Spine Shape Analysis: A Clustering Perspective , 2016, ECCV Workshops.

[31]  Yong Kim,et al.  Online three-dimensional dendritic spines mophological classification based on semi-supervised learning , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[32]  Jonathan R. Whitlock,et al.  Learning Induces Long-Term Potentiation in the Hippocampus , 2006, Science.

[33]  Karel Svoboda,et al.  Locally dynamic synaptic learning rules in pyramidal neuron dendrites , 2007, Nature.

[34]  A. Dunaevsky,et al.  Dendritic spine morphogenesis and plasticity. , 2005, Journal of neurobiology.

[35]  KM Harris,et al.  Three-dimensional structure of dendritic spines and synapses in rat hippocampus (CA1) at postnatal day 15 and adult ages: implications for the maturation of synaptic physiology and long-term potentiation [published erratum appears in J Neurosci 1992 Aug;12(8):following table of contents] , 1992, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[36]  Müjdat Çetin,et al.  Disjunctive normal shape models , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[37]  Rafael Yuste,et al.  Analysis of spine morphological plasticity in developing hippocampal pyramidal neurons , 2000, Hippocampus.

[38]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[39]  Olivier Hermine,et al.  Phenotypic and Genotypic Characteristics of Mastocytosis According to the Age of Onset , 2008, PloS one.

[40]  J. Špaček,et al.  Three-Dimensional analysis of dendritic spines , 1983, Anatomy and Embryology.

[41]  T. Sejnowski,et al.  Hippocampal Spine Head Sizes Are Highly Precise , 2015, bioRxiv.