An automated pipeline for dendrite spine detection and tracking of 3D optical microscopy neuron images of in vivo mouse models

Recent advances in computational methods for measurement of dendritic spines imaged by light microscopy

Dendritic spines are small protrusions that receive most of the excitatory inputs to the pyramidal neurons in the neocortex and the hippocampus. Excitatory neural circuits in the neocortex and hippocampus are important for experience-dependent changes in brain functions, including postnatal sensory refinement and memory formation. Several lines of evidence indicate that synaptic efficacy is correlated with spine size and structure. Hence, precise and accurate measurement of spine morphology is important for evaluation of neural circuit function and plasticity. Recent advances in light microscopy and image analysis techniques have opened the way toward a full description of spine nanostructure. In addition, large datasets of spine nanostructure can be effectively analyzed using machine learning techniques and other mathematical approaches, and recent advances in super-resolution imaging allow researchers to analyze spine structure at an unprecedented level of precision. This review summarizes computational methods that can effectively identify, segment and quantitate dendritic spines in either 2D or 3D imaging. Nanoscale analysis of spine structure and dynamics, combined with new mathematical approaches, will facilitate our understanding of spine functions in physiological and pathological conditions.

Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes

BACKGROUND

Dendritic spines are structural correlates of excitatory synapses in the brain. Their density and structure are shaped by experience, pointing to their role in memory encoding. Dendritic spine imaging, followed by manual analysis, is a primary way to study spines. However, an approach that analyses dendritic spines images in an automated and unbiased manner is needed to fully capture how spines change with normal experience, as well as in disease.

NEW METHOD

We propose an approach based on fully convolutional neural networks (FCNs) to detect dendritic spines in two-dimensional maximum-intensity projected images from confocal fluorescent micrographs. We experiment on both fractionally strided convolution and efficient sub-pixel convolutions. Dendritic spines far from the dendritic shaft are pruned by extraction of the shaft to reduce false positives. Performance of the proposed method is evaluated by comparing predicted spine positions to those manually marked by experts.

RESULTS

The averaged distance between predicted and manually annotated spines is 2.81 ± 2.63 pixels (0.082 ± 0.076 microns) and 2.87 ± 2.33 pixels (0.084 ± 0.068 microns) based on two different experts. FCN-based detection achieves F scores > 0.80 for both sets of expert annotations.

COMPARISON WITH EXISTING METHODS

Our method significantly outperforms two well-known software, NeuronStudio and Neurolucida (p-value < 0.02).

CONCLUSIONS

FCN architectures used in this work allow for automated dendritic spine detection. Superior outcomes are possible even with small training data-sets. The proposed method may generalize to other datasets on larger scales.

An automated pipeline for bouton, spine, and synapse detection of in vivo two-photon images

Background

In the nervous system, the neurons communicate through synapses. The size, morphology, and connectivity of these synapses are significant in determining the functional properties of the neural network. Therefore, they have always been a major focus of neuroscience research. Two-photon laser scanning microscopy allows the visualization of synaptic structures in vivo, leading to many important findings. However, the identification and quantification of structural imaging data currently rely heavily on manual annotation, a method that is both time-consuming and prone to bias.

Results

We present an automated approach for the identification of synaptic structures in two-photon images. Axon boutons and dendritic spines are structurally distinct. They can be detected automatically using this image processing method. Then, synapses can be identified by integrating information from adjacent axon boutons and dendritic spines. In this study, we first detected the axonal boutons and dendritic spines respectively, and then identified synapses based on these results. Experimental results were validated manually, and the effectiveness of our proposed method was demonstrated.

Conclusions

This approach will helpful for neuroscientists to automatically analyze and quantify the formation, elimination and destabilization of the axonal boutons, dendritic spines and synapses.

Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine

Dendritic spines are described as neuronal protrusions. The morphology of dendritic spines and dendrites has a strong relationship to its function, as well as playing an important role in understanding brain function. Quantitative analysis of dendrites and dendritic spines is essential to an understanding of the formation and function of the nervous system. However, highly efficient tools for the quantitative analysis of dendrites and dendritic spines are currently undeveloped. In this paper we propose a novel three-step cascaded algorithm–RTSVM— which is composed of ridge detection as the curvature structure identifier for backbone extraction, boundary location based on differences in density, the Hu moment as features and Twin Support Vector Machine (TSVM) classifiers for spine classification. Our data demonstrates that this newly developed algorithm has performed better than other available techniques used to detect accuracy and false alarm rates. This algorithm will be used effectively in neuroscience research.

Image Informatics Strategies for Deciphering Neuronal Network Connectivity

Brain function relies on an intricate network of highly dynamic neuronal connections that rewires dramatically under the impulse of various external cues and pathological conditions. Amongst the neuronal structures that show morphological plasticity are neurites, synapses, dendritic spines and even nuclei. This structural remodelling is directly connected with functional changes such as intercellular communication and the associated calcium bursting behaviour. In vitro cultured neuronal networks are valuable models for studying these morpho-functional changes. Owing to the automation and standardization of both image acquisition and image analysis, it has become possible to extract statistically relevant readouts from such networks. Here, we focus on the current state-of-the-art in image informatics that enables quantitative microscopic interrogation of neuronal networks. We describe the major correlates of neuronal connectivity and present workflows for analysing them. Finally, we provide an outlook on the challenges that remain to be addressed, and discuss how imaging algorithms can be extended beyond in vitro imaging studies.

Detection of Dendritic Spines Using Wavelet-Based Conditional Symmetric Analysis and Regularized Morphological Shared-Weight Neural Networks

Identification and detection of dendritic spines in neuron images are of high interest in diagnosis and treatment of neurological and psychiatric disorders (e.g., Alzheimer's disease, Parkinson's diseases, and autism). In this paper, we have proposed a novel automatic approach using wavelet-based conditional symmetric analysis and regularized morphological shared-weight neural networks (RMSNN) for dendritic spine identification involving the following steps: backbone extraction, localization of dendritic spines, and classification. First, a new algorithm based on wavelet transform and conditional symmetric analysis has been developed to extract backbone and locate the dendrite boundary. Then, the RMSNN has been proposed to classify the spines into three predefined categories (mushroom, thin, and stubby). We have compared our proposed approach against the existing methods. The experimental result demonstrates that the proposed approach can accurately locate the dendrite and accurately classify the spines into three categories with the accuracy of 99.1% for “mushroom” spines, 97.6% for “stubby” spines, and 98.6% for “thin” spines.

Integration of multiscale dendritic spine structure and function data into systems biology models

Comprising 10¹¹ neurons with 10¹⁴ synaptic connections the human brain is the ultimate systems biology puzzle. An increasing body of evidence highlights the observation that changes in brain function, both normal and pathological, consistently correlate with dynamic changes in neuronal anatomy. Anatomical changes occur on a full range of scales from the trafficking of individual proteins, to alterations in synaptic morphology both individually and on a systems level, to reductions in long distance connectivity and brain volume. The major sites of contact for synapsing neurons are dendritic spines, which provide an excellent metric for the number and strength of signaling connections between elements of functional neuronal circuits. A comprehensive model of anatomical changes and their functional consequences would be a holy grail for the field of systems neuroscience but its realization appears far on the horizon. Various imaging technologies have advanced to allow for multi-scale visualization of brain plasticity and pathology, but computational analysis of the big data sets involved forms the bottleneck toward the creation of multiscale models of brain structure and function. While a full accounting of techniques and progress toward a comprehensive model of brain anatomy and function is beyond the scope of this or any other single paper, this review serves to highlight the opportunities for analysis of neuronal spine anatomy and function provided by new imaging technologies and the high-throughput application of older technologies while surveying the strengths and weaknesses of currently available computational analytical tools and room for future improvement.

Quantitative morphological analysis of curvilinear network for microscopic image based on individual fibre segmentation (IFS)

Microscopic images of curvilinear fibre network structure like cytoskeleton are traditionally analysed by qualitative observation, which can hardly provide quantitative information of their morphological properties. However, such information is crucially contributive to the understanding of important biological events, even helps to learn about the inner relations hard to perceive. Individual fibre segmentation-based curvilinear structure detector proposed in this study can identify each individual fibre in the network, as well as connections between different fibres. Quantitative information of each individual fibre, including length, orientation and position, can be extracted; so are the connecting modes in the fibre network, such as bifurcation, intersection and overlap. Distribution of fibres with different morphological properties is also presented. No manual intervening or subjective judging is required in the analysing process. Both synthesized and experimental microscopic images have verified that the detector is capable to segment curvilinear network at the subcellular level with strong noise immunity. The proposed detector is finally applied to the morphological study on cytoskeleton. It is believed that the individual fibre segmentation-based curvilinear structure detector can greatly enhance our understanding of those biological images generated from tons of biological experiments.

A quantitative analytic pipeline for evaluating neuronal activities by high-throughput synaptic vesicle imaging

Synaptic vesicle dynamics play an important role in the study of neuronal and synaptic activities of neurodegradation diseases ranging from the epidemic Alzheimer's disease to the rare Rett syndrome. A high-throughput assay with a large population of neurons would be useful and efficient to characterize neuronal activity based on the dynamics of synaptic vesicles for the study of mechanisms or to discover drug candidates for neurodegenerative and neurodevelopmental disorders. However, the massive amounts of image data generated via high-throughput screening require enormous manual processing time and effort, restricting the practical use of such an assay. This paper presents an automated analytic system to process and interpret the huge data set generated by such assays. Our system enables the automated detection, segmentation, quantification, and measurement of neuron activities based on the synaptic vesicle assay. To overcome challenges such as noisy background, inhomogeneity, and tiny object size, we first employ MSVST (Multi-Scale Variance Stabilizing Transform) to obtain a denoised and enhanced map of the original image data. Then, we propose an adaptive thresholding strategy to solve the inhomogeneity issue, based on the local information, and to accurately segment synaptic vesicles. We design algorithms to address the issue of tiny objects of interest overlapping. Several post processing criteria are defined to filter false positives. A total of 152 features are extracted for each detected vesicle. A score is defined for each synaptic vesicle image to quantify the neuron activity. We also compare the unsupervised strategy with the supervised method. Our experiments on hippocampal neuron assays showed that the proposed system can automatically detect vesicles and quantify their dynamics for evaluating neuron activities. The availability of such an automated system will open opportunities for investigation of synaptic neuropathology and identification of candidate therapeutics for neurodegeneration.

Emergence of layer IV barrel cytoarchitecture is delayed in somatosensory cortex of GAP-43 deficient mice following delayed development of dendritic asymmetry

The emergence of barrel cytoarchitecture in mouse somatosensory cortex is extremely well defined. However, mechanisms underlying the development of this cellular organization are not completely understood. While it is generally accepted that hollows emerge via passive displacement of cortical cells by dense thalamocortical afferent clusters in barrel centers, it is not known what causes cellular segregation of barrel sides and septa. Here, we hypothesized that the emergence of sides and septa is related to the progressive asymmetry of dendrites from the cells of the barrel side toward the barrel hollow during development. We tested this hypothesis in the barrel cortex of growth-associated protein-43 heterozygous mice (GAP43 (+/-) mice) that display a 2-day delay in retraction of septally oriented dendrites compared to (+/+) littermates. We predicted that this delayed retraction would result in a subsequent 2-day delay in the emergence of barrel sides and septa. Using cresyl violet staining of barrel cortex, we found that initial emergence of hollows was not different between GAP43 (+/-) mice and (+/+) littermate controls. However, the emergence of sides and septa was delayed by 2 days, supporting our hypothesis that the emergence of barrel sides and septa is related to, and perhaps reliant upon, the developmental step of dendritic orientation toward barrel hollows. This process, which is mechanistically distinct from the emergence of barrel hollows, is likely due to both active and passive events resulting from asymmetric cell orientation.

Methods of dendritic spine detection: from Golgi to high-resolution optical imaging

Dendritic spines, the bulbous protrusions that form the postsynaptic half of excitatory synapses, are one of the most prominent features of neurons and have been imaged and studied for over a century. In that time, changes in the number and morphology of dendritic spines have been correlated to the developmental process as well as the pathophysiology of a number of neurodegenerative diseases. Due to the sheer scale of synaptic connectivity in the brain, work to date has merely scratched the surface in the study of normal spine function and pathology. This review will highlight traditional approaches to the imaging of dendritic spines and newer approaches made possible by advances in microscopy, protein engineering, and image analysis. The review will also describe recent work that is leading researchers toward the possibility of a systematic and comprehensive study of spine anatomy throughout the brain.

Automated 4D analysis of dendritic spine morphology: applications to stimulus-induced spine remodeling and pharmacological rescue in a disease model

Uncovering the mechanisms that regulate dendritic spine morphology has been limited, in part, by the lack of efficient and unbiased methods for analyzing spines. Here, we describe an automated 3D spine morphometry method and its application to spine remodeling in live neurons and spine abnormalities in a disease model. We anticipate that this approach will advance studies of synapse structure and function in brain development, plasticity, and disease.

Oriented Markov random field based dendritic spine segmentation for fluorescence microscopy images

Dendritic spines have been shown to be closely related to various functional properties of the neuron. Usually dendritic spines are manually labeled to analyze their morphological changes, which is very time-consuming and susceptible to operator bias, even with the assistance of computers. To deal with these issues, several methods have been recently proposed to automatically detect and measure the dendritic spines with little human interaction. However, problems such as degraded detection performance for images with larger pixel size (e.g. 0.125 μm/pixel instead of 0.08 μm/pixel) still exist in these methods. Moreover, the shapes of detected spines are also distorted. For example, the "necks" of some spines are missed. Here we present an oriented Markov random field (OMRF) based algorithm which improves spine detection as well as their geometric characterization. We begin with the identification of a region of interest (ROI) containing all the dendrites and spines to be analyzed. For this purpose, we introduce an adaptive procedure for identifying the image background. Next, the OMRF model is discussed within a statistical framework and the segmentation is solved as a maximum a posteriori estimation (MAP) problem, whose optimal solution is found by a knowledge-guided iterative conditional mode (KICM) algorithm. Compared with the existing algorithms, the proposed algorithm not only provides a more accurate representation of the spine shape, but also improves the detection performance by more than 50% with regard to reducing both the misses and false detection.

A global spatial similarity optimization scheme to track large numbers of dendritic spines in time-lapse confocal microscopy

Dendritic spines form postsynaptic contact sites in the central nervous system. The rapid and spontaneous morphology changes of spines have been widely observed by neurobiologists. Determining the relationship between dendritic spine morphology change and its functional properties such as memory learning is a fundamental yet challenging problem in neurobiology research. In this paper, we propose a novel algorithm to track the morphology change of multiple spines simultaneously in time-lapse neuronal images based on nonrigid registration and integer programming. We also propose a robust scheme to link disappearing-and-reappearing spines. Performance comparisons with other state-of-the-art cell and spine tracking algorithms, and the ground truth show that our approach is more accurate and robust, and it is capable of tracking a large number of neuronal spines in time-lapse confocal microscopy images.

Neuron tracing in perspective

The study of the structure and function of neuronal cells and networks is of crucial importance in the endeavor to understand how the brain works. A key component in this process is the extraction of neuronal morphology from microscopic imaging data. In the past four decades, many computational methods and tools have been developed for digital reconstruction of neurons from images, with limited success. As witnessed by the growing body of literature on the subject, as well as the organization of challenging competitions in the field, the quest for a robust and fully automated system of more general applicability still continues. The aim of this work, is to contribute by surveying recent developments in the field for anyone interested in taking up the challenge. Relevant aspects discussed in the article include proposed image segmentation methods, quantitative measures of neuronal morphology, currently available software tools for various related purposes, and morphology databases. (c) 2010 International Society for Advancement of Cytometry.

Automatic robust neurite detection and morphological analysis of neuronal cell cultures in high-content screening

Cell-based high content screening (HCS) is becoming an important and increasingly favored approach in therapeutic drug discovery and functional genomics. In HCS, changes in cellular morphology and biomarker distributions provide an information-rich profile of cellular responses to experimental treatments such as small molecules or gene knockdown probes. One obstacle that currently exists with such cell-based assays is the availability of image processing algorithms that are capable of reliably and automatically analyzing large HCS image sets. HCS images of primary neuronal cell cultures are particularly challenging to analyze due to complex cellular morphology. Here we present a robust method for quantifying and statistically analyzing the morphology of neuronal cells in HCS images. The major advantages of our method over existing software lie in its capability to correct non-uniform illumination using the contrast-limited adaptive histogram equalization method; segment neuromeres using Gabor-wavelet texture analysis; and detect faint neurites by a novel phase-based neurite extraction algorithm that is invariant to changes in illumination and contrast and can accurately localize neurites. Our method was successfully applied to analyze a large HCS image set generated in a morphology screen for polyglutamine-mediated neuronal toxicity using primary neuronal cell cultures derived from embryos of a Drosophila Huntington's Disease (HD) model.