Morphological Neuron Classification Based on Dendritic Tree Hierarchy

Morphological classification of neurons based on Sugeno fuzzy integration and multi-classifier fusion

In order to extract more important morphological features of neuron images and achieve accurate classification of the neuron type, a method is proposed that uses Sugeno fuzzy integral integration of three optimized deep learning models, namely AlexNet, VGG11_bn, and ResNet-50. Firstly, using the pre-trained model of AlexNet and the output layer is fine-tuned to improve the model's performance. Secondly, in the VGG11_bn network, Global Average Pooling (GAP) is adopted to replace the traditional fully connected layer to reduce the number of parameters. Additionally, the generalization ability of the model is improved by transfer learning. Thirdly, the SE(squeeze and excitation) module is added to the ResNet-50 variant ResNeXt-50 to adjust the channel weight and capture the key information of the input data. The GELU activation function is used to better fit the data distribution. Finally, Sugeno fuzzy integral is used to fuse the output of each model to get the final classification result. The experimental results showed that on the Img_raw, Img_resample and Img_XYalign dataset, the accuracy of 4-category classification reached 98.04%, 91.75% and 93.13%, respectively, and the accuracy of 12-category classification reached 97.82%, 85.68% and 87.60%, respectively. The proposed method has good classification performance in the morphological classification of neurons.

Graph Representation Learning for Large-Scale Neuronal Morphological Analysis

The analysis of neuronal morphological data is essential to investigate the neuronal properties and brain mechanisms. The complex morphologies, absence of annotations, and sheer volume of these data pose significant challenges in neuronal morphological analysis, such as identifying neuron types and large-scale neuron retrieval, all of which require accurate measuring and efficient matching algorithms. Recently, many studies have been conducted to describe neuronal morphologies quantitatively using predefined measurements. However, hand-crafted features are usually inadequate for distinguishing fine-grained differences among massive neurons. In this article, we propose a novel morphology-aware contrastive graph neural network (MACGNN) for unsupervised neuronal morphological representation learning. To improve the retrieval efficiency in large-scale neuronal morphological datasets, we further propose Hash-MACGNN by introducing an improved deep hash algorithm to train the network end-to-end to learn binary hash representations of neurons. We conduct extensive experiments on the largest dataset, NeuroMorpho, which contains more than 100 000 neurons. The experimental results demonstrate the effectiveness and superiority of our MACGNN and Hash-MACGNN for large-scale neuronal morphological analysis.

Quantifying neuronal structural changes over time using dynamic morphometrics

Brain circuit development involves tremendous structural formation and rearrangement of dendrites, axons, and the synaptic connections between them. Direct studies of neuronal morphogenesis are now possible through recent developments in multiple technologies, including single-neuron labeling, time-lapse imaging in intact tissues, and 4D rendering software capable of tracking neural growth over periods spanning minutes to days. These methods allow detailed quantification of structural changes of neurons over time, called dynamic morphometrics, providing new insights into fundamental growth patterns, underlying molecular mechanisms, and the intertwined influences of external factors, including neural activity, and intrinsic genetic programs. Here, we review the methods of dynamic morphometrics sampling and analyses, focusing on their applications to studies of activity-driven dendritogenesis in vertebrate systems.

New morphological features based on the Sholl analysis for automatic classification of traced neurons

BACKGROUND

This article addresses the automatic classification of reconstructed neurons through their morphological features. The purpose was to extend the capabilities of the L-Measure software.

METHODS

New morphological features were developed, based on modifications of the conventional Sholl analysis. The lengths of the compartments, as well as their volumes, were added to the features used in the classical analysis in order to improve the results during automatic neuron classification. FSM were used to obtain subsets of lower cardinality from the full feature sets and the usefulness of these subsets was tested through their use in supervised classification tasks. The study was based on two types of neurons belonging to mice: pyramidal and GABAergic interneurons. Furthermore, a set of pyramidal neurons belonging to Later 4 and Layer 5 was analyzed.

RESULTS

RF classifier shown the best performance combined with a Wrapper method.U-WNAD set allowed to obtain higher values than WN, A and D in all cases and better results than LM for the filters and wrappers FSM. U-LM-WNAD set, led to the highest AUC values for all the FSM studied. Similar results for different regions of cortex were obtained. Comparison with Existing Methods The new features exhibited high discriminatory power with which the values of AUC and Acc obtained in the experiments exceeded those obtained using only the features provided by L-Measure.

CONCLUSIONS

The highest values of AUC and Acc were obtained from the sets U-WNAD and U-LM-WNAD, evidencing the discriminatory power of the new proposed features.

A Method for the Symbolic Representation of Neurons

The field of neuroanatomy has progressed considerably in recent decades, thanks to the emergence of novel methods which provide new insights into the organization of the nervous system. These new methods have produced a wealth of data that needs to be analyzed, shifting the bottleneck from the acquisition to the analysis of data. In other disciplines, such as in many engineering areas, scientists and engineers are dealing with increasingly complex systems, using hierarchical decompositions, graphical models and simplified schematic diagrams for analysis and design processes. This approach makes it possible for users to simultaneously combine global system views and very detailed representations of specific areas of interest, by selecting appropriate representations for each of these views. In this way, users can concentrate on specific details while also maintaining a general system overview - a capability that is essential for understanding structure and function whenever complexity is an issue. Following this approach, this paper focuses on a graphical tool designed to help neuroanatomists to better understand and detect morphological characteristics of neuronal cells. The method presented here, based on a symbolic representation that can be tailored to enhance a particular range of features of a neuron or neuron set, has proven to be useful for highlighting particular geometries that may be hidden due to the complexity of the analysis tasks and the richness of neuronal morphologies. A software tool has been developed to generate graphical representations of neurons from 3D computer-aided reconstruction files.