Method and system for automatically detecting single neuron dendritic spine in fluorescence image

Abstract

The invention discloses an automatic detection method and system for a single neuron dendritic spine in a fluorescence image. The method comprises the steps: splitting a to-be-detected three-dimensional fluorescence image into a plurality of image blocks, carrying out the projection splicing of the image blocks, and obtaining a target to-be-recognized image corresponding to all dendrites of a single neuron; uniformly scattering seed points along the single neuron dendritic skeleton, and taking neighborhood image blocks taking the seed points as centers from the target to-be-identified image; performing dendrite spine segmentation on each neighborhood image block by using a semantic segmentation network based on a deep residual network structure and a multi-scale cavity convolution structure to obtain a dendrite spine segmentation image, and fusing the dendrite spine segmentation images; and carrying out connected domain analysis on the fused dendritic spine segmentation map to obtain asingle connected domain, splitting the dendritic spine on each connected domain into one or more dendritic spines, and combining the dendritic spines in each connected domain to obtain a single neuron dendritic spine segmentation result. According to the invention, the accuracy of identifying the dendritic spine is greatly improved.

Description

technical field [0001] The invention belongs to the field of neuroscience image analysis, and more specifically relates to an automatic detection method and system for dendritic spines of a single neuron in a fluorescent image based on a deep semantic segmentation network. Background technique [0002] Neurons are mainly composed of cell bodies, dendrites and axons, and different neurons are connected to each other and transmit information through synapses. Many spine-like protrusions are visible on the surface of dendrites, called dendritic spines, which are a site for the connection between dendrites and axon terminals of neurons to form synapses. Medical research shows that dendritic spines have electrical properties and plasticity, which are related to the growth and development of nerve cells and the establishment and disappearance of synapses, and play a key role in human brain cognition, learning, memory and neurological diseases. Therefore, the detection of dendriti...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for automatic detection of single neuron dendritic spines in fluorescent images, thereby solving the problem of existing detection of neuron dendritic spines under big data. It is time-consuming and labor-intensive, and it is difficult to take into account the technical problems of detecting all dendritic spines with different shapes, sizes and attachment degrees.

Images