Automated identification of neural cells in the multi-photon images using deep-neural networks

TL;DR

This paper presents an automated deep learning approach using U-Net and transfer learning models to identify and classify neural cells in multi-photon images, significantly aiding large-scale neuroscience data analysis.

Contribution

It introduces a novel pipeline combining U-Net segmentation with transfer learning for cell classification, demonstrating improved accuracy in neural cell identification.

Findings

InceptionV3 achieved the best classification performance.

The method automates neural cell segmentation and classification.

Deep learning enhances efficiency in processing large neuroscience datasets.

Abstract

The advancement of the neuroscientific imaging techniques has produced an unprecedented size of neural cell imaging data, which calls for automated processing. In particular, identification of cells from two photon images demands segmentation of neural cells out of various materials and classification of the segmented cells according to their cell types. To automatically segment neural cells, we used U-Net model, followed by classification of excitatory and inhibitory neurons and glia cells using a transfer learning technique. For transfer learning, we tested three public models of resnet18, resnet50 and inceptionv3, after replacing the fully connected layer with that for three classes. The best classification performance was found for the model with inceptionv3. The proposed application of deep learning technique is expected to provide a critical way to cell identification in the era of big neuroscience data.