Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks

Neuronal soma segmentation is a crucial step for the quantitative analysis of neuronal morphology. Automated neuronal soma segmentation methods have opened up the opportunity to improve the time-consuming manual labeling required during the neuronal soma morphology reconstruction for large-scale images. However, the presence of touching neuronal somata and variable soma shapes in images brings challenges for automated algorithms. This study proposes a neuronal soma segmentation method combining 3D U-shaped fully convolutional neural networks with multi-task learning. Compared to existing methods, this technique applies multi-task learning to predict the soma boundary to split touching somata, and adopts U-shaped architecture convolutional neural network which is effective for a limited dataset. The contour-aware multi-task learning framework is applied to the proposed method to predict the masks of neuronal somata and boundaries simultaneously. In addition, a spatial attention module is embedded into the multi-task model to improve neuronal soma segmentation results. The Nissl-stained dataset captured by the micro-optical sectioning tomography system is used to validate the proposed method. Following comparison to four existing segmentation models, the proposed method outperforms the others notably in both localization and segmentation. The novel method has potential for high-throughput neuronal soma segmentation in large-scale optical imaging data for neuron morphology quantitative analysis.

Automated summary

The study introduces a novel neuronal soma segmentation method that combines 3D U-shaped fully convolutional neural networks with multi-task learning, aiming to address the challenges posed by touching neuronal somata and variable soma shapes in images. This technique outperforms existing methods by applying multi-task learning to predict soma boundaries for splitting touching somata and utilizing a U-shaped convolutional neural network effective for limited datasets. The proposed method also incorporates a contour-aware multi-task learning framework and a spatial attention module to simultaneously predict masks of neuronal somata and boundaries, resulting in improved segmentation results for high-throughput analysis of large-scale optical imaging data.