LDN-SNP: SNP-based lightweight deep network for CT image segmentation of COVID-19

The rapid prevalence and spread of 2019 coronavirus (COVID-19) has brought tremendous impact and damage to the world’s health and economy. Chest CT images have been used as an important screening and diagnostic tool in identifying and managing COVID-19 infection, and the deep learning models have been successfully used in COVID-19 CT image segmentation. However, they encounter some challenges, especially the limited labeled samples and large models with huge numbers of training parameters. To address these challenges, this paper proposes a lightweight segmentation network for COVID-19 CT images, termed as LDN-SNP network. The LDN-SNP network is based on a new type of neuron model, SNP-type neurons. Based on SNP-type neurons, we design four convolution modules. The LDN-SNP network is composed of encoder and decoder, where the encoder is stacked by the first three modules, while the decoder is stacked by the fourth module. The proposed LDN-SNP network contains only 81316 training parameters. Three benchmark CT image data sets of COVID-19 are used to evaluate the proposed LDN-SNP network and compare the eleven state-of-the-art deep learning networks. LDN-SNP has several significant advantages: (1) It introduces a new neuron model and gives its mathematical model, which is different from the traditional neuron model; (2) It has only 81 K parameters and is therefore not prone to overfitting; (3) It is computationally efficient and therefore convenient for subsequent practical deployment. Experimental results demonstrate the advantages of the proposed LDN-SNP network for CT image segmentation of COVID-19. •A lightweight segmentation network is proposed for COVID-19 CT image segmentation•A new type of neuron model is introduced, termed SNP-type neurons.•The segmentation network is entirely designed based on the SNP-type neuron model.