JavadiMoghaddam SeyyedMohammad, Gholamalinejad Hossain
Department of Computer Engineering, Bozorgmehr University of Qaenat, Qaen, Iran.
Department of Computer Science, Bozorgmehr University of Qaenat, Qaen. Iran.
Biomed Signal Process Control. 2021 Sep;70:102987. doi: 10.1016/j.bspc.2021.102987. Epub 2021 Jul 21.
The novel Coronavirus named COVID-19 that World Health Organization (WHO) announced as a pandemic rapidly spread worldwide. Fast diagnosis of the virus infection is critical to prevent further spread of the virus, help identify the infected population, and cure the patients. Due to the increasing rate of infection and the limitations of the diagnosis kit, auxiliary detection tools are needed. Recent studies show that a deep learning model that comes up with the salient information of CT images can aid in the COVID-19 diagnosis. This study proposes a novel deep learning structure that the pooling layer of this model is a combination of pooling and the Squeeze Excitation Block (SE-block) layer. The proposed model uses Batch Normalization and Mish Function to optimize convergence time and performance of COVID-19 diagnosis. A dataset of two public hospitals was used to evaluate the proposed model. Moreover, it was compared to some different popular deep neural networks (DNN). The results expressed an accuracy of 99.03 with a recognition time of test mode of 0.069 ms in graphics processing unit (GPU). Furthermore, the best network results in classification metrics parameters and real-time applications belong to the proposed model.
世界卫生组织（WHO）宣布为大流行病的新型冠状病毒COVID-19在全球迅速传播。快速诊断病毒感染对于防止病毒进一步传播、帮助识别感染人群以及治愈患者至关重要。由于感染率不断上升以及诊断试剂盒的局限性，需要辅助检测工具。最近的研究表明，能够提取CT图像显著信息的深度学习模型有助于COVID-19的诊断。本研究提出了一种新颖的深度学习结构，该模型的池化层是池化与挤压激励块（SE-block）层的组合。所提出的模型使用批量归一化和米什函数来优化COVID-19诊断的收敛时间和性能。使用两家公立医院的数据集来评估所提出的模型。此外，还将其与一些不同的流行深度神经网络（DNN）进行了比较。结果表明，在图形处理单元（GPU）中，测试模式的识别时间为0.069毫秒时，准确率为99.03。此外，在分类指标参数和实时应用方面，最佳网络结果属于所提出的模型。
