No abstract

To the date, the Coronavirus disease 2019 (COVID-19) is still spreading around the world. Reverse transcription polymerase chain reaction (RT-PCR), which is regarded as the gold standard by the anti-epidemic front. Unfortunately, due to its lack of sensitivity (only 60%~71%), unstability, long processing time, some alternative diagnostic tools including computed tomography (CT) have been developed using convolutional neural networks (CNNs). This paper retrospectively collected 3227 CT scans (including 1601 COVID-19 positive and 1626 negative samples), on which ResNet-18 outperforms all three classical ResNets with the precision of 0.971, accuracy of 0.943, F1 of 0.942, sensitivity of 0.914, specificity of 0.973 and AUC of 0.985 respectively. Finally, the visualization technique classification activation map (CAM) was applied for lesions localization.

High-dimensional large sample data sets, between feature variables and between samples, may cause some correlative or repetitive factors, occupy lots of storage space, and consume much computing time. Using the Elman neural network to deal with them, too many inputs will influence the operating efficiency and recognition accuracy; too many simultaneous training samples, as well as being not able to get precise neural network model, also restrict the recognition accuracy. Aiming at these series of problems, we introduce the partial least squares (PLS) and cluster analysis (CA) into Elman neural network algorithm, by the PLS for dimension reduction which can eliminate the correlative and repetitive factors of the features. Using CA eliminates the correlative and repetitive factors of the sample. If some subclass becomes small sample, with high-dimensional feature and fewer numbers, PLS shows a unique advantage. Each subclass is regarded as one training sample to train the different precise neural network models. Then simulation samples are discriminated and classified into different subclasses, using the corresponding neural network to recognize it. An optimized Elman neural network classification algorithm based on PLS and CA (PLS-CA-Elman algorithm) is established. The new algorithm aims at improving the operating efficiency and recognition accuracy. By the case analysis, the new algorithm has unique superiority, worthy of further promotion.

At the end of 2019, the outbreak of the COVID-19 epidemic brought huge economic losses all around the world, and also seriously affect human work, life and study. A large number of infected patients brought huge workload to doctors, but deep learning methods can effectively assist their diagnosis. This paper is based on Faster R-CNN, an end-to-end target detection model, to realize the detection of lesions in CT images of the novel coronavirus, which contributes to track the later condition of the confirmed patients and conduct timely treatment. Firstly, Kmeans++ was carried out to cluster the dimensions of the bounding box of the ground truth in annotated CT images, and appropriate anchors sizes and ratios were selected. Then, the performance of the Faster R-CNN model based on VGG-16 and ResNet-50 on the original datasets and the augment datasets is compared. Finally, the results show that, in the enhanced dataset, the Faster R-CNN model based on VGG-16 achieved a better performance, the Recall and Precision of which on the overall test set reached 68.12% and 65.58% respectively, and the missed detection rate(MR) was 31.88%.