COVID-19 Pneumonia Level Detection using Deep Learning Algorithm

The first COVID-19 confirmed case is reported in Wuhan, China and spread across the globe with unprecedented impact on humanity. Since this pandemic requires pervasive diagnosis, it is significant to develop smart, fast and efficient detection technique. To this end, we developed an Artificial Intelligence (AI) engine to classify the lung inflammation level (mild, progressive, severe stage) of the COVID-19 confirmed patient. In particular, the developed model consists of two phases; in the first phase, we calculate the volume and density of lesions and opacities of the CT images of the confirmed COVID-19 patient using Morphological approaches. In the second phase, the second phase classifies the pneumonia level of the confirmed COVID-19 patient. To achieve precise classification of lung inflammation, we use modified Convolution Neural Network (CNN) and k-Nearest Neighbor (kNN). The result of the experiments show that the utilized models can provide the accuracy up to 95.65\% and 91.304 \% of CNN and kNN respectively.

[1]  Fabian Schilling,et al.  The Effect of Batch Normalization on Deep Convolutional Neural Networks , 2016 .

[2]  Yan Zhao,et al.  Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus-Infected Pneumonia in Wuhan, China. , 2020, JAMA.

[3]  Bruno P Roquette,et al.  Prediction of admission in pediatric emergency department with deep neural networks and triage textual data , 2020, Neural Networks.

[4]  Yaozong Gao,et al.  Lung Infection Quantification of COVID-19 in CT Images with Deep Learning , 2020, ArXiv.

[5]  A. bin Abdullah,et al.  Supervised learning algorithms for visual object categorization , 2010 .

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Lian-lian Wu,et al.  Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography: a prospective study , 2020, medRxiv.

[8]  Chong-Wah Ngo,et al.  Towards optimal bag-of-features for object categorization and semantic video retrieval , 2007, CIVR '07.

[9]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[10]  S. Lindstrom,et al.  First Case of 2019 Novel Coronavirus in the United States , 2020, The New England journal of medicine.

[11]  W. Marsden.  I and J , 2012 .

[12]  Michael Milford,et al.  Deep learning features at scale for visual place recognition , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Long Jiang Zhang,et al.  Coronavirus Disease 2019 (COVID-19): A Perspective from China , 2020, Radiology.

[14]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[15]  Ivanna K. Timotius,et al.  Evaluation of Edge Orientation Histograms in smile detection , 2014, 2014 6th International Conference on Information Technology and Electrical Engineering (ICITEE).

[16]  Ting Yu,et al.  Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study , 2020, The Lancet.

[17]  Neha Sharma,et al.  An Analysis Of Convolutional Neural Networks For Image Classification , 2018 .