Image Classification of Covid-19 Pneumonia Based on Mask-EfficientNet

Wu Wang

¹ School of Mathematics and Computer Science, Yunnan Minzu University, 2929 Yuehua Street, Kunming, 650500, China

² Key Laboratory for Research in Galaxies and Cosmology, Shanghai Astronomical Observatory, Chinese Academy of Sciences, 80 Nandan Rd., Shanghai 200030, China

Novel coronavirus is a serious disease-causing virus which spreads through the air, such a highly contagious virus will cause great harm to the body after disease. After the Novel coronavirus infects someone, viruses hidden in the body will spread rapidly and widely in the population as the carrier moves, that cause catastrophic consequences. Therefore, how to quickly detect the infection of novel coronary pneumonia has become an urgent issue. Analysing the lung image of Computed Tomography (CT) is an important method to accurately detect whether people is infected by novel coronavirus in medical practice. In this paper, firstly, we use the binarized features of the novel coronary pneumonia image, and then use the features of histogram and mask as additional features, finally we design an improved network based on Efficient-Net. Through comparative experiments with other mainstream Convolutional Neural Network(CNN) networks, it is found that the model proposed in this paper reduces the parameters of the model and improves the detection accuracy.

EfficientNet, image classification, Convolutional Neural Network, Covid-19

Xiao Xu, Wu Wang, Quanfeng Xu (2022). Image Classification of Covid-19 Pneumonia Based on Mask-EfficientNet. Journal of Networking and Network Applications, Volume 2, Issue 4, pp. 153–160. https://doi.org/10.33969/J-NaNA.2022.020403.

[1] Jeffrey P Kanne. Chest ct findings in 2019 novel coronavirus (2019-ncov) infections from wuhan, china: key points for the radiologist. Radiology, 2020.

[2] Muhammad EH Chowdhury, Tawsifur Rahman, Amith Khandakar, Rashid Mazhar, Muhammad Abdul Kadir, Zaid Bin Mahbub, Khan-dakar Reajul Islam, Muhammad Salman Khan, Atif Iqbal, and Nasser Al Emadi. Can ai help in screening viral and covid-19 pneumonia? IEEE Access, 8:132665–132676, 2020.

[3] Sakshi Indolia, Anil Kumar Goswami, Surya Prakesh Mishra, and Pooja Asopa. Conceptual understanding of convolutional neural network-a deep learning approach. Procedia computer science, 132:679–688, 2018.

[4] Ahmad Chaddad, Lama Hassan, and Christian Desrosiers. Deep cnn models for predicting covid-19 in ct and x-ray images. Journal of medical imaging, 8(S1):014502, 2021.

[5] Ramin Ranjbarzadeh, Saeid Jafarzadeh Ghoushchi, Malika Bendechache, Amir Amirabadi, Mohd Nizam Ab Rahman, Soroush Baseri Saadi, Amirhossein Aghamohammadi, and Mersedeh Kooshki Forooshani. Lung infection segmentation for covid-19 pneumonia based on a cascade convolutional network from ct images. BioMed Research International, 2021, 2021.

[6] Milletari Fausto, Navab Nassir, and Ahmadi Seyed-Ahmad. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV), pages 565–571. IEEE, 2016.

[7] Skourt Brahim Ait, El Hassani Abdelhamid, and Aicha Majda. Lung ct image segmentation using deep neural networks. Procedia Computer Science, 127:109–113, 2018.

[8] Qingzeng Song, Lei Zhao, and Xingke Luo. Using deep learning for classification of lung nodules on computed tomography images. Journal of healthcare engineering, 2017, 2017.

[9] Karen Simonyan and Andrew Zisserman. Very deep convolu-tional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.

[10] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.

[11] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017.

[12] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019.

[13] Sugimori and Hiroyuki. Classification of computed tomography images in different slice positions using deep learning. Journal of healthcare engineering, 2018, 2018.

[14] Hussain Mahbub, Bird Jordan J, and Faria Diego R. A study on cnn transfer learning for image classification. In UK Workshop on computational Intelligence, pages 191–202. Springer, 2018. 

[15] Shanshan Wang, Tao Zhang, and Fei Li. A synergic neural network for medical image classification based on attention mechanism. In 2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML), pages 82–87. IEEE, 2022.

[16] Hongyu Zhou, Shuang Yu, Bian Cheng, Yifan Hu, Kai Ma, and Yefeng Zheng. Comparing to learn: Surpassing imagenet pretraining on radiographs by comparing image representations. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 398–407. Springer, 2020.