Shui-Hua Wang1,2, Yin Zhang3, Xiaochun Cheng4, Xin Zhang5, Yu-Dong Zhang6. 1. School of Computer Science, Henan Polytechnic University, China, Henan 454001, China. 2. School of Architecture Building and Civil Engineering, Loughborough University, Loughborough LE11 3TU, UK. 3. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. 4. School of Science & Technology, Middlesex University, London NW4 4BT, UK. 5. Department of Medical Imaging, The Fourth People's Hospital of Huai'an, Huai'an, Jiangsu Province 223002, China. 6. School of Informatics, University of Leicester, Leicester LE1 7RH, UK.
Abstract
AIM: COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. METHODS: In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. RESULTS: The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. CONCLUSION: This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.
AIM: COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. METHODS: In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. RESULTS: The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. CONCLUSION: This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.
Authors: Hoon Ko; Heewon Chung; Wu Seong Kang; Kyung Won Kim; Youngbin Shin; Seung Ji Kang; Jae Hoon Lee; Young Jun Kim; Nan Yeol Kim; Hyunseok Jung; Jinseok Lee Journal: J Med Internet Res Date: 2020-06-29 Impact factor: 5.428
Authors: Joseph Paul Cohen; Lan Dao; Karsten Roth; Paul Morrison; Yoshua Bengio; Almas F Abbasi; Beiyi Shen; Hoshmand Kochi Mahsa; Marzyeh Ghassemi; Haifang Li; Tim Duong Journal: Cureus Date: 2020-07-28
Authors: Arthur A M Teodoro; Douglas H Silva; Muhammad Saadi; Ogobuchi D Okey; Renata L Rosa; Sattam Al Otaibi; Demóstenes Z Rodríguez Journal: J Signal Process Syst Date: 2021-11-08