Article
Biology
Junding Sun, Pengpeng Pi, Chaosheng Tang, Shui-Hua Wang, Yu-Dong Zhang
Summary: This study developed a computer-aided diagnosis system that can effectively diagnose suspected COVID-19 cases. A new pre-training method based on transfer learning with self-supervised learning and a convolutional neural network based on attention mechanism were used for feature extraction, and the highest accuracy diagnosis was achieved through a hybrid ensemble model.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
BingBing Zheng, Yu Zhu, Qin Shi, Dawei Yang, Yanmei Shao, Tao Xu
Summary: This paper proposes a mutex attention network based on deep learning for auxiliary diagnosis of COVID-19 on CT images, providing effective information for diagnosis.
APPLIED INTELLIGENCE
(2022)
Article
Engineering, Multidisciplinary
Yudong Zhang, Xin Zhang, Weiguo Zhu
Summary: The proposed ANC method achieved high accuracy in diagnosing COVID-19, outperforming 9 state-of-the-art approaches. By integrating CBAM and Grad-CAM, the diagnostic interpretability was improved, and overfitting was avoided.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2021)
Article
Computer Science, Information Systems
Akram Ali Alhadad, Omar Tarawneh, Reham R. Mostafa, Hazem M. El-Bakry
Summary: In this study, a novel approach combining residual attention with deep support vector data description (DSVDD) is proposed to diagnose COVID-19. The approach achieved high performance in classifying CT images into intact, COVID-19, and non-COVID-19 pneumonia.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Computer Science, Artificial Intelligence
Kai Hu, Yingjie Huang, Wei Huang, Hui Tan, Zhineng Chen, Zheng Zhong, Xuanya Li, Yuan Zhang, Xieping Gao
Summary: This paper introduces a novel imbalanced data classification method for COVID-19 diagnosis, which effectively addresses the issue of class imbalance through deep supervised learning with self adaptive auxiliary loss. Experiments demonstrate the superior performance of this method in COVID-19 diagnosis.
Article
Medicine, General & Internal
Lu Lou, Hong Liang, Zhengxia Wang
Summary: This paper proposes a deep learning-based COVID-19 detection method and evaluates its performance on embedded edge-computing devices. By adding attention module and mixed loss into the original VGG19 model, the method achieves parameter reduction and increased classification accuracy. The experimental results demonstrate that the proposed method is practicable and convenient on a low-cost medical edge-computing terminal.
Review
Engineering, Multidisciplinary
Xing Guo, Yu-Dong Zhang, Siyuan Lu, Zhihai Lu
Summary: The paper focuses on the research of Corona Virus Disease 2019 diagnosis, introducing the diagnosis procedure based on machine learning and seven specific methods, comparing their advantages and limitations. Despite significant achievements, challenges such as unbalanced datasets, difficulty in collecting labeled data, and poor data quality still exist in machine learning-based classification of COVID-19 images.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2022)
Review
Biochemistry & Molecular Biology
Shigao Huang, Jie Yang, Simon Fong, Qi Zhao
Summary: Artificial intelligence has been effectively utilized in various aspects of the COVID-19 crisis, accelerating the diagnosis of positive patients and providing guidance for ideal deployment in pandemics. Future applications of AI technology can help address current challenges and guide its optimal deployment in pandemics.
INTERNATIONAL JOURNAL OF BIOLOGICAL SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
R. Karthik, R. Menaka, M. Hariharan, Daehan Won
Summary: Accurate detection of COVID-19 is a challenging research topic in healthcare. This study proposes a novel CNN model that achieves precise localization and segmentation of COVID-19 infected tissues through attention mechanism and reconstruction techniques. The model achieves outstanding performance on multiple datasets.
PATTERN RECOGNITION
(2022)
Review
Mathematics
Suya Jin, Guiyan Liu, Qifeng Bai
Summary: Deep learning is a field of artificial intelligence that uses neural networks to extract patterns from large datasets. It has seen rapid development in recent years and has been successfully applied in various disciplines. This article provides an overview of deep-learning techniques, their applications in COVID-19 research, and specific examples of their use in diagnosis, prognosis, and treatment management. Deep learning can analyze medical imaging, lab test results, and other data to diagnose diseases, predict disease progression, recommend treatment plans, and assist in drug development and prevention strategies. However, challenges include the lack of diverse data and the need for more interpretable models.
Article
Computer Science, Artificial Intelligence
Xing Wu, Cheng Chen, Mingyu Zhong, Jianjia Wang, Jun Shi
Summary: The weakly-supervised deep active learning framework COVID-AL is proposed for diagnosing COVID-19, which can efficiently diagnose COVID-19 and outperforms existing active learning methods in the diagnosis.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Rokaya Rehouma, Michael Buchert, Yi-Ping Phoebe Chen
Summary: COVID-19 is a significant health challenge globally, and early detection is crucial for controlling the spread and reducing mortality rates. Machine learning has made significant progress in COVID-19 detection using medical imaging, with deep learning algorithms widely used for patient identification and achieving good predictive results.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Chunmei He, Lanqing Zheng, Taifeng Tan, Xianjun Fan, Zhengchun Ye
Summary: The study proposes a multi-attention representation network partial domain adaptation (MARPDA) method for diagnosing COVID-19. By constructing multiple attention representation networks to acquire image representations and learn knowledge from different feature spaces, the method achieves better performance in diagnosing COVID-19.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Navid Ghassemi, Afshin Shoeibi, Marjane Khodatars, Jonathan Heras, Alireza Rahimi, Assef Zare, Yu-Dong Zhang, Ram Bilas Pachori, Manuel Gorriz
Summary: The outbreak of COVID-19 has had a significant impact on people worldwide. Accurately diagnosing and isolating patients is crucial in fighting this pandemic, and medical imaging, particularly CT imaging, has been a focus of research due to its accuracy and availability. This paper presents a method using pre-trained deep neural networks and a CycleGAN model for data augmentation, achieving state-of-the-art performance with 99.60% accuracy. A dataset of 3163 images from 189 patients, collected from suspected COVID-19 cases, has been publicly made available for evaluation. The method's reliability is further assessed using calibration metrics and the Grad-CAM technique for explaining its decisions.
APPLIED SOFT COMPUTING
(2023)
Article
Biology
Yu Fu, Peng Xue, Enqing Dong
Summary: A novel method based on a densely connected attention network was proposed, which achieved highly accurate results in diagnosing cases based on chest CT images. The method effectively located lung lesions of patients infected with the coronavirus and showed excellent performance in distinguishing COVID-19, common pneumonia, and normal controls.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Vanbang Le, Dawei Yang, Yu Zhu, Bingbing Zheng, Chunxue Bai, Hongcheng Shi, Jie Hu, Changwen Zhai, Shaohua Lu
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2018)
Article
Computer Science, Information Systems
Bingbing Zheng, Yaoqi Liu, Yu Zhu, Fuli Yu, Tianjiao Jiang, Dawei Yang, Tao Xu