Abstract
The new coronavirus has caused more than one million deaths and continues to spread rapidly. This virus targets the lungs, causing respiratory distress which can be mild or severe. The X-ray or computed tomography (CT) images of lungs can reveal whether the patient is infected with COVID-19 or not. Many researchers are trying to improve COVID-19 detection using artificial intelligence. Our motivation is to develop an automatic method that can cope with scenarios in which preparing labeled data is time consuming or expensive. In this article, we propose a Semi-supervised Classification using Limited Labeled Data (SCLLD) relying on Sobel edge detection and Generative Adversarial Networks (GANs) to automate the COVID-19 diagnosis. The GAN discriminator output is a probabilistic value which is used for classification in this work. The proposed system is trained using 10,000 CT scans collected from Omid Hospital, whereas a public dataset is also used for validating our system. The proposed method is compared with other state-of-the-art supervised methods such as Gaussian processes. To the best of our knowledge, this is the first time a semi-supervised method for COVID-19 detection is presented. Our system is capable of learning from a mixture of limited labeled and unlabeled data where supervised learners fail due to a lack of sufficient amount of labeled data. Thus, our semi-supervised training method significantly outperforms the supervised training of Convolutional Neural Network (CNN) when labeled training data is scarce. The 95% confidence intervals for our method in terms of accuracy, sensitivity, and specificity are 99.56 ± 0.20%, 99.88 ± 0.24%, and 99.40 ± 0.18%, respectively, whereas intervals for the CNN (trained supervised) are 68.34 ± 4.11%, 91.2 ± 6.15%, and 46.40 ± 5.21%.
- [1] 2021. Retrieved May 1, 2021 from https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200513-covid-19-sitrep-114.pdf?sfvrsn=17ebbbe_4.Google Scholar
- [2] 2021. Retrieved May 1, 2021 from https://www.kaggle.com/bayazjafarli/covid19-covidpneumanianormal-cases.Google Scholar
- [3] 2021. Retrieved May 1, 2021 from https://coronavirus.jhu.edu/map.html.Google Scholar
- [4] 2021. Retrieved May 1, 2021 from https://utswmed.org/medblog/covid19-testing-methods/.Google Scholar
- [5] . 2020. Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases. Radiology 296, 2 (2020), E32–E40.Google ScholarCross Ref
- [6] . 2020. Risk factors prediction, clinical outcomes, and mortality in COVID-19 patients. Journal of Medical Virology 93 (2020), 2307–2320.Google Scholar
- [7] . 2020. Coronary artery disease detection using artificial intelligence techniques: A survey of trends, geographical differences and diagnostic features 1991–2020. Computers in Biology and Medicine 128 (2020), 104095.Google Scholar
- [8] . 2020. COVID_MTNet: Covid-19 detection with multi-task deep learning approaches. arXiv:2004.03747. https://arxiv.org/abs/2004.03747.Google Scholar
- [9] . 2016. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Transactions on Medical Imaging 35, 5 (2016), 1207–1216.Google ScholarCross Ref
- [10] . 2020. Covid-19: Automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine 43, 2 (2020), 635–640.Google ScholarCross Ref
- [11] . 2021. COVIDiag: A clinical CAD system to diagnose COVID-19 pneumonia based on CT findings. European Radiology 31, 1 (2021), 121–130.Google ScholarCross Ref
- [12] . 2020. Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks. Computers in Biology and Medicine 121 (2020), 103795.Google ScholarCross Ref
- [13] . 2020. Objective evaluation of deep uncertainty predictions for COVID-19 detection. arXiv:2012.11840. https://arxiv.org/abs/2012.11840.Google Scholar
- [14] . 2014. Exact inference for Gaussian process regression in case of big data with the Cartesian product structure. arXiv:1403.6573. https://arxiv.org/abs/1403.6573.Google Scholar
- [15] . 2020. Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: A descriptive study. The Lancet 395, 10223 (2020), 507–513.Google ScholarCross Ref
- [16] . 2020. Early diagnosis of COVID-19-affected patients based on X-ray and computed tomography images using deep learning algorithm. Soft Computing (2020), 1–9.Google ScholarDigital Library
- [17] . 2015. Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution CT. Investigative Radiology 50, 4 (2015), 261.Google ScholarCross Ref
- [18] . 2021. Identification of clinical features associated with mortality in COVID-19 patients. medRxiv. https://doi.org/10.1101/2021.04.19.21255715Google Scholar
- [19] . 2020. Sensitivity of chest CT for COVID-19: Comparison to RT-PCR. Radiology 296, 2 (2020), E115–E117.Google ScholarCross Ref
- [20] . 2003. Unsupervised learning. In Summer School on Machine Learning. Springer, 72–112.Google Scholar
- [21] . 2014. Generative adversarial networks. arXiv:1406.2661. https://arxiv.org/abs/1406.2661. Google ScholarDigital Library
- [22] . 2020. Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications. Neurocomputing 410 (2020), 237–270.Google ScholarCross Ref
- [23] . 2020. Rapid AI development cycle for the coronavirus (COVID-19) pandemic: Initial results for automated detection & patient monitoring using deep learning CT image analysis. arXiv:2003.05037. https://arxiv.org/abs/2003.05037.Google Scholar
- [24] . 2020. COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in x-ray images. arXiv:2003.11055. https://arxiv.org/abs/2003.11055.Google Scholar
- [25] . 2015. Generalized entropy based semi-supervised learning. In 2015 IEEE/ACIS 14th International Conference on Computer and Information Science (ICIS’15). IEEE, 259–263.Google Scholar
- [26] . 2020. Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning. Journal of Biomolecular Structure and Dynamics 39 (2020), 5682-5689.Google Scholar
- [27] . 2021. CovidCTNet: An open-source deep learning approach to identify covid-19 using small cohort of CT images. npj Digit. Med. 4, 29 (2021). https://doi.org/10.1038/s41746-021-00399-3Google Scholar
- [28] . 2020. Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: A review. arXiv:2007.01285. https://arxiv.org/abs/2007.01285.Google Scholar
- [29] . 2021. CNN AE: Convolution neural network combined with autoencoder approach to detect survival chance of COVID 19 patients. Scientific Reports 11, 1 (2021), 1–18.Google Scholar
- [30] . 2020. COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image: Model development and validation. Journal of Medical Internet Research 22, 6 (2020), e19569.Google ScholarCross Ref
- [31] . 2020. Blockchain-federated-learning and deep learning models for covid-19 detection using CT imaging. IEEE Sensors Journal 21, 14 (2021), 16301–16314.
DOI: 10.1109/JSEN.2021.3076767Google Scholar - [32] . 2020. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology 296 (2020), E65–E71.Google ScholarCross Ref
- [33] . 2018. Generative adversarial networks for generation and classification of physical rehabilitation movement episodes. International Journal of Machine Learning and Computing 8, 5 (2018), 428.Google Scholar
- [34] . 2014. Efficient mini-batch training for stochastic optimization. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 661–670. Google ScholarDigital Library
- [35] . 2018. Reliable semi-supervised learning when labels are missing at random. arXiv:1811.10947. https://arxiv.org/abs/1811.10947.Google Scholar
- [36] . 2021. Diagnosing COVID-19 pneumonia from X-ray and CT images using deep learning and transfer learning algorithms. In Multimodal Image Exploitation and Learning 2021, Vol. 11734. International Society for Optics and Photonics, 117340E.Google Scholar
- [37] . 2021. Automatic detection of coronavirus disease (COVID-19) using x-ray images and deep convolutional neural networks. Pattern Anal Applic 24 (2021), 1207–1220. https://doi.org/10.1007/s10044-021-00984-yGoogle Scholar
- [38] . 2020. A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. European Radiology 30, 12 (2020), 6517–6527.Google ScholarCross Ref
- [39] . 2009. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. IGI Global. Google ScholarDigital Library
- [40] . 2020. A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-Scan images. Chaos, Solitons & Fractals 140 (2020), 110190.Google ScholarCross Ref
- [41] . 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434. https://arxiv.org/abs/1511.06434.Google Scholar
- [42] . 2006. Gaussian Processes for Machine Learning. MIT Press. Cambridge, MA.Google Scholar
- [43] . 2020. A novel and reliable deep learning web-based tool to detect COVID-19 infection form chest CT-scan. arXiv:2006.14419. https://arxiv.org/abs/2006.14419.Google Scholar
- [44] . 2016. Improved techniques for training GANs. Advances in Neural Information Processing Systems 29 (2016), 2234–2242. Google ScholarDigital Library
- [45] . 2017. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision. 618–626.Google ScholarCross Ref
- [46] . 2020. Detection of coronavirus disease (COVID-19) based on deep features and support vector machine.
DOI: 10.33889/IJMEMS.2020.5.4.052Google Scholar - [47] . 2021. Diagnosis of COVID-19 using CT scan images and deep learning techniques. Emergency Radiology (2021), 1–9.
DOI: 10.1007/s10140-020-01886-yGoogle Scholar - [48] . 2020. CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with K-means clustering.
DOI : https://doi.org/10.20944/preprints202007.0650.v1Google Scholar - [49] . 2021. Fusion of convolution neural network, support vector machine and Sobel filter for accurate detection of COVID-19 patients using X-ray images. Biomedical Signal Processing and Control 68 (2021), 102622.Google ScholarCross Ref
- [50] . 2021. A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: A retrospective study of 196 patients. Annals of Translational Medicine 9, 3 (2021).Google ScholarCross Ref
- [51] . 2021. Epileptic seizure detection using deep learning techniques: A review. International Journal of Environmental Research and Public Health 18, 11 (2021), 5780.Google Scholar
- [52] . 2020. Automated detection and forecasting of COVID-19 using deep learning techniques: A review. arXiv:2007.10785. https://arxiv.org/abs/2007.10785.Google Scholar
- [53] . 2021. Deep learning enables accurate diagnosis of novel coronavirus (COVID-19) with CT images. IEEE/ACM Transactions on Computational Biology and Bioinformatics (2021).Google ScholarDigital Library
- [54] . 2020. Characteristics of COVID-19 infection in Beijing. Journal of Infection 80, 4 (2020), 401–406.Google ScholarCross Ref
- [55] . 2019. Three-stage network for age estimation. CAAI Transactions on Intelligence Technology 4, 2 (2019), 122–126.Google ScholarDigital Library
- [56] . 2020. OVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest x-ray images. Scientific Reports 10, 1 (2020), 1–12.Google Scholar
- [57] . 2021. A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19). European Radiology (2021), 1–9.Google Scholar
- [58] . 2021. COVID-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Information Fusion 67 (2021), 208–229.Google ScholarCross Ref
- [59] . 2020. A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering 6, 10 (2020), 1122–1129.Google ScholarCross Ref
- [60] . 2020. Chest X-ray findings monitoring COVID-19 disease course and severity. Egyptian Journal of Radiology and Nuclear Medicine 51, 1 (2020), 1–18.Google ScholarCross Ref
- [61] . 2020. Diagnosis of COVID-19: Facts and challenges. New Microbes and New Infections (2020), 100761.Google ScholarCross Ref
- [62] . 2020. COVID-19 screening on chest x-ray images using deep learning based anomaly detection. https://europepmc.org/article/ppr/ppr346108.Google Scholar
- [63] . 2020. A seven-layer convolutional neural network for chest CT based COVID-19 diagnosis using stochastic pooling. IEEE Sensors Journal (2020).Google Scholar
- [64] . 2020. CVID-CT-Dataset: A CT scan dataset about COVID-19. arXiv:2003.13865. https://arxiv.org/abs/2003.13865.Google Scholar
Index Terms
- Uncertainty-Aware Semi-Supervised Method Using Large Unlabeled and Limited Labeled COVID-19 Data
Recommendations
Semi-supervised learning using multiple clusterings with limited labeled data
Supervised classification consists in learning a predictive model using a set of labeled samples. It is accepted that predictive models accuracy usually increases as more labeled samples are available. Labeled samples are generally difficult to obtain ...
Learning Instance Weighted Naive Bayes from labeled and unlabeled data
In real-world data mining applications, it is often the case that unlabeled instances are abundant, while available labeled instances are very limited. Thus, semi-supervised learning, which attempts to benefit from large amount of unlabeled data ...
Semi-supervised multi-label classification using incomplete label information
Highlights- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
AbstractClassifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...
Comments