Abstract
Many studies on automated COVID-19 diagnosis have advanced rapidly with the increasing availability of large-scale CT annotated datasets. Inevitably, there are still a large number of unlabeled CT slices in the existing data sources since it requires considerable consuming labor efforts. Notably, cinical experience indicates that the neighboring CT slices may present similar symptoms and signs. Inspired by such wisdom, we propose DACE, a novel CNN-based deep active context estimation framework, which leverages the unlabeled neighbors to progressively learn more robust feature representations and generate a well-performed classifier for COVID-19 diagnosis. Specifically, the backbone of the proposed DACE framework is constructed by a well-designed Long-Short Hierarchical Attention Network (LSHAN), which effectively incorporates two complementary attention mechanisms, i.e., short-range channel interactions (SCI) module and long-range spatial dependencies (LSD) module, to learn the most discriminative features from CT slices. To make full use of such available data, we design an efficient context estimation criterion to carefully assign the additional labels to these neighbors. Benefiting from two complementary types of informative annotations from
-nearest neighbors, i.e., the majority of high-confidence samples with pseudo labels and the minority of low-confidence samples with hand-annotated labels, the proposed LSHAN can be fine-tuned and optimized in an incremental learning manner. Extensive experiments on the Clean-CC-CCII dataset demonstrate the superior performance of our method compared with the state-of-the-art baselines.
- . 2020. COVID_MTNet: COVID-19 detection with multi-task deep learning approaches. arxiv:2004.03747.Google Scholar
- . 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 Scholar
Cross Ref
- . 2020. Chest CT findings in coronavirus disease-19 (COVID-19): Relationship to duration of infection. Radiology 295, 3 (2020), 200463.Google Scholar
Cross Ref
- . 2019a. DualCheXNet: Dual asymmetric feature learning for thoracic disease classification in chest x-rays. Biomedical Signal Processing and Control 53 (2019), 101554.Google Scholar
Cross Ref
- . 2020. Label co-occurrence learning with graph convolutional networks for multi-label chest x-ray image classification. IEEE Journal of Biomedical and Health Informatics 24, 8 (2020), 2292–2302.Google Scholar
Cross Ref
- . 2019b. Lesion location attention guided network for multi-label thoracic disease classification in chest x-rays. IEEE Journal of Biomedical and Health Informatics 24, 7 (2019), 2016–2027.Google Scholar
- . 2018. Dynamic illness severity prediction via multi-task RNNs for intensive care unit. In Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM’18). IEEE, Los Alamitos, CA, 917–922.Google Scholar
Cross Ref
- . 2021. Dual attention multiple instance learning with unsupervised complementary loss for COVID-19 screening. Medical Image Analysis 72 (2021), 102105.Google Scholar
- . 1995. Support-vector networks. Machine Learning 20, 3 (1995), 273–297. Google Scholar
Digital Library
- . 2019. Retinal image synthesis and semi-supervised learning for glaucoma assessment. IEEE Transactions on Medical Imaging 38, 9 (2019), 2211–2218.Google Scholar
Cross Ref
- . 2020. Inf-Net: Automatic COVID-19 lung infection segmentation from CT images. IEEE Transactions on Medical Imaging 39, 8 (2020), 2626–2637.Google Scholar
Cross Ref
- . 2020. Sensitivity of chest CT for COVID-19: Comparison to RT-PCR. Radiology 296, 2 (2020), E115–E117.Google Scholar
- . 2020. Machine learning based on clinical variables and chest CT quantitative measurements for early prediction of progression risk in COVID-19 patients: A multicentre study. Lancet. Preprint, June 12, 2020.Google Scholar
- . 2012. Active learning for clinical text classification: Is it better than random sampling?Journal of the American Medical Informatics Association 19, 5 (2012), 809–816.Google Scholar
- . 2017. 3D Densely Connected Convolutional Network for the Recognition of Human Shopping Actions. Ph.D. Dissertation. Université d’Ottawa/University of Ottawa.Google Scholar
- . 2020. Accurate screening of COVID-19 using attention based deep 3D multiple instance learning. IEEE Transactions on Medical Imaging 39, 8 (2020), 2584–2594.Google Scholar
Cross Ref
- . 2018. Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6546–6555.Google Scholar
Cross Ref
- . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- . 2020a. Benchmarking deep learning models and automated model design for COVID-19 detection with chest CT scans. medRxiv. Preprint, June 17, 2020.Google Scholar
- . 2020b. Sample-efficient deep learning for COVID-19 diagnosis based on CT scans. medRxiv. Preprint, April 17, 2020.Google Scholar
- . 1992. Theory of the backpropagation neural network. In Neural Networks for Perception. Elsevier, 65–93. Google Scholar
Digital Library
- . 2020. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet 395, 10223 (2020), 497–506.Google Scholar
Cross Ref
- . 2017. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4700–4708.Google Scholar
Cross Ref
- . 2020. COVID-19 CT image synthesis with a conditional generative adversarial network. arxiv:2007.14638.Google Scholar
- . 2020. Development and Evaluation of an AI System for COVID-19 Diagnosis. Nature Communications 11 (2020), Article 5088.Google Scholar
Cross Ref
- . 2020. Diagnosis of Coronavirus Disease 2019 (COVID-19) with structured latent multi-view representation learning. IEEE Transactions on Medical Imaging 39, 8 (2020), 2606–2614.Google Scholar
Cross Ref
- . 2020c. A machine-learning method based on ocular surface features for COVID-19 screening. medRxiv. Preprint, November 2, 2020.Google Scholar
- . 2020a. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology. Online, March 19, 2020.Google Scholar
Cross Ref
- . 2020b. Auxiliary signal-guided knowledge encoder-decoder for medical report generation. arxiv:2006.03744.Google Scholar
- . 2013. Network in network. arxiv:1312.4400.Google Scholar
- . 2020. Adaptively clustering-driven learning for visual relationship detection. IEEE Transactions on Multimedia. Early access, December 10, 2020.Google Scholar
Cross Ref
- . 2016. SGDR: Stochastic gradient descent with warm restarts. arxiv:1608.03983.Google Scholar
- . 2020. Coronavirus Covid-19 has killed more people than SARS and MERS combined, despite lower case fatality rate. BMJ 368 (2020), m641.Google Scholar
- . 2019. Parting with illusions about deep active learning. arxiv:1912.05361.Google Scholar
- . 2020. Dual-sampling attention network for diagnosis of COVID-19 from community acquired pneumonia. IEEE Transactions on Medical Imaging 39, 8 (2020), 2595–2605.Google Scholar
Cross Ref
- . 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. 8026–8037. Google Scholar
Digital Library
- . 2019. Temporal self-attention network for medical concept embedding. In Proceedings of the 2019 IEEE International Conference on Data Mining (ICDM’19). IEEE, Los Alamitos, CA, 498–507.Google Scholar
Cross Ref
- . 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 Scholar
Cross Ref
- . 2020. Detection of coronavirus disease (COVID-19) based on deep features. Preprints 2020 (2020), 2020030300.Google Scholar
- . 2001. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review 5, 1 (2001), 3–55. Google Scholar
Digital Library
- . 2021. Heterogeneous data fusion for predicting mild cognitive impairment conversion. Information Fusion 66 (2021), 54–63.Google Scholar
Cross Ref
- . 2020. Large-scale screening of covid-19 from community acquired pneumonia using infection size-aware classification. arxiv:2003.09860.Google Scholar
- . 2021. Deep learning enables accurate diagnosis of novel coronavirus (COVID-19) with CT images. IEEE/ACM Transactions on Computational Biology and Bioinformatics. Online ahead of print, March 11, 2020.Google Scholar
Digital Library
- . 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. arxiv:1905.11946.Google Scholar
- . 2020a. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in Wuhan, China. JAMA 323, 11 (2020), 1061–1069.Google Scholar
Cross Ref
- . 2016. Cost-effective active learning for deep image classification. IEEE Transactions on Circuits and Systems for Video Technology 27, 12 (2016), 2591–2600. Google Scholar
Digital Library
- . 2020. COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest x-ray images. arxiv:2003.09871.Google Scholar
- . 2020d. ECA-net: Efficient channel attention for deep convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11534–11542.Google Scholar
Cross Ref
- . 2016. Diagnosis code assignment using sparsity-based disease correlation embedding. IEEE Transactions on Knowledge and Data Engineering 28, 12 (2016), 3191–3202. Google Scholar
Digital Library
- . 2020b. A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19). MedRxiv. Preprint, April 24, 2020.Google Scholar
- . 2020c. COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis. Information Fusion 68 (2020), 131–148.Google Scholar
- . 2020. A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT. IEEE Transactions on Medical Imaging 39, 8 (2020), 2615–2625.Google Scholar
- . 2018. Non-local neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7794–7803.Google Scholar
Cross Ref
- . 2020. JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation. arxiv:2004.07054.Google Scholar
- . 2020. Chest CT for typical coronavirus disease 2019 (COVID-19) pneumonia: Relationship to negative RT-PCR testing.Radiology 296, 2 (2020), 200343.Google Scholar
- . 2020. GASNet: Weakly-supervised framework for COVID-19 lesion segmentation. arxiv:2010.09456.Google Scholar
- . 2020c. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 181, 6 (2020), 1423–1433.e11.Google Scholar
Cross Ref
- . 2020a. Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation. Information Fusion 64 (2020), 149–187.Google Scholar
Cross Ref
- . 2020d. A seven-layer convolutional neural network for chest CT based COVID-19 diagnosis using stochastic pooling. IEEE Sensors Journal. Early access, September 22, 2020.Google Scholar
- . 2020b. Inductive structure consistent hashing via flexible semantic calibration. IEEE Transactions on Neural Networks and Learning Systems. Early access, September 9, 2020.Google Scholar
- . 2021. Probability ordinal-preserving semantic hashing for large-scale image retrieval. ACM Transactions on Knowledge Discovery from Data 15, 3 (2021), 37.Google Scholar
Digital Library
- . 2020. Deep learning-based detection for COVID-19 from chest CT using weak label. medRxiv. Preprint, March 26, 2020.Google Scholar
- . 2016. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2921–2929.Google Scholar
Cross Ref
- . 2019. Efficient utilization of missing data in cost-sensitive learning. IEEE Transactions on Knowledge and Data Engineering 33, 6 (2019), 2425–2436.Google Scholar
Index Terms
Deep Active Context Estimation for Automated COVID-19 Diagnosis
Recommendations
Supervised and weakly supervised deep learning models for COVID-19 CT diagnosis: A systematic review
Highlights- Based on multi-level arrangements, an overview of deep supervised and weakly supervised COVID-19 CT approaches.
AbstractArtificial intelligence (AI) and computer vision (CV) methods become reliable to extract features from radiological images, aiding COVID-19 diagnosis ahead of the pathogenic tests and saving critical time for disease management and ...
Deep Learning-Based CAD System for COVID-19 Diagnosis via Spectral-Temporal Images
ICICM '22: Proceedings of the 12th International Conference on Information Communication and ManagementThe diagnosis of COVID-19 and understanding the condition of the patients who have critical responses is crucial to stop the rapid propagation of such disease. Consequently, diminishing adverse impacts that affected various industrial divisions, ...
Learning from pseudo-lesion: a self-supervised framework for COVID-19 diagnosis
AbstractThe Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019, and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based ...






Comments