Fast automated detection of COVID-19 from medical images using convolutional neural networks

Liang, Shuang; Liu, Huixiang; Gu, Yu; Guo, Xiuhua; Li, Hongjun; Li, Li; Wu, Zhiyuan; Li, Mengyang; Tao, Lixin

doi:10.1038/s42003-020-01535-7

Cited by 56 publications

(30 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the onset of the pandemic, classification of specific chest CT image anomalies has become key to support differential diagnosis of COVID-19-induced lung inflammation from pneumonia of other origin and the radiologist’s performance achieved sensitivity and specificity close to 90% [ 23 , 24 ]. Image classification by computerized deep learning methods, in particular convolutional neuronal networks, which rely on strong correlations between lesion areas in radiologic images and clinical indicators, achieve a specificity of >99% [ 25 ]. CT assessment includes the number, type, rate of anomaly development and particularly the distribution pattern in the lung.…”

Section: Introductionmentioning

confidence: 99%

SARS-CoV-2-Laden Respiratory Aerosol Deposition in the Lung Alveolar-Interstitial Region Is a Potential Risk Factor for Severe Disease: A Modeling Study

Hofer

Hofstätter

Duschl

et al. 2021

JPM

View full text Add to dashboard Cite

COVID-19, predominantly a mild disease, is associated with more severe clinical manifestation upon pulmonary involvement. Virion-laden aerosols and droplets target different anatomical sites for deposition. Compared to droplets, aerosols more readily advance into the peripheral lung. We performed in silico modeling to confirm the secondary pulmonary lobules as the primary site of disease initiation. By taking different anatomical aerosol origins into consideration and reflecting aerosols from exhalation maneuvers breathing and vocalization, the physicochemical properties of generated respiratory aerosol particles were defined upon conversion to droplet nuclei by evaporation at ambient air. To provide detailed, spatially-resolved information on particle deposition in the thoracic region of the lung, a top-down refinement approach was employed. Our study presents evidence for hot spots of aerosol deposition in lung generations beyond the terminal bronchiole, with a maximum in the secondary pulmonary lobules and a high preference to the lower lobes of both lungs. In vivo, initial chest CT anomalies, the ground glass opacities, resulting from partial alveolar filling and interstitial thickening in the secondary pulmonary lobules, are likewise localized in these lung generations, with the highest frequency in both lower lobes and in the early stage of disease. Hence, our results suggest a disease initiation right there upon inhalation of virion-laden respiratory aerosols, linking the aerosol transmission route to pathogenesis associated with higher disease burden and identifying aerosol transmission as a new independent risk factor for developing a pulmonary phase with a severe outcome.

show abstract

Section: Introductionmentioning

confidence: 99%

SARS-CoV-2-Laden Respiratory Aerosol Deposition in the Lung Alveolar-Interstitial Region Is a Potential Risk Factor for Severe Disease: A Modeling Study

Hofer

Hofstätter

Duschl

et al. 2021

JPM

View full text Add to dashboard Cite

show abstract

“…In another study, the authors of [113] established a deep learning framework for detecting COVID-19 in X-ray and computed tomography images. ResBlock-A, ResBlock-B, and Control Gate Block made up a modular CNN-based classification system.…”

Section: Custom Deep Learning Techniquesmentioning

confidence: 99%

Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights

Awassa

Jdey

Dhahri

et al. 2022

Sensors

View full text Add to dashboard Cite

COVID-19 has evolved into one of the most severe and acute illnesses. The number of deaths continues to climb despite the development of vaccines and new strains of the virus have appeared. The early and precise recognition of COVID-19 are key in viably treating patients and containing the pandemic on the whole. Deep learning technology has been shown to be a significant tool in diagnosing COVID-19 and in assisting radiologists to detect anomalies and numerous diseases during this epidemic. This research seeks to provide an overview of novel deep learning-based applications for medical imaging modalities, computer tomography (CT) and chest X-rays (CXR), for the detection and classification COVID-19. First, we give an overview of the taxonomy of medical imaging and present a summary of types of deep learning (DL) methods. Then, utilizing deep learning techniques, we present an overview of systems created for COVID-19 detection and classification. We also give a rundown of the most well-known databases used to train these networks. Finally, we explore the challenges of using deep learning algorithms to detect COVID-19, as well as future research prospects in this field.

show abstract

“…On the other hand, an accurate and quick diagnosis of COVID-19 can be achieved from CXR. In recent research [4][5][6], it is reported that CXRs examination has improved diagnosis, the readers are referred to [7][8][9][10][11][12][13][14]. However, manual analysis and interpretation of CXRs are not only quite time consuming, but it is also error-prone due to their subjectivity.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, an accurate and quick diagnosis of COVID-19 can be achieved from CXR. In recent research [ 4–6 ], it is reported that CXRs examination has improved the sensitivity of COVID-19 diagnostic. For additional computer aided applications of COVID-19 diagnosis, the readers are referred to [ 7–14 ].…”

Section: Introductionmentioning

confidence: 99%

Computer-aided COVID-19 diagnosis and a comparison of deep learners using augmented CXRs

Naseer

Tamoor

Azhar

2022

XST

View full text Add to dashboard Cite

Background: Coronavirus Disease 2019 (COVID-19) is contagious, producing respiratory tract infection, caused by a newly discovered coronavirus. Its death toll is too high, and early diagnosis is the main problem nowadays. Infected people show a variety of symptoms such as fatigue, fever, tastelessness, dry cough, etc. Some other symptoms may also be manifested by radiographic visual identification. Therefore, Chest X-Rays (CXR) play a key role in the diagnosis of COVID-19. Methods: In this study, we use Chest X-Rays images to develop a computer-aided diagnosis (CAD) of the disease. These images are used to train two deep networks, the Convolution Neural Network (CNN), and the Long Short-Term Memory Network (LSTM) which is an artificial Recurrent Neural Network (RNN). The proposed study involves three phases. First, the CNN model is trained on raw CXR images. Next, it is trained on pre-processed CXR images and finally enhanced CXR images are used for deep network CNN training. Geometric transformations, color transformations, image enhancement, and noise injection techniques are used for augmentation. From augmentation, we get 3,220 augmented CXRs as training datasets. In the final phase, CNN is used to extract the features of CXR imagery that are fed to the LSTM model. The performance of the four trained models is evaluated by the evaluation techniques of different models, including accuracy, specificity, sensitivity, false-positive rate, and receiver operating characteristic (ROC) curve. Results: We compare our results with other benchmark CNN models. Our proposed CNN-LSTM model gives superior accuracy (99.02%) than the other state-of-the-art models. Our method to get improved input, helped the CNN model to produce a very high true positive rate (TPR 1) and no false-negative result whereas false negative was a major problem while using Raw CXR images. Conclusions: We conclude after performing different experiments that some image pre-processing and augmentation, remarkably improves the results of CNN-based models. It will help a better early detection of the disease that will eventually reduce the mortality rate of COVID.

show abstract

Fast automated detection of COVID-19 from medical images using convolutional neural networks

Cited by 56 publications

References 40 publications

SARS-CoV-2-Laden Respiratory Aerosol Deposition in the Lung Alveolar-Interstitial Region Is a Potential Risk Factor for Severe Disease: A Modeling Study

SARS-CoV-2-Laden Respiratory Aerosol Deposition in the Lung Alveolar-Interstitial Region Is a Potential Risk Factor for Severe Disease: A Modeling Study

Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights

Computer-aided COVID-19 diagnosis and a comparison of deep learners using augmented CXRs

Contact Info

Product

Resources

About