A Systematic Review on the Use of Artificial Intelligence Techniques in the Diagnosis of COVID-19 from Chest X-Ray Images

Mohammad Hosein Sadeghi; Hamid Omidi; Sedigheh Sina

doi:10.34172/ajmb.2020.17

A Systematic Review on the Use of Artificial Intelligence Techniques in the Diagnosis of COVID-19 from Chest X-Ray Images

Avicenna Journal of Medical Biochemistry ◽

10.34172/ajmb.2020.17 ◽

2020 ◽

Vol 8 (2) ◽

pp. 120-127

Author(s):

Mohammad Hosein Sadeghi ◽

Hamid Omidi ◽

Sedigheh Sina

Keyword(s):

Artificial Intelligence ◽

Systematic Review ◽

Sensitivity And Specificity ◽

Model Performance ◽

Area Under The Curve ◽

Google Scholar ◽

X Ray ◽

Source Codes ◽

Specificity And Sensitivity ◽

Chest X Ray

Background: In this study, the artificial intelligence (AI) techniques used for the detection of coronavirus disease 2019 (COVID-19) from the chest x-ray were reviewed. Methods: PubMed, arXiv, and Google Scholar were used to search for AI studies. Results: A total of 20 papers were extracted from Google Scholar, 14 from arXiv, and 5 from PubMed. In 17 papers, publicly available datasets and in 3 papers, independent datasets were used. 10 papers disclosed source codes. Nine papers were about creating a novel AI software, 8 papers reported the modification of the existing AI models, and 3 compared the performance of the existing AI software programs. All papers have used deep learning as AI technique. Most papers reported accuracy, specificity, and sensitivity of the models, and also the area under the curve (AUC) for investigation of the model performance for the prediction of COVID-19. Nine papers reported accuracy, sensitivity, and specificity. The number of datasets used in the studies ranged from 50 to 94323. The accuracy, sensitivity, and specificity of the models ranged from 0.88 to 0.98, 0.80 to 1.00, and 0.70 to 1.00, respectively. Conclusion: The studies revealed that AI can help human in fighting the new Coronavirus.

Download Full-text

The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review

Diagnostics ◽

10.3390/diagnostics11122206 ◽

2021 ◽

Vol 11 (12) ◽

pp. 2206

Author(s):

Dana Li ◽

Lea Marie Pehrson ◽

Carsten Ammitzbøl Lauridsen ◽

Lea Tøttrup ◽

Marco Fraccaro ◽

...

Keyword(s):

Artificial Intelligence ◽

Systematic Review ◽

Assessment Tool ◽

Cochrane Library ◽

Original Research ◽

Quality Assessment Tool ◽

Bias Assessment ◽

X Ray ◽

Chest X Ray ◽

Sensitivity Specificity

Our systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE, PubMed, Cochrane library, SCOPUS, and Web of Science were retrieved. Included articles were published within the last 20 years and used a device based on artificial intelligence (AI) technology to detect or diagnose pulmonary findings. The AI-based device had to be used in an observer test where the performance of human observers with and without addition of the device was measured as sensitivity, specificity, accuracy, AUC, or time spent on image reading. A total of 38 studies were included for final assessment. The quality assessment tool for diagnostic accuracy studies (QUADAS-2) was used for bias assessment. The average sensitivity increased from 67.8% to 74.6%; specificity from 82.2% to 85.4%; accuracy from 75.4% to 81.7%; and Area Under the ROC Curve (AUC) from 0.75 to 0.80. Generally, a faster reading time was reported when radiologists were aided by AI-based devices. Our systematic review showed that performance generally improved for the physicians when assisted by AI-based devices compared to unaided interpretation.

Download Full-text

Sensitivity and specificity of artificial intelligence with Microsoft Azure in detecting pneumothorax in emergency department: A pilot study

Hong Kong Journal of Emergency Medicine ◽

10.1177/1024907920948994 ◽

2020 ◽

pp. 102490792094899

Author(s):

Kwok Hung Alastair Lai ◽

Shu Kai Ma

Keyword(s):

Artificial Intelligence ◽

Emergency Department ◽

Sensitivity And Specificity ◽

National Institutes Of Health ◽

Dramatic Improvement ◽

X Ray ◽

Training Images ◽

Normal Chest ◽

Chest X Ray ◽

Microsoft Azure

Background: Artificial intelligence is becoming an increasingly important tool in different medical fields. This article aims to evaluate the sensitivity and specificity of artificial intelligence trained with Microsoft Azure in detecting pneumothorax. Methods: A supervised learning artificial intelligence is trained with a collection of X-ray images of pneumothorax from National Institutes of Health chest X-ray dataset online. A subset of the image dataset focused on pneumothorax is used in training. Two artificial intelligence programs are trained with different numbers of training images. After the training, a collection of pneumothorax X-ray images from patient attending emergency department is retrieved through the Clinical Data Analysis & Reporting System. In total, 115 pneumothorax patients and 60 normal inpatients are recruited. The pneumothorax chest X-ray and the resolution chest X-ray of the above patient group and a collection of normal chest X-ray from inpatients without pneumothorax will be retrieved, and these three sets of images will then undergo testing by artificial intelligence programs to give a probability of being a pneumothorax X-ray. Results: The sensitivity of artificial intelligence-one is 33.04%, and the specificity is at least 61.74%. The sensitivity of artificial intelligence-two is 46.09%, and the specificity is at least 71.30%. The dramatic improvement of 46.09% in sensitivity and improvement of 15.48% in specificity by addition of around 1000 X-ray images is encouraging. The mean improvement of AI-two over AI-one is 19.7% increase in probability difference. Conclusions: We should not rely on artificial intelligence in diagnosing pneumothorax X-ray solely by our models and more training should be expected to explore its full function.

Download Full-text

Artificial intelligence applied on chest X-ray can aid in the diagnosis of COVID-19 infection: a first experience from Lombardy, Italy

10.1101/2020.04.08.20040907 ◽

2020 ◽

Cited By ~ 9

Author(s):

Isabella Castiglioni ◽

Davide Ippolito ◽

Matteo Interlenghi ◽

Caterina Beatrice Monti ◽

Christian Salvatore ◽

...

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Area Under The Curve ◽

Training Dataset ◽

List Type ◽

X Rays ◽

Independent Dataset ◽

X Ray ◽

Chest X Ray

AbstractObjectivesWe tested artificial intelligence (AI) to support the diagnosis of COVID-19 using chest X-ray (CXR). Diagnostic performance was computed for a system trained on CXRs of Italian subjects from two hospitals in Lombardy, Italy.MethodsWe used for training and internal testing an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals. We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as reference standard.ResultsAt 10-fold cross-validation, our AI model classified COVID-19 and non COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74–0.81), 0.82 specificity (95% CI 0.78–0.85) and 0.89 area under the curve (AUC) (95% CI 0.86–0.91). For the independent dataset, AI showed 0.80 sensitivity (95% CI 0.72–0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73–0.87), and 0.81 AUC (95% CI 0.73– 0.87). Radiologists’ reading obtained 0.63 sensitivity (95% CI 0.52–0.74) and 0.78 specificity (95% CI 0.61–0.90) in one centre and 0.64 sensitivity (95% CI 0.52–0.74) and 0.86 specificity (95% CI 0.71–0.95) in the other.ConclusionsThis preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of AI for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.Key pointsArtificial intelligence based on convolutional neural networks was preliminary applied to chest-X-rays of patients suspected to be infected by COVID-19.Convolutional neural networks trained on a limited dataset of 250 COVID-19 and 250 non-COVID-19 were tested on an independent dataset of 110 patients suspected for COVID-19 infection and provided a balanced performance with 0.80 sensitivity and 0.81 specificity.Training on larger multi-institutional datasets may allow this tool to increase its performance.

Download Full-text

Training Artificial Intelligence Neural Networks to Detect Devices on a Chest X-ray, a Pathway to COVID-19 Testing

Journal of the National Medical Association ◽

10.1016/j.jnma.2020.09.140 ◽

2020 ◽

Vol 112 (5) ◽

pp. S50

Author(s):

Zachary Eller ◽

Michelle Chen ◽

Jermaine Heath ◽

Uzma Hussain ◽

Thomas Obisean ◽

...

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

X Ray ◽

Chest X Ray

Download Full-text

Machine learning applied on chest x-ray can aid in the diagnosis of COVID-19: a first experience from Lombardy, Italy

European Radiology Experimental ◽

10.1186/s41747-020-00203-z ◽

2021 ◽

Vol 5 (1) ◽

Cited By ~ 1

Author(s):

Isabella Castiglioni ◽

Davide Ippolito ◽

Matteo Interlenghi ◽

Caterina Beatrice Monti ◽

Christian Salvatore ◽

...

Keyword(s):

Deep Learning ◽

Area Under The Curve ◽

Clinical Information ◽

Training Dataset ◽

Independent Dataset ◽

X Ray ◽

Learning Classifier ◽

Chest X Ray ◽

Polymerase Chain ◽

Deep Learning Model

Abstract Background We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. Methods We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. Results At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74–0.81), 0.82 specificity (95% CI 0.78–0.85), and 0.89 area under the curve (AUC) (95% CI 0.86–0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72–0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73–0.87), and 0.81 AUC (95% CI 0.73–0.87). Radiologists’ reading obtained 0.63 sensitivity (95% CI 0.52–0.74) and 0.78 specificity (95% CI 0.61–0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52–0.74) and 0.86 specificity (95% CI 0.71–0.95) in Centre 2. Conclusions This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.

Download Full-text

AB0796 THE EVALUATION OF LUNG DIAGNOSTIC PROCEDURE AT THE ONSET OF INFLAMMATORY RHEUMATIC DISEASES WITH INTERSTITIAL LUNG DISEASE

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2021-eular.3119 ◽

2021 ◽

Vol 80 (Suppl 1) ◽

pp. 1422.3-1423

Author(s):

T. Hoffmann ◽

P. Oelzner ◽

F. Marcus ◽

M. Förster ◽

J. Böttcher ◽

...

Keyword(s):

Carbon Monoxide ◽

Interstitial Lung Disease ◽

Lung Function ◽

Lung Disease ◽

Sensitivity And Specificity ◽

Lung Function Test ◽

Inflammatory Rheumatic Diseases ◽

X Ray ◽

Function Test ◽

Chest X Ray

Background:Interstitial lung disease (ILD) in inflammatory rheumatic diseases (IRD) is associated with increased mortality. Moreover, the lung is one of the most effected organs on IRD. Consequently, screening methods were required to the detect ILD in IRD.Objectives:The objective of the following study is to evaluate the diagnostic value of lung function test, chest x-ray and HR-CT of the lung in the detection of ILD at the onset of IRD.Methods:The study is designed as a case-control study and includes 126 patients with a newly diagnosed IRD. It was matched by gender, age and the performance of lung function test and chest x-ray. The sensitivity and specificity were verified by crosstabs and receiver operating characteristic (ROC) curve analysis. The study cohort was divided in two groups (ILD group: n = 63 and control group: n = 63). If possible, all patients received a lung function test and optional a chest x-ray. Patients with pathological findings in the screening tests (chest x-ray or reduced diffusing capacity for carbon monoxide (DLCO) < 80 %) maintained a high-resolution computer tomography (HR-CT) of the lung. Additionally, an immunological bronchioalveolar lavage was performed in the ILD group as gold standard for the detection of ILD.Results:The DLCO (< 80 %) revealed a sensitivity of 83.6 % and specificity of 45.8 % for the detection of ILD. Other examined parameter of lung function test showed no sufficient sensitivity as screening test (FVC = Forced Vital Capacity, FEV1 = Forced Expiratory Volume in 1 second, TLC = Total Lung Capacity, TLCO = Transfer factor of the Lung for carbon monoxide). Also, a combination of different parameter did not increase the sensitivity. The sensitivity and specificity of chest x-ray for the verification of ILD was 64.2 % versus 73.6 %. The combination of DLCO (< 80 %) and chest x-ray showed a sensitivity with 95.2 % and specificity with 38.7 %. The highest sensitivity (95.2 %) and specificity (77.4 %) was observed for the combination of DLCO (< 80 %) and HR-CT of the lung.Conclusion:The study highlighted that a reduced DLCO in lung function test is associated with a lung involvement in IRD. DLCO represented a potential screening parameter for lung manifestation in IRD. Especially patients with suspected vasculitis should receive an additional chest x-ray. Based on the high sensitivity of DLCO in combination with chest x-ray or HR-CT for the detection of ILD in IRD, all patients with a reduced DLCO (< 80%) should obtained an imaging of the lung.Disclosure of Interests:None declared

Download Full-text

Current limitations to identify COVID-19 using artificial intelligence with chest X-ray imaging

Health and Technology ◽

10.1007/s12553-021-00520-2 ◽

2021 ◽

Vol 11 (2) ◽

pp. 411-424 ◽

Cited By ~ 1

Author(s):

José Daniel López-Cabrera ◽

Rubén Orozco-Morales ◽

Jorge Armando Portal-Diaz ◽

Orlando Lovelle-Enríquez ◽

Marlén Pérez-Díaz

Keyword(s):

Artificial Intelligence ◽

X Ray ◽

X Ray Imaging ◽

Chest X Ray

Download Full-text

Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

10.21203/rs.3.rs-66836/v2 ◽

2021 ◽

Author(s):

Ali Mohammad Alqudah ◽

Shoroq Qazan ◽

Ihssan S. Masad

Keyword(s):

Artificial Intelligence ◽

Input Image ◽

Image Size ◽

X Ray ◽

Softmax Classifier ◽

Non Invasive ◽

Efficient Detection ◽

X Ray Imaging ◽

Chest X Ray

Abstract BackgroundChest diseases are serious health problems that threaten the lives of people. The early and accurate diagnosis of such diseases is very crucial in the success of their treatment and cure. Pneumonia is one of the most widely occurred chest diseases responsible for a high percentage of deaths especially among children. So, detection and classification of pneumonia using the non-invasive chest x-ray imaging would have a great advantage of reducing the mortality rates.ResultsThe results showed that the best input image size in this framework was 64 64 based on comparison between different sizes. Using CNN as a deep features extractor and utilizing the 10-fold methodology the propose artificial intelligence framework achieved an accuracy of 94% for SVM and 93.9% for KNN, a sensitivity of 93.33% for SVM and 93.19% for KNN and a specificity of 96.68% for SVM and 96.60% for KNN.ConclusionsIn this study, an artificial intelligence framework has been proposed for the detection and classification of pneumonia based on chest x-ray imaging with different sizes of input images. The proposed methodology used CNN for features extraction that were fed to two different types of classifiers, namely, SVM and KNN; in addition to the SoftMax classifier which is the default CNN classifier. The proposed CNN has been trained, validated, and tested using a large dataset of chest x-ray images contains in total 5852 images.

Download Full-text