X-ray versus computerized tomography (CT) images for detection of COVID-19 using deep learning

Background: The recent outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the disease corresponding to it (coronavirus disease 2019; COVID-19) has been declared a pandemic by the World Health Organization. COVID-19 has become a global crisis, shattering health care systems, and weakening economies of most countries. The current methods of testing that are employed include reverse transcription polymerase chain reaction (RT-PCR), rapid antigen testing, and lateral flow testing with RT-PCR being used as the golden standard despite its accuracy being at a mere 63%. It is a manual process which is time consuming, taking about an average of 48 hours to obtain the results. Alternative methods employing deep learning techniques and radiologic images are up and coming. Methods: In this paper, we used a dataset consisting of COVID-19 and non-COVID-19 folders for both X-Ray and CT images which contained a total number of 17,599 images. This dataset has been used to compare 3 (non-pre-trained) CNN models and 5 pre-trained models and their performances in detecting COVID-19 under various parameters like validation accuracy, training accuracy, validation loss, training loss, prediction accuracy, sensitivity and the training time required, with CT and X-Ray images separately. Results: Xception provided the highest validation accuracy (88%) when trained with the dataset containing the X- ray images while VGG19 provided the highest validation accuracy (81.2%) when CT images are used for training. Conclusions: The model, VGG16, showed the most consistent performance, with a validation accuracy of 76.6% for CT images and 87.76% for X-ray images. When comparing the results between the modalities, models trained with the X-ray dataset showed better performances than the same models trained with CT images. Hence, it can be concluded that X-ray images provide a higher accuracy in detecting COVID-19 making it an effective method for detecting COVID-19 in real life.

Download Full-text

Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images

Energies ◽

10.3390/en14154595 ◽

2021 ◽

Vol 14 (15) ◽

pp. 4595

Author(s):

Parisa Asadi ◽

Lauren E. Beckingham

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Random Forest ◽

Ct Images ◽

Ct Imaging ◽

Learning Method ◽

Learning Methods ◽

X Ray ◽

Machine Learning Methods ◽

Filtering Techniques

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

Download Full-text

Vulnerability in Deep Transfer Learning Models to Adversarial Fast Gradient Sign Attack for COVID-19 Prediction from Chest Radiography Images

Applied Sciences ◽

10.3390/app11094233 ◽

2021 ◽

Vol 11 (9) ◽

pp. 4233

Author(s):

Biprodip Pal ◽

Debashis Gupta ◽

Md. Rashed-Al-Mahfuz ◽

Salem A. Alyami ◽

Mohammad Ali Moni

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Chest Radiography ◽

High Sensitivity ◽

Ct Images ◽

Classification Performance ◽

Learning Models ◽

X Ray ◽

Image Capturing ◽

Fast Gradient

The COVID-19 pandemic requires the rapid isolation of infected patients. Thus, high-sensitivity radiology images could be a key technique to diagnose patients besides the polymerase chain reaction approach. Deep learning algorithms are proposed in several studies to detect COVID-19 symptoms due to the success in chest radiography image classification, cost efficiency, lack of expert radiologists, and the need for faster processing in the pandemic area. Most of the promising algorithms proposed in different studies are based on pre-trained deep learning models. Such open-source models and lack of variation in the radiology image-capturing environment make the diagnosis system vulnerable to adversarial attacks such as fast gradient sign method (FGSM) attack. This study therefore explored the potential vulnerability of pre-trained convolutional neural network algorithms to the FGSM attack in terms of two frequently used models, VGG16 and Inception-v3. Firstly, we developed two transfer learning models for X-ray and CT image-based COVID-19 classification and analyzed the performance extensively in terms of accuracy, precision, recall, and AUC. Secondly, our study illustrates that misclassification can occur with a very minor perturbation magnitude, such as 0.009 and 0.003 for the FGSM attack in these models for X-ray and CT images, respectively, without any effect on the visual perceptibility of the perturbation. In addition, we demonstrated that successful FGSM attack can decrease the classification performance to 16.67% and 55.56% for X-ray images, as well as 36% and 40% in the case of CT images for VGG16 and Inception-v3, respectively, without any human-recognizable perturbation effects in the adversarial images. Finally, we analyzed that correct class probability of any test image which is supposed to be 1, can drop for both considered models and with increased perturbation; it can drop to 0.24 and 0.17 for the VGG16 model in cases of X-ray and CT images, respectively. Thus, despite the need for data sharing and automated diagnosis, practical deployment of such program requires more robustness.

Download Full-text

Deep Learning Detection of COVID-19, Temporal Variation and its Link with Temperature in Nigeria

Asian Journal of Research in Computer Science ◽

10.9734/ajrcos/2021/v7i330182 ◽

2021 ◽

pp. 55-62

Author(s):

Ebiendele Eromosele Precious

Keyword(s):

Deep Learning ◽

Health Workers ◽

World Health ◽

Religious Activities ◽

X Ray ◽

Global Pandemic ◽

First Case ◽

Average Accuracy ◽

Maximum Temperatures ◽

Health Organization

COVID-19 was announced as a global pandemic on 11 March 2020 by the World Health Organization due to its spread globally. Nigeria recorded its first case on 27 February 2020. Since then, it has spread to all parts of the country. In this paper we study the effectiveness and skill performance of deep learning architectures in assisting health workers in detecting COVID-19 infected patient through X-ray images. Analytical deductions obtained from 500 X-ray images of both infected and non-infected patients confirmed that our proposed model InceptionV3 is effective in detecting COVID-19 and attain an average accuracy of 92%. The relationship or link between the COVID-19 daily occurrence and two meteorological variables (minimum and maximum temperatures) are further assessed. The result also indicated that the cases recorded in Wednesdays and Fridays are observed to be higher than other days which usually coincide with either religious activities or market days in the country, while a progressively decline in weekday cases is observed towards the weekend with Sundays (ranging from 152 to 280 cases) having the lowest cases. The study further indicated statistically that COVID-19 daily cases significantly decline when maximum and minimum temperature are increasing (-0.79 and -0.44 correlation coefficient).

Download Full-text

Efficiency of Artificial Intelligence in Detecting COVID-19 Pneumonia and Other Pneumonia Causes by Quantum Fourier Transform Method

10.1101/2020.12.29.20248900 ◽

2021 ◽

Author(s):

Erdi Acar ◽

Bilge Öztoprak ◽

Mustafa Reşorlu ◽

Murat Daş ◽

İhsan Yılmaz ◽

...

Keyword(s):

Artificial Intelligence ◽

Fourier Transform ◽

Low Dose ◽

Ct Images ◽

Performance Criteria ◽

World Health ◽

Fast Method ◽

Quantum Fourier Transform ◽

Rt Pcr ◽

Low Dose Ct

AbstractThe new coronavirus (COVID-19) appeared in Wuhan in December 2019 and has been announced as a pandemic by the World Health Organization (WHO). Currently, this deadly pandemic has caused more than 1 million deaths worldwide. Therefore, it is essential to detect positive cases as early as possible to prevent the further spread of this outbreak. Currently, the most widely used COVID-19 detection technique is a real-time reverse transcription-polymerase chain reaction (RT-PCR). However, RT-PCR is time-consuming to confirm infection in the patient. Because RT-PCR is less sensitive, it provides high false-negative results. Computed tomography (CT) is recommended as a solution to this problem by healthcare professionals because of its higher sensitivity for early and rapid diagnosis. In addition, radiation used in CT poses a serious threat to patients. In this study, we propose a CNN-based method to distinguish COVID-19 pneumonia from other types of viral and bacterial pneumonia using low-dose CT images to reduce the radiation dose used in CT. In our study, we used a data set consisting of 7717 CT images of 350 patients that we collected from Çanakkale Onsekiz Mart University Research Hospital. We used a CNN-based network that suppresses noise to remove interference from low-dose CT images. In the image preprocessing phase, we provided lung segmentation from CT images and applied quantum Fourier transform. By evaluating all possible variations of local knowledge at the same time with quantum Fourier transformation, the most informative spatial information was extracted. In CNN-based architecture, we used pre-trained ResNet50v2 as a feature extractor and fine-tune by training with our dataset. We visualized the efficiency of the ResNet50v2 network using the t-SNE method. We performed the classification process with a fully connected layer. We created a heat map using the GradCam technique to see where the model focuses on the images while classifying. In this experimental study, the results of 99.5%, 99.2%, 99.0%, 99.7%, and 99.1%, were obtained in the context of performance criteria such as accuracy, precision, sensitivity, specificity, and f1 score, respectively. This study revealed the artificial intelligence-based computer-aided diagnosis (CAD)system as an effective and fast method to accurately diagnose COVID-19 pneumonia.

Download Full-text

COVIDScreen: Explainable deep learning framework for differential diagnosis of COVID-19 using chest X-Rays

10.21203/rs.3.rs-61891/v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Rajeev Kumar Singh ◽

Rohan Pandey ◽

Rishie Nandhan Babu

Keyword(s):

Deep Learning ◽

Model Performance ◽

Alternative Methods ◽

Model Complexity ◽

X Rays ◽

Kappa Score ◽

X Ray ◽

Pruning Strategy ◽

Chest X Ray ◽

To Come

Abstract COVID-19 has emerged as a global crisis with unprecedented socio-economic challenges, jeopardizing our lives and livelihoods for years to come. The unavailability of vaccines for COVID-19 has rendered rapid testing of the population instrumental in order to contain the exponential rise in cases of infection. Shortage of RT-PCR test kits and delay in obtaining test results calls for alternative methods of rapid and reliable diagnosis. In this article, we propose a novel Deep Learning based solution to rapidly classify COVID -19 patient using chest X-Ray. The proposed solution uses image enhancement, image segmentation and employs a modified stacked ensemble model consisting of four CNN base-learners along with Naive Bayes as meta-learner to classify Chest X-Ray into three classes viz. COVID-19, Pneumonia and Normal. An effective pruning strategy as introduced in the proposed framework results in increased model performance, generalisability, and decreased model complexity. We incorporate explainability in our article by using Grad-CAM visualisation in order to establish trust in the medical AI system. Furthermore, we evaluate multiple state of the art GAN architectures and their ability to generate realistic synthetic samples of COVID-19 chest X-Rays to deal with limited numbers of training samples. The proposed solution significantly outperforms existing methods, with 98.67\% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98 for COVID-19, Normal, and Pneumonia classes respectively on standard datasets. The proposed solution can be used as one element of patient evaluation along with gold standard clinical and laboratory testing.

Download Full-text

An Explainable Artificial Intelligence based Prospective Framework for COVID-19 Risk Prediction

10.1101/2021.03.02.21252269 ◽

2021 ◽

Author(s):

Vishal Sharma ◽

Piyush ◽

Samarth Chhatwal ◽

Bipin Singh

Keyword(s):

Artificial Intelligence ◽

Risk Prediction ◽

Infection Risk ◽

Alternative Methods ◽

Confirmatory Test ◽

Rt Pcr ◽

Web Based ◽

X Ray ◽

Explainable Artificial Intelligence ◽

Chest X Ray

Given the spread of COVID-19 to vast geographical regions and populations, it is not feasible to undergo or recommend the RT-PCR based tests to all individuals with flu-like symptoms. The reach of RT-PCR based testing is still limited due to the high cost of the test and huge population in few countries. Thus, alternative methods for COVID-19 infection risk prediction can be useful. We built an explainable artificial intelligence (AI) based integrated web-based prospective framework for COVID-19 risk prediction. We employed a two-step procedure for the non-clinical prediction of COVID19 infection risk. In the first step we assess the initial risk of COVID19 infection based on carefully selected parameters associated with COVID-19 positive symptoms from recent research. Generally, X-ray scans are cheaper and easily available in most government and private health centres. Therefore, based on the outcome of the computed initial risk in first step, we further provide an optional prediction using the chest X-ray scans in the second step of our proposed AI based prospective framework. Since there is a bottleneck to undergo an expensive RT-PCR based confirmatory test in economically backward nations, this is a crucial part of our explainable AI based prospective framework. The initial risk assessment outcome is analysed in combination with the advanced deep learning-based analysis of chest X-ray scans to provide an accurate prediction of COVID-19 infection risk. This prospective web-based AI framework can be employed in limited resource settings after clinical validation in future. The cost and time associated with the adoption of this prospective AI based prospective framework will be minimal and hence it will be beneficial to majority of the population living in low-income settings such as small towns and rural areas that have limited access to advanced healthcare facilities.

Download Full-text

A Deep Learning Approach to Detect COVID-19 Patients from Chest X-ray Images

AI ◽

10.3390/ai1030027 ◽

2020 ◽

Vol 1 (3) ◽

pp. 418-435

Author(s):

Khandaker Haque ◽

Ahmed Abdelgawad

Keyword(s):

Deep Learning ◽

World Health ◽

X Rays ◽

X Ray ◽

Global Pandemic ◽

Proposed Model ◽

Dental Diseases ◽

Chest X Ray ◽

Artery Disease ◽

Health Organization

Deep Learning has improved multi-fold in recent years and it has been playing a great role in image classification which also includes medical imaging. Convolutional Neural Networks (CNNs) have been performing well in detecting many diseases including coronary artery disease, malaria, Alzheimer’s disease, different dental diseases, and Parkinson’s disease. Like other cases, CNN has a substantial prospect in detecting COVID-19 patients with medical images like chest X-rays and CTs. Coronavirus or COVID-19 has been declared a global pandemic by the World Health Organization (WHO). As of 8 August 2020, the total COVID-19 confirmed cases are 19.18 M and deaths are 0.716 M worldwide. Detecting Coronavirus positive patients is very important in preventing the spread of this virus. On this conquest, a CNN model is proposed to detect COVID-19 patients from chest X-ray images. Two more CNN models with different number of convolution layers and three other models based on pretrained ResNet50, VGG-16 and VGG-19 are evaluated with comparative analytical analysis. All six models are trained and validated with Dataset 1 and Dataset 2. Dataset 1 has 201 normal and 201 COVID-19 chest X-rays whereas Dataset 2 is comparatively larger with 659 normal and 295 COVID-19 chest X-ray images. The proposed model performs with an accuracy of 98.3% and a precision of 96.72% with Dataset 2. This model gives the Receiver Operating Characteristic (ROC) curve area of 0.983 and F1-score of 98.3 with Dataset 2. Moreover, this work shows a comparative analysis of how change in convolutional layers and increase in dataset affect classifying performances.

Download Full-text

COVID-19 Chest X-Ray Images Diagnosis: A Neutrosophic and Deep Transfer Learning Approach

10.20944/preprints202004.0371.v1 ◽

2020 ◽

Author(s):

Nour Eldeen M. Khalifa ◽

Florentin Smarandache ◽

Mohamed Loey

Keyword(s):

Deep Learning ◽

Performance Metrics ◽

World Health ◽

Transfer Model ◽

X Ray ◽

Proposed Model ◽

The World ◽

Chest X Ray ◽

Testing Accuracy ◽

Transfer Models

Coronavirus, also known as COVID-19, has spread to several countries around the world. It was announced as a pandemic disease by The World Health Organization (WHO) in 2020 for its devastating impact on humans. With the advancements in computer science algorithms, the detection of this type of virus in the early stages is urgently needed for the fast recovery of patients. In this paper, a neutrosophic with a deep learning model for the detection of COVID-19 from chest X-ray medical digital images is presented. The proposed model relies on neutrosophic theory by converting the medical images from the grayscale spatial domain to the neutrosophic domain. The neutrosophic domain consists of three types of images and they are, the True (T) images, the Indeterminacy (I) images, and the Falsity (F) images. Using neutrosophic images has positively affected the accuracy of the proposed model. The dataset used in this research has been collected from different sources as there is no benchmark dataset for COVID-19 chest X-ray until the writing of this research. The dataset consists of four classes and they are COVID-19, Normal, Pneumonia bacterial, and Pneumonia virus. After the conversion to the neutrosophic domain, the images are fed into three different deep transfer models and they are Alexnet, Googlenet, and Restnet18. Those models are selected as they have a small number of layers on their architectures and they have been used with related work. To test the performance of the conversion to the neutrosophic domain, four scenarios have been tested. The first scenario is training the deep transfer models with True (T) neutrosophic images only. The second one is training on Indeterminacy (I) neutrosophic images, while the third scenario is training the deep models over the Falsity (F) neutrosophic images. The fourth scenario is training over the combined (T, I, F) neutrosophic images. According to the experimental results, the combined (T, I, F) neutrosophic images achieved the highest accuracy possible for the validation, testing and all performance metrics such Precision, Recall and F1 Score using Resnet18 as a deep transfer model. The proposed model achieved a testing accuracy with 78.70%. Furthermore, the proposed model using neutrosophic and Resnet18 had achieved superior testing accuracy with a related work which achieved 52.80% with the same experimental environmental setup and the same deep learning hyperparameters.

Download Full-text

Pneumonia and Eye Disease Detection using Convolutional Neural Networks

Engineering, Technology & Applied Science Research ◽

10.48084/etasr.3503 ◽

2020 ◽

Vol 10 (3) ◽

pp. 5769-5774 ◽

Cited By ~ 1

Author(s):

P. Chakraborty ◽

C. Tharini

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Detection System ◽

Eye Disease ◽

Medical Professionals ◽

Disease Detection ◽

Training Time ◽

X Ray ◽

Detection Systems

Automatic disease detection systems based on Convolutional Neural Networks (CNNs) are proposed in this paper for helping the medical professionals in the detection of diseases from scan and X-ray images. CNN based classification helps decision making in a prompt manner with high precision. CNNs are a subset of deep learning which is a branch of Artificial Intelligence. The main advantage of CNNs compared to other deep learning algorithms is that they require minimal pre-processing. In the proposed disease detection system, two medical image datasets consisting of Optical Coherence Tomography (OCT) and chest X-ray images of 1-5 year-old children are considered and used as inputs. The medical images are processed and classified using CNN and various performance measuring parameters such as accuracy, loss, and training time are measured. The system is then implemented in hardware, where the testing is done using the trained models. The result shows that the validation accuracy obtained in the case of the eye dataset is around 90% whereas in the case of lung dataset it is around 63%. The proposed system aims to help medical professionals to provide a diagnosis with better accuracy thus helping in reducing infant mortality due to pneumonia and allowing finding the severity of eye disease at an earlier stage.

Download Full-text

Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images

Healthcare ◽

10.3390/healthcare10010166 ◽

2022 ◽

Vol 10 (1) ◽

pp. 166

Author(s):

Mohamed Mouhafid ◽

Mokhtar Salah ◽

Chi Yue ◽

Kewen Xia

Keyword(s):

Deep Learning ◽

Ensemble Learning ◽

Detection System ◽

Weighted Average ◽

Recognition System ◽

Ct Images ◽

Chest Ct ◽

Rt Pcr ◽

Infected People ◽

Desirable Outcome

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along with RT-PCR, computed tomography (CT) has become a vital technique in diagnosing and managing COVID-19 patients. COVID-19 reveals a number of radiological signatures that can be easily recognized through chest CT. These signatures must be analyzed by radiologists. It is, however, an error-prone and time-consuming process. Deep Learning-based methods can be used to perform automatic chest CT analysis, which may shorten the analysis time. The aim of this study is to design a robust and rapid medical recognition system to identify positive cases in chest CT images using three Ensemble Learning-based models. There are several techniques in Deep Learning for developing a detection system. In this paper, we employed Transfer Learning. With this technique, we can apply the knowledge obtained from a pre-trained Convolutional Neural Network (CNN) to a different but related task. In order to ensure the robustness of the proposed system for identifying positive cases in chest CT images, we used two Ensemble Learning methods namely Stacking and Weighted Average Ensemble (WAE) to combine the performances of three fine-tuned Base-Learners (VGG19, ResNet50, and DenseNet201). For Stacking, we explored 2-Levels and 3-Levels Stacking. The three generated Ensemble Learning-based models were trained on two chest CT datasets. A variety of common evaluation measures (accuracy, recall, precision, and F1-score) are used to perform a comparative analysis of each method. The experimental results show that the WAE method provides the most reliable performance, achieving a high recall value which is a desirable outcome in medical applications as it poses a greater risk if a true infected patient is not identified.

Download Full-text