Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 158
Filter
1.
Stud Health Technol Inform ; 290: 679-683, 2022 Jun 06.
Article in English | MEDLINE | ID: covidwho-1879416

ABSTRACT

Since the emergence of COVID-19, deep learning models have been developed to identify COVID-19 from chest X-rays. With little to no direct access to hospital data, the AI community relies heavily on public data comprising numerous data sources. Model performance results have been exceptional when training and testing on open-source data, surpassing the reported capabilities of AI in pneumonia-detection prior to the COVID-19 outbreak. In this study impactful models are trained on a widely used open-source data and tested on an external test set and a hospital dataset, for the task of classifying chest X-rays into one of three classes: COVID-19, non-COVID pneumonia and no-pneumonia. Classification performance of the models investigated is evaluated through ROC curves, confusion matrices and standard classification metrics. Explainability modules are implemented to explore the image features most important to classification. Data analysis and model evalutions show that the popular open-source dataset COVIDx is not representative of the real clinical problem and that results from testing on this are inflated. Dependence on open-source data can leave models vulnerable to bias and confounding variables, requiring careful analysis to develop clinically useful/viable AI tools for COVID-19 detection in chest X-rays.


Subject(s)
COVID-19 , Deep Learning , COVID-19/diagnostic imaging , Humans , Radiography , SARS-CoV-2 , X-Rays
2.
IEEE J Biomed Health Inform ; 26(4): 1496-1505, 2022 Apr.
Article in English | MEDLINE | ID: covidwho-1878965

ABSTRACT

Deep learning based methods have shown great promise in achieving accurate automatic detection of Coronavirus Disease (covid) - 19 from Chest X-Ray (cxr) images.However, incorporating explainability in these solutions remains relatively less explored. We present a hierarchical classification approach for separating normal, non-covid pneumonia (ncp) and covid cases using cxr images. We demonstrate that the proposed method achieves clinically consistent explainations. We achieve this using a novel multi-scale attention architecture called Multi-scale Attention Residual Learning (marl) and a new loss function based on conicity for training the proposed architecture. The proposed classification strategy has two stages. The first stage uses a model derived from DenseNet to separate pneumonia cases from normal cases while the second stage uses the marl architecture to discriminate between covid and ncp cases. With a five-fold cross validation the proposed method achieves 93%, 96.28%, and 84.51% accuracy respectively over three large, public datasets for normal vs. ncp vs. covid classification. This is competitive to the state-of-the-art methods. We also provide explanations in the form of GradCAM attributions, which are well aligned with expert annotations. The attributions are also seen to clearly indicate that marl deems the peripheral regions of the lungs to be more important in the case of covid cases while central regions are seen as more important in ncp cases. This observation matches the criteria described by radiologists in clinical literature, thereby attesting to the utility of the derived explanations.


Subject(s)
COVID-19 , Deep Learning , Pneumonia , Algorithms , Attention , COVID-19/diagnostic imaging , Humans , Neural Networks, Computer , SARS-CoV-2 , X-Rays
3.
Comput Intell Neurosci ; 2022: 6185013, 2022.
Article in English | MEDLINE | ID: covidwho-1861702

ABSTRACT

It is critical to establish a reliable method for detecting people infected with COVID-19 since the pandemic has numerous harmful consequences worldwide. If the patient is infected with COVID-19, a chest X-ray can be used to determine this. In this work, an X-ray showing a COVID-19 infection is classified by the capsule neural network model we trained to recognise. 6310 chest X-ray pictures were used to train the models, separated into three categories: normal, pneumonia, and COVID-19. This work is considered an improved deep learning model for the classification of COVID-19 disease through X-ray images. Viewpoint invariance, fewer parameters, and better generalisation are some of the advantages of CapsNet compared with the classic convolutional neural network (CNN) models. The proposed model has achieved an accuracy greater than 95% during the model's training, which is better than the other state-of-the-art algorithms. Furthermore, to aid in detecting COVID-19 in a chest X-ray, the model could provide extra information.


Subject(s)
COVID-19 , Deep Learning , COVID-19/diagnostic imaging , Humans , Neural Networks, Computer , Thorax/diagnostic imaging , X-Rays
4.
Sensors (Basel) ; 22(10)2022 May 13.
Article in English | MEDLINE | ID: covidwho-1855752

ABSTRACT

Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effect on the global economy and health. COVID-19 cases have been rapidly increasing, with no sign of stopping. As a result, test kits and accurate detection models are in short supply. Early identification of COVID-19 patients will help decrease the infection rate. Thus, developing an automatic algorithm that enables the early detection of COVID-19 is essential. Moreover, patient data are sensitive, and they must be protected to prevent malicious attackers from revealing information through model updates and reconstruction. In this study, we presented a higher privacy-preserving federated learning system for COVID-19 detection without sharing data among data owners. First, we constructed a federated learning system using chest X-ray images and symptom information. The purpose is to develop a decentralized model across multiple hospitals without sharing data. We found that adding the spatial pyramid pooling to a 2D convolutional neural network improves the accuracy of chest X-ray images. Second, we explored that the accuracy of federated learning for COVID-19 identification reduces significantly for non-independent and identically distributed (Non-IID) data. We then proposed a strategy to improve the model's accuracy on Non-IID data by increasing the total number of clients, parallelism (client-fraction), and computation per client. Finally, for our federated learning model, we applied a differential privacy stochastic gradient descent (DP-SGD) to improve the privacy of patient data. We also proposed a strategy to maintain the robustness of federated learning to ensure the security and accuracy of the model.


Subject(s)
COVID-19 , Privacy , COVID-19/diagnostic imaging , Humans , Neural Networks, Computer , Thorax , X-Rays
5.
ISA Trans ; 124: 82-89, 2022 May.
Article in English | MEDLINE | ID: covidwho-1851356

ABSTRACT

Testing is one of the important methodologies used by various countries in order to fight against COVID-19 infection. The infection is considered as one of the deadliest ones although the mortality rate is not very high. COVID-19 infection is being caused by SARS-CoV2 which is termed as severe acute respiratory syndrome coronavirus 2 virus. To prevent the community, transfer among the masses, testing plays an important role. Efficient and quicker testing techniques helps in identification of infected person which makes it easier for to isolate the patient. Deep learning methods have proved their presence and effectiveness in medical image analysis and in the identification of some of the diseases like pneumonia. Authors have been proposed a deep learning mechanism and system to identify the COVID-19 infected patient on analyzing the X-ray images. Symptoms in the COVID-19 infection is well similar to the symptoms occurring in the influenza and pneumonia. The proposed model Inception Nasnet (INASNET) is being able to separate out and classify the X-ray images in the corresponding normal, COVID-19 infected or pneumonia infected classes. This testing method will be a boom for the doctors and for the state as it is a way cheaper method as compared to the other testing kits used by the healthcare workers for the diagnosis of the disease. Continuous analysis by convolutional neural network and regular evaluation will result in better accuracy and helps in eliminating the false-negative results. INASNET is based on the combined platform of InceptionNet and Neural network architecture search which will result in having higher and faster predictions. Regular testing, faster results, economically viable testing using X-ray images will help the front line workers to make a win over COVID-19.


Subject(s)
COVID-19 , Deep Learning , Pneumonia , Algorithms , COVID-19/diagnostic imaging , Humans , Neural Networks, Computer , RNA, Viral , Radiography, Thoracic/methods , SARS-CoV-2 , X-Rays
6.
Ceylon Med J ; 66(4): 168-176, 2021 Dec 31.
Article in English | MEDLINE | ID: covidwho-1847468

ABSTRACT

Introduction: Although several chest X-ray (CXR) severity scoring systems are in use to assess Covid-19 pneumonia (CP), inhomogeneity has been observed among the assessment methodologies. Objectives: To describe and validate severity scoring system based on different features to identify the most suitable scoring system to predict CP severity and outcome. Method: This retrospective study examined CXRs (n=147) of CP patients (n=85) to calculate severity scores using three scoring systems based on area infiltrated and the density patterns: A, A&D, and New. The best scoring system to predict the mortality was identified using the area under the curve (AUC) and linear regression analysis. Results: Regardless of the scoring system used, CXR severity has shown a good correlation to clinical CP severity (A: χ2=6.745; p =0.034; A&D: χ2=12.404; p =0.002; New: χ2=10.219; p =0.006). The mortality predictability of all scoring systems were satisfactory with high AUC ("A": AUC=0.685, sensitivity:67.4%, specificity:54.5% at a cut-off point of 5/8; positive predictive value (PPV): 40.3%, negative predictive value (NPV):78.6%"; A&D": AUC=0.748, sensitivity:69.6%, specificity:61.4% at a cut-off point of 7/16, PPV:45.1%, NPV:81.6%; "New": AUC=0.727; p ≤ 0.001, sensitivity:67.4%, specificity:68.3% at a cut-off point of 18/48, PPV:49.2%, NPV:82.1%). Additionally, the mortality predicting ability of the "New" scoring system was significantly higher than the other two systems (OR:2.897; CI [1.071-7.8.36]; p=0.036). Conclusion: Covid-19 pneumonia severity assessed with the CXR severity scoring systems correlated significantly with clinical severity and outcome. Overall, the "New" CXR severity scoring system is comparatively better at predicting the mortality of Covid-19 pneumonia.


Subject(s)
COVID-19 , COVID-19/diagnostic imaging , Humans , Predictive Value of Tests , Retrospective Studies , X-Rays
7.
Int J Mol Sci ; 23(9)2022 May 09.
Article in English | MEDLINE | ID: covidwho-1847347

ABSTRACT

3CLpro of SARS-CoV-2 is a promising target for developing anti-COVID19 agents. In order to evaluate the catalytic activity of 3CLpros according to the presence or absence of the dimerization domain, two forms had been purified and tested. Enzyme kinetic studies with a FRET method revealed that the catalytic domain alone presents enzymatic activity, despite it being approximately 8.6 times less than that in the full domain. The catalytic domain was crystallized and its X-ray crystal structure has been determined to 2.3 Å resolution. There are four protomers in the asymmetric unit. Intriguingly, they were packed as a dimer though the dimerization domain was absent. The RMSD of superimposed two catalytic domains was 0.190 for 182 Cα atoms. A part of the long hinge loop (LH-loop) from Gln189 to Asp197 was not built in the model due to its flexibility. The crystal structure indicates that the decreased proteolytic activity of the catalytic domain was due to the incomplete construction of the substrate binding part built by the LH-loop. A structural survey with other 3CLpros showed that SARS-CoV families do not have interactions between DM-loop due to the conformational difference at the last turn of helix α7 compared with others. Therefore, we can conclude that the monomeric form contains nascent enzyme activity and that its efficiency increases by dimerization. This new insight may contribute to understanding the behavior of SARS-CoV-2 3CLpro and thus be useful in developing anti-COVID-19 agents.


Subject(s)
COVID-19 , SARS-CoV-2 , Catalytic Domain , Coronavirus 3C Proteases , Dimerization , Humans , Kinetics , X-Rays
8.
Comput Biol Med ; 145: 105498, 2022 06.
Article in English | MEDLINE | ID: covidwho-1838703

ABSTRACT

BACKGROUND: Automated generation of radiological reports for different imaging modalities is essentially required to smoothen the clinical workflow and alleviate radiologists' workload. It involves the careful amalgamation of image processing techniques for medical image interpretation and language generation techniques for report generation. This paper presents CADxReport, a coattention and reinforcement learning based technique for generating clinically accurate reports from chest x-ray (CXR) images. METHOD: CADxReport, uses VGG19 network pre-trained over ImageNet dataset and a multi-label classifier for extracting visual and semantic features from CXR images, respectively. The co-attention mechanism with both the features is used to generate a context vector, which is then passed to HLSTM for radiological report generation. The model is trained using reinforcement learning to maximize CIDEr rewards. OpenI dataset, having 7, 470 CXRs along with 3, 955 associated structured radiological reports, is used for training and testing. RESULTS: Our proposed model is able to generate clinically accurate reports from CXR images. The quantitative evaluations confirm satisfactory results by achieving the following performance scores: BLEU-1 = 0.577, BLEU-2 = 0.478, BLEU-3 = 0.403, BLEU-4 = 0.346, ROUGE = 0.618 and CIDEr = 0.380. CONCLUSIONS: The evaluation using BLEU, ROUGE, and CIDEr score metrics indicates that the proposed model generates sufficiently accurate CXR reports and outperforms most of the state-of-the-art methods for the given task.


Subject(s)
Deep Learning , Image Processing, Computer-Assisted , Radiography , Thorax , X-Rays
9.
Comput Biol Med ; 145: 105442, 2022 06.
Article in English | MEDLINE | ID: covidwho-1838691

ABSTRACT

Chest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR).


Subject(s)
Deep Learning , Humans , Neural Networks, Computer , Radiography , X-Rays
10.
BMC Med Res Methodol ; 22(1): 125, 2022 04 28.
Article in English | MEDLINE | ID: covidwho-1817183

ABSTRACT

BACKGROUND: The health crisis resulting from the global COVID-19 pandemic highlighted more than ever the need for rapid, reliable and safe methods of diagnosis and monitoring of respiratory diseases. To study pulmonary involvement in detail, one of the most common resources is the use of different lung imaging modalities (like chest radiography) to explore the possible affected areas. METHODS: The study of patient characteristics like sex and age in pathologies of this type is crucial for gaining knowledge of the disease and for avoiding biases due to the clear scarcity of data when developing representative systems. In this work, we performed an analysis of these factors in chest X-ray images to identify biases. Specifically, 11 imbalance scenarios were defined with female and male COVID-19 patients present in different proportions for the sex analysis, and 6 scenarios where only one specific age range was used for training for the age factor. In each study, 3 different approaches for automatic COVID-19 screening were used: Normal vs COVID-19, Pneumonia vs COVID-19 and Non-COVID-19 vs COVID-19. The study was validated using two public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process. RESULTS: The results for the sex-related analysis indicate this factor slightly affects the system in the Normal VS COVID-19 and Pneumonia VS COVID-19 approaches, although the identified differences are not relevant enough to worsen considerably the system. Regarding the age-related analysis, this factor was observed to be influencing the system in a more consistent way than the sex factor, as it was present in all considered scenarios. However, this worsening does not represent a major factor, as it is not of great magnitude. CONCLUSIONS: Multiple studies have been conducted in other fields in order to determine if certain patient characteristics such as sex or age influenced these deep learning systems. However, to the best of our knowledge, this study has not been done for COVID-19 despite the urgency and lack of COVID-19 chest x-ray images. The presented results evidenced that the proposed methodology and tested approaches allow a robust and reliable analysis to support the clinical decision-making process in this pandemic scenario.


Subject(s)
COVID-19 , Deep Learning , Pneumonia , COVID-19/diagnostic imaging , Female , Humans , Male , Pandemics , Radiography , X-Rays
11.
Talanta ; 245: 123486, 2022 Aug 01.
Article in English | MEDLINE | ID: covidwho-1796081

ABSTRACT

Cancer is the leading cause of death in many countries. The development of new methods for early screening of cancers is highly desired. Targeted metallomics has been successfully applied in the screening of cancers through quantification of elements in the matrix, which is time consuming and requires combined techniques for the quantification due to the large elemental difference in the matrix. This work proposed a non-targeted metallomics (NTM) approach through synchrotron radiation based X-ray fluorescence (SRXRF) and machine learning algorithms (MLAs) for the screening of cancers. One hundred serum samples were collected from cancer patients who were confirmed by pathological examination with 100 matched serum samples from healthy volunteers. The serum samples were studied with SRXRF and the spectra from both groups were directly clarified through MLAs, which did not require the quantification of elements. The NTM approach through SRXRF and MLAs is fast (5s for data collection for one sample) and accurate (over 96% accuracy) for cancer screening. Besides, this approach can also identify the most affected elements in cancer samples like Ca, Zn and Ti as we found, which may shed lights on the drug development for cancer treatment. This NTM approach can also be applied through commercially available XRF instruments or ICP-TOF-MS with MLAs. It has the potential for the screening and prediction of other diseases like COVID-19 and neurodegenerative diseases in a high throughput and least invasive way.


Subject(s)
COVID-19 , Neoplasms , COVID-19/diagnosis , Early Detection of Cancer , Humans , Machine Learning , Neoplasms/diagnostic imaging , Spectrometry, X-Ray Emission , Synchrotrons , X-Rays
12.
Comput Intell Neurosci ; 2022: 4694567, 2022.
Article in English | MEDLINE | ID: covidwho-1794372

ABSTRACT

Background and Objective. The new coronavirus disease (known as COVID-19) was first identified in Wuhan and quickly spread worldwide, wreaking havoc on the economy and people's everyday lives. As the number of COVID-19 cases is rapidly increasing, a reliable detection technique is needed to identify affected individuals and care for them in the early stages of COVID-19 and reduce the virus's transmission. The most accessible method for COVID-19 identification is Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR); however, it is time-consuming and has false-negative results. These limitations encouraged us to propose a novel framework based on deep learning that can aid radiologists in diagnosing COVID-19 cases from chest X-ray images. Methods. In this paper, a pretrained network, DenseNet169, was employed to extract features from X-ray images. Features were chosen by a feature selection method, i.e., analysis of variance (ANOVA), to reduce computations and time complexity while overcoming the curse of dimensionality to improve accuracy. Finally, selected features were classified by the eXtreme Gradient Boosting (XGBoost). The ChestX-ray8 dataset was employed to train and evaluate the proposed method. Results and Conclusion. The proposed method reached 98.72% accuracy for two-class classification (COVID-19, No-findings) and 92% accuracy for multiclass classification (COVID-19, No-findings, and Pneumonia). The proposed method's precision, recall, and specificity rates on two-class classification were 99.21%, 93.33%, and 100%, respectively. Also, the proposed method achieved 94.07% precision, 88.46% recall, and 100% specificity for multiclass classification. The experimental results show that the proposed framework outperforms other methods and can be helpful for radiologists in the diagnosis of COVID-19 cases.


Subject(s)
COVID-19 , Deep Learning , Analysis of Variance , Humans , SARS-CoV-2 , X-Rays
13.
Sci Rep ; 12(1): 6193, 2022 04 13.
Article in English | MEDLINE | ID: covidwho-1788318

ABSTRACT

The COVID-19 pandemic repeatedly overwhelms healthcare systems capacity and forced the development and implementation of triage guidelines in ICU for scarce resources (e.g. mechanical ventilation). These guidelines were often based on known risk factors for COVID-19. It is proposed that image data, specifically bedside computed X-ray (CXR), provide additional predictive information on mortality following mechanical ventilation that can be incorporated in the guidelines. Deep transfer learning was used to extract convolutional features from a systematically collected, multi-institutional dataset of COVID-19 ICU patients. A model predicting outcome of mechanical ventilation (remission or mortality) was trained on the extracted features and compared to a model based on known, aggregated risk factors. The model reached a 0.702 area under the curve (95% CI 0.707-0.694) at predicting mechanical ventilation outcome from pre-intubation CXRs, higher than the risk factor model. Combining imaging data and risk factors increased model performance to 0.743 AUC (95% CI 0.746-0.732). Additionally, a post-hoc analysis showed an increase performance on high-quality than low-quality CXRs, suggesting that using only high-quality images would result in an even stronger model.


Subject(s)
COVID-19 , Deep Learning , Humans , Intensive Care Units , Pandemics , Respiration, Artificial , X-Rays
14.
Radiol Med ; 127(6): 602-608, 2022 Jun.
Article in English | MEDLINE | ID: covidwho-1787865

ABSTRACT

To evaluate the possible prognostic significance of the development of peripheral consolidations at chest x-ray in COVID-19 pneumonia, we retrospectively studied 92 patients with severe respiratory failure (PaO2/FiO2 ratio < 200 mmHg) that underwent at least two chest x-ray examinations (baseline and within 10 days of admission). Patients were divided in two groups based on the evolution of chest x-ray toward the appearance of peripheral consolidations or toward a greater extension of the lung abnormalities but without peripheral consolidations. Patients who developed lung abnormalities without peripheral consolidations as well as patients who developed peripheral consolidations showed, at follow-up, a significant worsening of the PaO2/FiO2 ratio but a significantly lower mortality and intubation rate was observed in patients with peripheral consolidations at chest x-ray. The progression of chest x-ray toward peripheral consolidations is an independent prognostic factor associated with lower intubation rate and mortality.


Subject(s)
COVID-19 , COVID-19/diagnostic imaging , Humans , Lung/diagnostic imaging , Prognosis , Retrospective Studies , Tomography, X-Ray Computed , X-Rays
15.
Ann Biomed Eng ; 50(7): 825-835, 2022 Jul.
Article in English | MEDLINE | ID: covidwho-1787835

ABSTRACT

Coronavirus 2019 (COVID-19) is a highly transmissible and pathogenic virus caused by severe respiratory syndrome coronavirus 2 (SARS-CoV-2), which first appeared in Wuhan, China, and has since spread in the whole world. This pathology has caused a major health crisis in the world. However, the early detection of this anomaly is a key task to minimize their spread. Artificial intelligence is one of the approaches commonly used by researchers to discover the problems it causes and provide solutions. These estimates would help enable health systems to take the necessary steps to diagnose and track cases of COVID. In this review, we intend to offer a novel method of automatic detection of COVID-19 using tomographic images (CT) and radiographic images (Chest X-ray). In order to improve the performance of the detection system for this outbreak, we used two deep learning models: the VGG and ResNet. The results of the experiments show that our proposed models achieved the best accuracy of 99.35 and 96.77% respectively for VGG19 and ResNet50 with all the chest X-ray images.


Subject(s)
COVID-19 , Deep Learning , Artificial Intelligence , COVID-19/diagnostic imaging , Humans , SARS-CoV-2 , Tomography, X-Ray Computed/methods , X-Rays
16.
PLoS One ; 17(4): e0265949, 2022.
Article in English | MEDLINE | ID: covidwho-1775451

ABSTRACT

BACKGROUND: The SARS-CoV-2 pandemic began in early 2020, paralyzing human life all over the world and threatening our security. Thus, the need for an effective, novel approach to diagnosing, preventing, and treating COVID-19 infections became paramount. METHODS: This article proposes a machine learning-based method for the classification of chest X-ray images. We also examined some of the pre-processing methods such as thresholding, blurring, and histogram equalization. RESULTS: We found the F1-score results rose to 97%, 96%, and 99% for the three analyzed classes: healthy, COVID-19, and pneumonia, respectively. CONCLUSION: Our research provides proof that machine learning can be used to support medics in chest X-ray classification and improving pre-processing leads to improvements in accuracy, precision, recall, and F1-scores.


Subject(s)
COVID-19 , Deep Learning , Algorithms , COVID-19/diagnostic imaging , Humans , SARS-CoV-2 , X-Rays
17.
J Xray Sci Technol ; 30(2): 365-376, 2022.
Article in English | MEDLINE | ID: covidwho-1771015

ABSTRACT

BACKGROUND: Chest X-ray images are widely used to detect many different lung diseases. However, reading chest X-ray images to accurately detect and classify different lung diseases by doctors is often difficult with large inter-reader variability. Thus, there is a huge demand for developing computer-aided automated schemes of chest X-ray images to help doctors more accurately and efficiently detect lung diseases depicting on chest X-ray images. OBJECTIVE: To develop convolution neural network (CNN) based deep learning models and compare their feasibility and performance to classify 14 chest diseases or pathology patterns based on chest X-rays. METHOD: Several CNN models pre-trained using ImageNet dataset are modified as transfer learning models and applied to classify between 14 different chest pathology and normal chest patterns depicting on chest X-ray images. In this process, a deep convolution generative adversarial network (DC-GAN) is also trained to mitigate the effects of small or imbalanced dataset and generate synthetic images to balance the dataset of different diseases. The classification models are trained and tested using a large dataset involving 91,324 frontal-view chest X-ray images. RESULTS: In this study, eight models are trained and compared. Among them, ResNet-152 model achieves an accuracy of 67% and 62% with and without data augmentation, respectively. Inception-V3, NasNetLarge, Xcaption, ResNet-50 and InceptionResNetV2 achieve accuracy of 68%, 62%, 66%, 66% and 54% respectively. Additionally, Resnet-152 with data augmentation achieves an accuracy of 83% but only for six classes. CONCLUSION: This study solves the problem of having fewer data by using GAN-based techniques to add synthetic images and demonstrates the feasibility of applying transfer learning CNN method to help classify 14 types of chest diseases depicting on chest X-ray images.


Subject(s)
COVID-19 , Deep Learning , Algorithms , Humans , Neural Networks, Computer , SARS-CoV-2 , X-Rays
18.
J Healthc Eng ; 2022: 6074538, 2022.
Article in English | MEDLINE | ID: covidwho-1770040

ABSTRACT

Early and accurate detection of COVID-19 is an essential process to curb the spread of this deadly disease and its mortality rate. Chest radiology scan is a significant tool for early management and diagnosis of COVID-19 since the virus targets the respiratory system. Chest X-ray (CXR) images are highly useful in the effective detection of COVID-19, thanks to its availability, cost-effective means, and rapid outcomes. In addition, Artificial Intelligence (AI) techniques such as deep learning (DL) models play a significant role in designing automated diagnostic processes using CXR images. With this motivation, the current study presents a new Quantum Seagull Optimization Algorithm with DL-based COVID-19 diagnosis model, named QSGOA-DL technique. The proposed QSGOA-DL technique intends to detect and classify COVID-19 with the help of CXR images. In this regard, the QSGOA-DL technique involves the design of EfficientNet-B4 as a feature extractor, whereas hyperparameter optimization is carried out with the help of QSGOA technique. Moreover, the classification process is performed by a multilayer extreme learning machine (MELM) model. The novelty of the study lies in the designing of QSGOA for hyperparameter optimization of the EfficientNet-B4 model. An extensive series of simulations was carried out on the benchmark test CXR dataset, and the results were assessed under different aspects. The simulation results demonstrate the promising performance of the proposed QSGOA-DL technique compared to recent approaches.


Subject(s)
Artificial Intelligence , COVID-19 , COVID-19/diagnostic imaging , COVID-19 Testing , Humans , Machine Learning , X-Rays
19.
Sensors (Basel) ; 22(6)2022 Mar 15.
Article in English | MEDLINE | ID: covidwho-1765833

ABSTRACT

Pneumothorax is a thoracic disease leading to failure of the respiratory system, cardiac arrest, or in extreme cases, death. Chest X-ray (CXR) imaging is the primary diagnostic imaging technique for the diagnosis of pneumothorax. A computerized diagnosis system can detect pneumothorax in chest radiographic images, which provide substantial benefits in disease diagnosis. In the present work, a deep learning neural network model is proposed to detect the regions of pneumothoraces in the chest X-ray images. The model incorporates a Mask Regional Convolutional Neural Network (Mask RCNN) framework and transfer learning with ResNet101 as a backbone feature pyramid network (FPN). The proposed model was trained on a pneumothorax dataset prepared by the Society for Imaging Informatics in Medicine in association with American college of Radiology (SIIM-ACR). The present work compares the operation of the proposed MRCNN model based on ResNet101 as an FPN with the conventional model based on ResNet50 as an FPN. The proposed model had lower class loss, bounding box loss, and mask loss as compared to the conventional model based on ResNet50 as an FPN. Both models were simulated with a learning rate of 0.0004 and 0.0006 with 10 and 12 epochs, respectively.


Subject(s)
Deep Learning , Pneumothorax , Computers , Humans , Pneumothorax/diagnostic imaging , Thorax , X-Rays
20.
Comput Biol Med ; 145: 105466, 2022 06.
Article in English | MEDLINE | ID: covidwho-1763670

ABSTRACT

Fast and accurate diagnosis is critical for the triage and management of pneumonia, particularly in the current scenario of a COVID-19 pandemic, where this pathology is a major symptom of the infection. With the objective of providing tools for that purpose, this study assesses the potential of three textural image characterisation methods: radiomics, fractal dimension and the recently developed superpixel-based histon, as biomarkers to be used for training Artificial Intelligence (AI) models in order to detect pneumonia in chest X-ray images. Models generated from three different AI algorithms have been studied: K-Nearest Neighbors, Support Vector Machine and Random Forest. Two open-access image datasets were used in this study. In the first one, a dataset composed of paediatric chest X-ray, the best performing generated models achieved an 83.3% accuracy with 89% sensitivity for radiomics, 89.9% accuracy with 93.6% sensitivity for fractal dimension and 91.3% accuracy with 90.5% sensitivity for superpixels based histon. Second, a dataset derived from an image repository developed primarily as a tool for studying COVID-19 was used. For this dataset, the best performing generated models resulted in a 95.3% accuracy with 99.2% sensitivity for radiomics, 99% accuracy with 100% sensitivity for fractal dimension and 99% accuracy with 98.6% sensitivity for superpixel-based histons. The results confirm the validity of the tested methods as reliable and easy-to-implement automatic diagnostic tools for pneumonia.


Subject(s)
COVID-19 , Deep Learning , Artificial Intelligence , COVID-19/diagnostic imaging , Child , Humans , Pandemics , SARS-CoV-2 , X-Rays
SELECTION OF CITATIONS
SEARCH DETAIL