ABSTRACT
OBJECTIVE: To assess the potential therapeutic role of exercise on health-related quality of life, assessed by the Pediatric Outcomes Data Collection Instrument (PODCI), coronary flow reserve (CFR), cardiac function, cardiorespiratory fitness, and inflammatory and cardiac blood markers in multisystemic inflammatory syndrome in children (MIS-C) patients. METHODS: This is a case series study of a 12-wk, home-based exercise intervention in children and adolescents after MIS-C diagnosis. From 16 MIS-C patients followed at our clinic, 6 were included (age: 7-16 years; 3 females). Three of them withdrew before the intervention and served as controls. The primary outcome was health-related quality of life, assessed PODCI. Secondary outcomes were CFR assessed by 13N-ammonia PET-CT imaging, cardiac function by echocardiography, cardiorespiratory fitness, and inflammatory and cardiac blood markers. RESULTS: In general, patients showed poor health-related quality of life, which seemed to be improved with exercise. Additionally, exercised patients showed improvements in coronary flow reserve, cardiac function, and aerobic conditioning. Non-exercised patients exhibited a slower pattern of recovery, particularly in relation to health-related quality of life and aerobic conditioning. CONCLUSIONS: Our results suggest that exercise may play a therapeutic role in the treatment of post-discharge MIS-C patients. As our design does not allow inferring causality, randomized controlled trials are necessary to confirm these preliminary findings.
ABSTRACT
The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.
ABSTRACT
Nowadays, with the outbreak of COVID-19, the prevention and treatment of COVID-19 has gradually become the focus of social disease prevention, and most patients are also more concerned about the symptoms. COVID-19 has symptoms similar to the common cold, and it cannot be diagnosed based on the symptoms shown by the patient, so it is necessary to observe medical images of the lungs to finally determine whether they are COVID-19 positive. As the number of patients with symptoms similar to pneumonia increases, more and more medical images of the lungs need to be generated. At the same time, the number of physicians at this stage is far from meeting the needs of patients, resulting in patients unable to detect and understand their own conditions in time. In this regard, we have performed image augmentation, data cleaning, and designed a deep learning classification network based on the data set of COVID-19 lung medical images. accurate classification judgment. The network can achieve 95.76% classification accuracy for this task through a new fine-tuning method and hyperparameter tuning we designed, which has higher accuracy and less training time than the classic convolutional neural network model. © 2023 SPIE.
ABSTRACT
The World Health Organization has labeled the novel coronavirus illness (COVID-19) a pandemic since March 2020. It's a new viral infection with a respiratory tropism that could lead to atypical pneumonia. Thus, according to experts, early detection of the positive cases with people infected by the COVID-19 virus is highly needed. In this manner, patients will be segregated from other individuals, and the infection will not spread. As a result, developing early detection and diagnosis procedures to enable a speedy treatment process and stop the transmission of the virus has become a focus of research. Alternative early-screening approaches have become necessary due to the time-consuming nature of the current testing methodology such as Reverse transcription polymerase chain reaction (RT-PCR) test. The methods for detecting COVID-19 using deep learning (DL) algorithms using sound modality, which have become an active research area in recent years, have been thoroughly reviewed in this work. Although the majority of the newly proposed methods are based on medical images (i.e. X-ray and CT scans), we show in this comprehensive survey that the sound modality can be a good alternative to these methods, providing faster and easiest way to create a database with a high performance. We also present the most popular sound databases proposed for COVID-19 detection. © 2022 IEEE.
ABSTRACT
Background: The 2019 novel coronavirus disease (COVID-19) has been reported as pandemy and the number of patients continues to rise. Based on recent data, cardiac injury is a prominent feature of the disease, leading to increased morbidity and mortality. In the present study we aimed to evaluate myocardial dysfunction using transthoracic echocardiography (TTE) and tissue Doppler imaging (TDI) in hospitalized COVID-19 patients. Methods and Results: We recruited 30 patients (56.7% male, 55.80 +/- 14.949 years) who were hospitalized with the diagnosis COVID-19 infection. We analyzed left ventricular (LV) and right ventricular (RV) conventional and TDI parameters at the time of hospitalization and during the course of the disease. Patients without any cardiac disease and with preserved LV ejection fraction (EF) were included. TTE examination was performed and all the variables were recorded and analyzed retrospectively. We observed that both LV and RV conventional echocardiographic parameters were similar when the day of admission to the hospital was compared to the 5th day of the disease. Regarding TDI analysis, we demonstrated significant impairment in LV septal and lateral deformation (P < 0.001). In the correlation analysis no marked correlation was observed between impairment in LV deformation and inflammation biomarkers. Conclusion(s): Cardiac involvement is an important feature of the COVID-19 infection but the exact mechanism is still undefined. Echocardiography is an essential technique to describe myocardial injury and provide new concepts for the possible definitions of cardiac dysfunction.Copyright © 2023 The Author(s).
ABSTRACT
Background: COVID-19 has been associated with cerebral microbleeds (CMB). Previously, an association of ApoE4 with COVID-19 severity and CMBs in autopsy was found. In this study, we investigated if carrying the Apoe4 allele relates to the number of CMBs in magnetic resonance imaging (MRI) in patients recovered from COVID-19. Material(s) and Method(s): Adult patients recovered from COVID-19 and a control group without a history of COVID-19 was recruited. Exclusion criteria were major neurologic disease, developmental disability or pregnancy. The participants underwent brain MRI 6 months after infection, and a blinded neuroradiologist analyzed the findings. ApoE was genotyped using a microarray. Statistical analysis was performed using the statistical software R. A negative binomial model was chosen based on the distribution of CMBs. Result(s): Of the 216 subjects that underwent MRI, 168 consented to genetic testing, additionally 2 patients were excluded due to extensive CMBs and 1 due to diffuse axonal injury. We included 113 COVID-19 patients (49 ICU-treated, 29 ward-treated and 35 home-isolated) and 52 controls. The most prevalent comorbidities were hypertension, asthma and diabetes. CMBs was found in 47 subjects, with the number of CMBs ranging from 0 to 26. The ApoeE4 allele was carried by 37%, equally distributed among the groups. After adjustment, age (aRR = 1.06, p = 0.007) and COVID-19 (aRR = 2.59, p = 0.038) were independently associated with CMBs. The ApoE4 allele (aRR = 2.16, p = 0.07, CI = 0.94-5.10) was not significant. Conclusion(s): Age and previous COVID-19, but not possession of the ApoeE4 allele, were independently associated with the number of CMBs.
ABSTRACT
It is important to evaluate medical imaging artificial intelligence (AI) models for possible implicit discrimination (ability to distinguish between subgroups not related to the specific clinical task of the AI model) and disparate impact (difference in outcome rate between subgroups). We studied potential implicit discrimination and disparate impact of a published deep learning/AI model for the prediction of ICU admission for COVID-19 within 24 hours of imaging. The IRB-approved, HIPAA-compliant dataset contained 8,357 chest radiography exams from February 2020-January 2022 (12% ICU admission within 24 hours) and was separated by patient into training, validation, and test sets (64%, 16%, 20% split). The AI output was evaluated in two demographic categories: sex assigned at birth (subgroups male and female) and self-reported race (subgroups Black/African-American and White). We failed to show statistical evidence that the model could implicitly discriminate between members of subgroups categorized by race based on prediction scores (area under the receiver operating characteristic curve, AUC: median [95% confidence interval, CI]: 0.53 [0.48, 0.57]) but there was some marginal evidence of implicit discrimination between members of subgroups categorized by sex (AUC: 0.54 [0.51, 0.57]). No statistical evidence for disparate impact (DI) was observed between the race subgroups (i.e. the 95% CI of the ratio of the favorable outcome rate between two subgroups included one) for the example operating point of the maximized Youden index but some evidence of disparate impact to the male subgroup based on sex was observed. These results help develop evaluation of implicit discrimination and disparate impact of AI models in the context of decision thresholds © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.
ABSTRACT
The COVID-19 pandemic has challenged many of the healthcare systems around the world. Many patients who have been hospitalized due to this disease develop lung damage. In low and middle-income countries, people living in rural and remote areas have very limited access to adequate health care. Ultrasound is a safe, portable and accessible alternative;however, it has limitations such as being operator-dependent and requiring a trained professional. The use of lung ultrasound volume sweep imaging is a potential solution for this lack of physicians. In order to support this protocol, image processing together with machine learning is a potential methodology for an automatic lung damage screening system. In this paper we present an automatic detection of lung ultrasound artifacts using a Deep Neural Network, identifying clinical relevant artifacts such as pleural and A-lines contained in the ultrasound examination taken as part of the clinical screening in patients with suspected lung damage. The model achieved encouraging preliminary results such as sensitivity of 94%, specificity of 81%, and accuracy of 89% to identify the presence of A-lines. Finally, the present study could result in an alternative solution for an operator-independent lung damage screening in rural areas, leading to the integration of AI-based technology as a complementary tool for healthcare professionals. © 2023 SPIE.
ABSTRACT
Extensive spread of the coronavirus disease (COVID-19) prompted an investigation of its diagnostic features. Acute viral pneumonia associated with COVID-19 has been described in detail using CT, radiography, and MRI. There is no data in the literature on the descriptive picture observed with dynamic MRI. Considering a comprehensive diagnostic approach, radiologists should know how to correctly recognize and interpret COVID-19 on MRI. This case series demonstrated the ability of dynamic MRI to detect the cloudy sky sign and distinguish it from consolidation in COVID-19 patients, thus presumably distinguishing between early or mild changes and a progressive clinical course. These changes in dynamic lung images on MRI can be recorded depending on the phase of the respiratory cycle. Thus, MRI, as a radiation-free tool that can be used to examine a patient with acute viral pneumonia COVID-19, can be useful in cases where access to computed tomography is limited and dynamic morphofunctional imaging is required. © Eco-Vector, 2023.
ABSTRACT
Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE
ABSTRACT
BackgroundCOVID 19 infection could lead to different sequelae in survivors, known as post-COVID or long COVID 19 syndromes. Some of them are thought to be due to the thrombophylic changes observed in COVID 19 infection, but some are thought to be caused by the administrated (especially high dose) corticosteroid treatment. Avascular necrosis of the femoral head (AVNFH) is a multifactorial disease which leads to compromised vascular supply, ischemia and finally necrosis of the femoral head. As corticosteroids usage and thrombophylic states are among the main known risk factors for the development AVNFH [1], it could be presumed that the frequency of this disease will increase with the COVID 19 pandemic. The exact corticosteroid dose needed for the development of AVNFH is not clear, but it has been stated that a higher daily dose and a larger total cumulative dose increase substantially the risk for the development of osteonecrosis [2].ObjectivesTo describe in detail the characteristics of AVNFH diagnosed in patients after COVID 19 infection.MethodsThe study was done in a tertiary university rheumatological clinic. Data was extracted from the records of patients who have been referred to the clinic because of hip pain between June and December 2022. Inclusion criteria were: - a new onset of uni-or bilateral hip pain that started after a documented COVID 19 infection;and an MRI scan of the hip joints showing osteonecrosis of one or both femoral heads. Exclusion criteria were the presence of hip pain prior to the COVID 19 infection, anamnesis of traumatic injuries of the hips or pelvis, personal history of hypercoagulable states.ResultsNine patients (4 women and 5 men) with an average age 59.1 years (range 38-72) were included in the study. Four patients had been diagnosed with bilateral and five – with unilateral AVNFH, thus 13 hip joints were analysed in total (8 left and 5 right sided). The mean time lap between the COVID 19 infection and the start of the hip pain was 26.2 weeks (range 10-48 weeks). All patients had limited and painful movement in their symptomatic hip(s), especially internal rotation and four of the patients had also elevated CRP levels (mean 11.7 mg/L). The stage of the AVNFH was evaluated according to the Ficat-Arlet classification (0-IV stage). In four hips the AVNFH was stage I, five hips were classified as stage II and the remaining four joints - as stage III. All symptomatic hip joints exhibited effusion/synovitis on both ultrasound examination and the corresponding MRI scan. It should be noted that the presence of hip effusion was found to be related with a worse prognosis in AVNFH [1]. In three patients the amount of the effusion required arthrocentesis and fluid aspiration. The analysis of the joint fluid was consistent with a degenerative disease (i.e., low WBC count with predominant lymphocytes and no crystals). All patients included in our study had received corticosteroids during their COVID19 infection, while 6 of the patients had also been hospitalized due to more severe disease. According to the patients' documentation, the mean cumulative dose of the received corticosteroids was 936.2 mg prednisolone equivalent per patient (range 187-2272 mg).ConclusionAVNFH must not be overlooked in a new onset hip pain after COVID 19 infection. Our results show that corticosteroids administrated during the infection and the presence of hip joint effusion on ultrasound are especially suggestive for the development of osteonecrosis, as they were registered in all of our patients. The presence of these two factors necessitates patient referral for an MRI scan of the hips, in order that AVNFH be detected timely.References[1]Petek D, Hannouche D, Suva D. Osteonecrosis of the femoral head: pathophysiology and current concepts of treatment. EFORT Open Rev. 2019 Mar 15;4(3):85-97.[2]Kerachian MA, Séguin C, Harvey EJ. Glucocorticoids in osteonecrosis of the femoral head: a new understanding of the mechanisms of action. J Steroid Biochem Mol Biol. 2009 Apr;114(3-5):121-8.Acknowledgements:NIL.Disclosur of InterestsPLAMEN TODOROV Speakers bureau: speaker at national level for AbbVie, Novartis and UCB, Lily Mekenyan: None declared, Anastas Batalov Speakers bureau: Speaker at national level for AbbVie, Novartis, Pfizer, Stada, Elly Lilly.
ABSTRACT
This paper introduces the improved method for the COVID-19 classification based on computed tomography (CT) volumes using a combination of a complex-architecture convolutional neural network (CNN) and orthogonal ensemble networks (OEN). The novel coronavirus disease reported in 2019 (COVID-19) is still spreading worldwide. Early and accurate diagnosis of COVID-19 is required in such a situation, and the CT scan is an essential examination. Various computer-aided diagnosis (CAD) methods have been developed to assist and accelerate doctors' diagnoses. Although one of the effective methods is ensemble learning, existing methods combine some major models which do not specialize in COVID-19. In this study, we attempted to improve the performance of a CNN for the COVID-19 classification based on chest CT volumes. The CNN model specializes in feature extraction from anisotropic chest CT volumes. We adopt the OEN, an ensemble learning method considering inter-model diversity, to boost its feature extraction ability. For the experiment, We used chest CT volumes of 1283 cases acquired in multiple medical institutions in Japan. The classification result on 257 test cases indicated that the combination could improve the classification performance. © 2023 SPIE.
ABSTRACT
This study proposes a graph convolutional neural networks (GCN) architecture for fusion of radiological imaging and non-imaging tabular electronic health records (EHR) for the purpose of clinical event prediction. We focused on a cohort of hospitalized patients with positive RT-PCR test for COVID-19 and developed GCN based models to predict three dependent clinical events (discharge from hospital, admission into ICU, and mortality) using demographics, billing codes for procedures and diagnoses and chest X-rays. We hypothesized that the two-fold learning opportunity provided by the GCN is ideal for fusion of imaging information and tabular data as node and edge features, respectively. Our experiments indicate the validity of our hypothesis where GCN based predictive models outperform single modality and traditional fusion models. We compared the proposed models against two variations of imaging-based models, including DenseNet-121 architecture with learnable classification layers and Random Forest classifiers using disease severity score estimated by pre-trained convolutional neural network. GCN based model outperforms both imaging-only methods. We also validated our models on an external dataset where GCN showed valuable generalization capabilities. We noticed that edge-formation function can be adapted even after training the GCN model without limiting application scope of the model. Our models take advantage of this fact for generalization to external data. © 2023 IEEE.
ABSTRACT
With the outbreak of covid-19 in 2020, timely and effective diagnosis and treatment of each covid-19 patient is particularly important. This paper combines the advantages of deep learning in image recognition, takes RESNET as the basic network framework, and carries out the experiment of improving the residual structure on this basis. It is tested on the open source new coronal chest radiograph data set, and the accuracy rate is 82.3%. Through a series of experiments, the training model has the advantages of good generalization, high accuracy and fast convergence. This paper proves the feasibility of the improved residual neural network in the diagnosis of covid-19. © 2023 SPIE.
ABSTRACT
During the pandemic COVID-19, there has been an increase in the number of patients with non-anginal chest pain at cardiologist appointments. Objective. To assess the incidence of signs of pleurisy and pericarditis after COVID-19 in non-comorbid patients with atypical chest pain and describe their characteristics according to echocardiography and magnetic resonance imaging. Materials and methods. From February 2021 to January 2022, 200 outpatients were prospectively enrolled in the study, all of them suffered from a discomfort in the heart region for the first time after SARS-CoV-2 infection. Inclusion criteria: 18-50 years old, 5-12 weeks after SARS-CoV-2 infection, non-anginal chest pain. Exclusion criteria: pneumonia or signs of pulmonary thromboembolism, coronary heart disease, congestive heart failure or kidney disease, clinical or laboratory signs of myocarditis, oncopathology, radiation or chemotherapy of the chest in past medical history. A survey was conducted (yes/no) for the presence of general malaise, quality of life deterioration, hyperthermia, cough. Ultrasound examination of the pericardium and pleura to detect effusion or post-inflammatory changes was performed in accordance with the recommendations. Magnetic resonance imaging was performed if ultrasound imaging was poor or there was no evidence of pericardial or pleural involvement in patients with typical symptoms. Results. 82 women and 118 men were included. Median of age 39 [28-46] years old. Pericarditis was diagnosed in 152 (76%) patients, including effusive pericarditis in 119 (78%), myocarditis in 6 (3%) and myopericarditis in 49 (25%) patients, pleurisy was detected in 22 (11%) patients, exudative pleurisy - in 11 (5.5%) patients with a predominant unilateral lesion of the mediastinal-diaphragmatic region adjacent to the heart. Hyperthermia was recorded in 2.5% of cases, general malaise - in 60% and a decrease in the quality of life - in 84%. Conclusion. Serositis as a cause of atypical chest pain among young non-comorbid patients in early postCOVID was identified in 87% of patients. In the coming years, it is probably worthwhile to perform ultrasound of the pericardium and pleura in all patients with chest pain.Copyright © 2022 Infectious Diseases: News, Opinions, Training.
ABSTRACT
Medical Imaging and Data Resource Center (MIDRC) has been built to support AI-based research in response to the COVID-19 pandemic. One of the main goals of MIDRC is to make data collected in the repository ready for AI analysis. Due to data heterogeneity, there is a need to standardize data and make data-mining easier. Our study aims to stratify imaging data according to underlying anatomy using open-source image processing tools. The experiments were performed using Google Colaboratory on computed tomography (CT) imaging data available from the MIDRC. We adopted the existing open-source tools to process CT series (N=389) to define the image sub-volumes according to body part classification, and additionally identified series slices containing specific anatomic landmarks. Cases with automatically identified chest regions (N=369) were then processed to automatically segment the lungs. In order to assess the accuracy of segmentation, we performed outlier analysis using 3D shape radiomics features extracted from the left and right lungs. Standardized DICOM objects were created to store the resulting segmentations, regions, landmarks and radiomics features. We demonstrated that the MIDRC chest CT collections can be enriched using open-source analysis tools and that data available in MIDRC can be further used to evaluate the robustness of publicly available tools. © 2023 SPIE.
ABSTRACT
The COVID-19 pandemic has made a dramatic impact on human life, medical systems, and financial resources. Due to the disease's pervasive nature, many different and interdisciplinary fields of research pivoted to study the disease. For example, deep learning (DL) techniques were employed early to assess patient diagnosis and prognosis from chest radiographs (CXRs) and computed tomography (CT) scans. While the use of artificial intelligence (AI) in the medical sector has displayed promising results, DL may suffer from lack of reproducibility and generalizability. In this study, the robustness of a pre-trained DL model utilizing the DenseNet-121 architecture was evaluated by using a larger collection of CXRs from the same institution that provided the original model with its test and training datasets. The current test set contained a larger span of dates, incorporated different strains of the virus, and included different immunization statuses. Considering differences in these factors, model performance between the original and current test sets was evaluated using area under the receiver operating characteristic curve (ROC AUC) [95% CI]. Statistical comparisons were performed using the Delong, Kolmogorov-Smirnov, and Wilcoxon rank-sum tests. Uniform manifold approximation and projection (UMAP) was used to help visualize whether underlying causes were responsible for differences in performance between test sets. In the task of classifying between COVID-positive and COVID-negative patients, the DL model achieved an AUC of 0.67 [0.65, 0.70], compared with the original performance of 0.76 [0.73, 0.79]. The results of this study suggest that underlying biases or overfitting may hinder performance when generalizing the model. © 2023 SPIE.
ABSTRACT
During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author
ABSTRACT
The successful elimination of the SARS-Cov2 virus has evaded the society and medical fraternity to date. Months have passed but the virus is still very much present amongst us though its severity and contagiousness have decreased. The pandemic which was first detected in Wuhan, China in late 2019 has had colossal ramifications for the societal, financial and physical well-being of humankind. Timely detection and isolation of infected persons is the only way to contain this contagion. One of the biggest hurdles in accurately detecting Covid-19 is its similarities to other thoracic ailments such as Lung cancer, bacterial and viral Pneumonia, tuberculosis and others. Differential observation is challenging due to identical radioscopic discoveries such as GGOs, crazy paving structures and their combinations. Thorax imaging such as X-rays(CXR) have proven to be an efficient and economical diagnostics for detecting Covid-19 Pneumonia. The proposed work aims at utilising three CNN models namely Inception-V3, DenseNet169 and VGG16 along with feature concatenation and Ensemble technique to correctly predict Covid-19 Pneumonia from Chest X-rays of patients. The Covid-19 Radiography dataset, having a total of 4839 CXR images, has been employed to evaluate the proposed model and accuracy, precision, recall and F1-Score of 97.74%, 97.78%, 97.73% and 97.75% has been obtained. The proposed system can assist medical professionals in detecting Covid-19 from a host of other pulmonary diseases with a high probability. © 2023 IEEE.
ABSTRACT
The global COVID-19 pandemic has caused a health crisis globally. Automated diagnostic methods can control the spread of the pandemic, as well as assists physicians to tackle high workload conditions through the quick treatment of affected patients. Owing to the scarcity of medical images and from different resources, the present image heterogeneity has raised challenges for achieving effective approaches to network training and effectively learning robust features. We propose a multi-joint unit network for the diagnosis of COVID-19 using the joint unit module, which leverages the receptive fields from multiple resolutions for learning rich representations. Existing approaches usually employ a large number of layers to learn the features, which consequently requires more computational power and increases the network complexity. To compensate, our joint unit module extracts low-, same-, and high-resolution feature maps simultaneously using different phases. Later, these learned feature maps are fused and utilized for classification layers. We observed that our model helps to learn sufficient information for classification without a performance loss and with faster convergence. We used three public benchmark datasets to demonstrate the performance of our network. Our proposed network consistently outperforms existing state-of-the-art approaches by demonstrating better accuracy, sensitivity, and specificity and F1-score across all datasets. © 2022 ACM.