Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 24
Filter
1.
Comput Math Methods Med ; 2022: 7631271, 2022.
Article in English | MEDLINE | ID: covidwho-1723964

ABSTRACT

The diagnosis of new diseases is a challenging problem. In the early stage of the emergence of new diseases, there are few case samples; this may lead to the low accuracy of intelligent diagnosis. Because of the advantages of support vector machine (SVM) in dealing with small sample problems, it is selected for the intelligent diagnosis method. The standard SVM diagnosis model updating needs to retrain all samples. It costs huge storage and calculation costs and is difficult to adapt to the changing reality. In order to solve this problem, this paper proposes a new disease diagnosis method based on Fuzzy SVM incremental learning. According to SVM theory, the support vector set and boundary sample set related to the SVM diagnosis model are extracted. Only these sample sets are considered in incremental learning to ensure the accuracy and reduce the cost of calculation and storage. To reduce the impact of noise points caused by the reduction of training samples, FSVM is used to update the diagnosis model, and the generalization is improved. The simulation results on the banana dataset show that the proposed method can improve the classification accuracy from 86.4% to 90.4%. Finally, the method is applied in COVID-19's diagnostic. The diagnostic accuracy reaches 98.2% as the traditional SVM only gets 84%. With the increase of the number of case samples, the model is updated. When the training samples increase to 400, the number of samples participating in training is only 77; the amount of calculation of the updated model is small.


Subject(s)
Diagnosis, Computer-Assisted/methods , Fuzzy Logic , Support Vector Machine , Algorithms , Artificial Intelligence/statistics & numerical data , COVID-19/diagnosis , Computational Biology , Diagnosis, Computer-Assisted/statistics & numerical data , Humans , SARS-CoV-2
2.
Am J Med Genet A ; 188(4): 1142-1148, 2022 04.
Article in English | MEDLINE | ID: covidwho-1593959

ABSTRACT

We studied if clinicians could gain sufficient working knowledge of a computer-assisted diagnostic decision support system (DDSS) (SimulConsult), to make differential diagnoses (DDx) of genetic disorders. We hypothesized that virtual training could be convenient, asynchronous, and effective in teaching clinicians how to use a DDSS. We determined the efficacy of virtual, asynchronous teaching for clinicians to gain working knowledge to make computer-assisted DDx. Our study consisted of three surveys (Baseline, Training, and After Use) and a series of case problems sent to clinicians at Vanderbilt University Medical Center. All participants were able to generate computer-assisted DDx that achieved passing scores of the case problems. Between 75% and 92% agreed/completely agreed the DDSS was useful to their work and for clinical decision support and was easy to use. Participants' use of the DDSS resulted in statistically significant time savings in key tasks and in total time spent on clinical tasks. Our results indicate that virtual, asynchronous teaching can be an effective format to gain a working knowledge of a DDSS, and its clinical use could result in significant time savings across multiple tasks as well as facilitate synergistic interaction between clinicians and lab specialists. This approach is especially pertinent and offers value amid the COVID-19 pandemic.


Subject(s)
Diagnosis, Computer-Assisted , Genetic Diseases, Inborn/diagnosis , Genetic Diseases, Inborn/genetics , Teaching , User-Computer Interface , Decision Support Systems, Clinical , Diagnosis, Computer-Assisted/methods , Education, Medical , Humans , Physicians , Surveys and Questionnaires
3.
BMC Med Imaging ; 21(1): 154, 2021 10 21.
Article in English | MEDLINE | ID: covidwho-1546762

ABSTRACT

BACKGROUND: The outbreak of coronavirus disease 2019 (COVID-19) causes tens of million infection world-wide. Many machine learning methods have been proposed for the computer-aided diagnosis between COVID-19 and community-acquired pneumonia (CAP) from chest computed tomography (CT) images. Most of these methods utilized the location-specific handcrafted features based on the segmentation results to improve the diagnose performance. However, the prerequisite segmentation step is time-consuming and needs the intervention by lots of expert radiologists, which cannot be achieved in the areas with limited medical resources. METHODS: We propose a generative adversarial feature completion and diagnosis network (GACDN) that simultaneously generates handcrafted features by radiomic counterparts and makes accurate diagnoses based on both original and generated features. Specifically, we first calculate the radiomic features from the CT images. Then, in order to fast obtain the location-specific handcrafted features, we use the proposed GACDN to generate them by its corresponding radiomic features. Finally, we use both radiomic features and location-specific handcrafted features for COVID-19 diagnosis. RESULTS: For the performance of our generated location-specific handcrafted features, the results of four basic classifiers show that it has an average of 3.21% increase in diagnoses accuracy. Besides, the experimental results on COVID-19 dataset show that our proposed method achieved superior performance in COVID-19 vs. community acquired pneumonia (CAP) classification compared with the state-of-the-art methods. CONCLUSIONS: The proposed method significantly improves the diagnoses accuracy of COVID-19 vs. CAP in the condition of incomplete location-specific handcrafted features. Besides, it is also applicable in some regions lacking of expert radiologists and high-performance computing resources.


Subject(s)
COVID-19/diagnosis , Deep Learning , Diagnosis, Computer-Assisted/methods , Machine Learning , SARS-CoV-2 , Tomography, X-Ray Computed/methods , COVID-19/epidemiology , Humans
4.
PLoS One ; 16(11): e0258760, 2021.
Article in English | MEDLINE | ID: covidwho-1502068

ABSTRACT

Ali-M3, an artificial intelligence program, analyzes chest computed tomography (CT) and detects the likelihood of coronavirus disease (COVID-19) based on scores ranging from 0 to 1. However, Ali-M3 has not been externally validated. Our aim was to evaluate the accuracy of Ali-M3 for detecting COVID-19 and discuss its clinical value. We evaluated the external validity of Ali-M3 using sequential Japanese sampling data. In this retrospective cohort study, COVID-19 infection probabilities for 617 symptomatic patients were determined using Ali-M3. In 11 Japanese tertiary care facilities, these patients underwent reverse transcription-polymerase chain reaction (RT-PCR) testing. They also underwent chest CT to confirm a diagnosis of COVID-19. Of the 617 patients, 289 (46.8%) were RT-PCR-positive. The area under the curve (AUC) of Ali-M3 for predicting a COVID-19 diagnosis was 0.797 (95% confidence interval: 0.762‒0.833) and the goodness-of-fit was P = 0.156. With a cut-off probability of a diagnosis of COVID-19 by Ali-M3 set at 0.5, the sensitivity and specificity were 80.6% and 68.3%, respectively. A cut-off of 0.2 yielded a sensitivity and specificity of 89.2% and 43.2%, respectively. Among the 223 patients who required oxygen, the AUC was 0.825. Sensitivity at a cut-off of 0.5% and 0.2% was 88.7% and 97.9%, respectively. Although the sensitivity was lower when the days from symptom onset were fewer, the sensitivity increased for both cut-off values after 5 days. We evaluated Ali-M3 using external validation with symptomatic patient data from Japanese tertiary care facilities. As Ali-M3 showed sufficient sensitivity performance, despite a lower specificity performance, Ali-M3 could be useful in excluding a diagnosis of COVID-19.


Subject(s)
COVID-19 Testing/methods , COVID-19/diagnosis , Deep Learning , Diagnosis, Computer-Assisted/methods , Tomography, X-Ray Computed/methods , Adult , Aged , Algorithms , Area Under Curve , Cohort Studies , Female , Humans , Image Processing, Computer-Assisted , Japan/epidemiology , Male , Middle Aged , Probability , ROC Curve , Reproducibility of Results , Retrospective Studies , Reverse Transcriptase Polymerase Chain Reaction , SARS-CoV-2 , Sensitivity and Specificity
5.
Comput Math Methods Med ; 2021: 6919483, 2021.
Article in English | MEDLINE | ID: covidwho-1484105

ABSTRACT

In March 2020, the World Health Organization announced the COVID-19 pandemic, its dangers, and its rapid spread throughout the world. In March 2021, the second wave of the pandemic began with a new strain of COVID-19, which was more dangerous for some countries, including India, recording 400,000 new cases daily and more than 4,000 deaths per day. This pandemic has overloaded the medical sector, especially radiology. Deep-learning techniques have been used to reduce the burden on hospitals and assist physicians for accurate diagnoses. In our study, two models of deep learning, ResNet-50 and AlexNet, were introduced to diagnose X-ray datasets collected from many sources. Each network diagnosed a multiclass (four classes) and a two-class dataset. The images were processed to remove noise, and a data augmentation technique was applied to the minority classes to create a balance between the classes. The features extracted by convolutional neural network (CNN) models were combined with traditional Gray-level Cooccurrence Matrix (GLCM) and Local Binary Pattern (LBP) algorithms in a 1-D vector of each image, which produced more representative features for each disease. Network parameters were tuned for optimum performance. The ResNet-50 network reached accuracy, sensitivity, specificity, and Area Under the Curve (AUC) of 95%, 94.5%, 98%, and 97.10%, respectively, with the multiclasses (COVID-19, viral pneumonia, lung opacity, and normal), while it reached accuracy, sensitivity, specificity, and AUC of 99%, 98%, 98%, and 97.51%, respectively, with the binary classes (COVID-19 and normal).


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , SARS-CoV-2 , Tomography, X-Ray Computed/methods , Algorithms , Computational Biology , Databases, Factual/statistics & numerical data , Diagnosis, Computer-Assisted/methods , Diagnosis, Computer-Assisted/statistics & numerical data , Early Diagnosis , Humans , Lung/diagnostic imaging , Neural Networks, Computer , Pandemics , Pneumonia, Viral/diagnostic imaging , Tomography, X-Ray Computed/statistics & numerical data
6.
Biomed Res Int ; 2021: 2295920, 2021.
Article in English | MEDLINE | ID: covidwho-1476866

ABSTRACT

The COVID-19 epidemic is spreading day by day. Early diagnosis of this disease is essential to provide effective preventive and therapeutic measures. This process can be used by a computer-aided methodology to improve accuracy. In this study, a new and optimal method has been utilized for the diagnosis of COVID-19. Here, a method based on fuzzy C-ordered means (FCOM) along with an improved version of the enhanced capsule network (ECN) has been proposed for this purpose. The proposed ECN method is improved based on mayfly optimization (MFO) algorithm. The suggested technique is then implemented on the chest X-ray COVID-19 images from publicly available datasets. Simulation results are assessed by considering a comparison with some state-of-the-art methods, including FOMPA, MID, and 4S-DT. The results show that the proposed method with 97.08% accuracy and 97.29% precision provides the highest accuracy and reliability compared with the other studied methods. Moreover, the results show that the proposed method with a 97.1% sensitivity rate has the highest ratio. And finally, the proposed method with a 97.47% F1-score rate gives the uppermost value compared to the others.


Subject(s)
Algorithms , COVID-19/diagnostic imaging , Diagnosis, Computer-Assisted/methods , Databases, Factual , Humans , Image Enhancement , Machine Learning , Neural Networks, Computer , Radiography/methods , Sensitivity and Specificity , X-Rays
7.
Front Immunol ; 12: 715072, 2021.
Article in English | MEDLINE | ID: covidwho-1430697

ABSTRACT

Background: Prediction of the severity of COVID-19 at its onset is important for providing adequate and timely management to reduce mortality. Objective: To study the prognostic value of damage parameters and cytokines as predictors of severity of COVID-19 using an extensive immunologic profiling and unbiased artificial intelligence methods. Methods: Sixty hospitalized COVID-19 patients (30 moderate and 30 severe) and 17 healthy controls were included in the study. The damage indicators high mobility group box 1 (HMGB1), lactate dehydrogenase (LDH), aspartate aminotransferase (AST), alanine aminotransferase (ALT), extensive biochemical analyses, a panel of 47 cytokines and chemokines were analyzed at weeks 1, 2 and 7 along with clinical complaints and CT scans of the lungs. Unbiased artificial intelligence (AI) methods (logistic regression and Support Vector Machine and Random Forest algorithms) were applied to investigate the contribution of each parameter to prediction of the severity of the disease. Results: On admission, the severely ill patients had significantly higher levels of LDH, IL-6, monokine induced by gamma interferon (MIG), D-dimer, fibrinogen, glucose than the patients with moderate disease. The levels of macrophage derived cytokine (MDC) were lower in severely ill patients. Based on artificial intelligence analysis, eight parameters (creatinine, glucose, monocyte number, fibrinogen, MDC, MIG, C-reactive protein (CRP) and IL-6 have been identified that could predict with an accuracy of 83-87% whether the patient will develop severe disease. Conclusion: This study identifies the prognostic factors and provides a methodology for making prediction for COVID-19 patients based on widely accepted biomarkers that can be measured in most conventional clinical laboratories worldwide.


Subject(s)
COVID-19/pathology , Diagnosis, Computer-Assisted/methods , Severity of Illness Index , Support Vector Machine , Alanine Transaminase/blood , Aspartate Aminotransferases/blood , Biomarkers/analysis , Cytokines/blood , Female , HMGB1 Protein/blood , Humans , L-Lactate Dehydrogenase/blood , Macrophages/immunology , Male , Middle Aged , Monocytes/immunology , Prognosis , Prospective Studies , SARS-CoV-2
8.
Med Sci Monit ; 27: e931467, 2021 Oct 06.
Article in English | MEDLINE | ID: covidwho-1344552

ABSTRACT

BACKGROUND Effective identification of patients with suspected COVID-19 is vital for the management. This study aimed to establish a simple clinical prediction model for COVID-19 in primary care. MATERIAL AND METHODS We consecutively enrolled 60 confirmed cases and 152 suspected cases with COVID-19 into the study. The training cohort consisted of 30 confirmed and 78 suspected cases, whereas the validation cohort consisted of 30 confirmed and 74 suspected cases. Four clinical variables - epidemiological history (E), body temperature (T), leukocytes count (L), and chest computed tomography (C) - were collected to construct a preliminary prediction model (model A). By integerizing coefficients of model A, a clinical prediction model (model B) was constructed. Finally, the scores of each variable in model B were summed up to build the ETLC score. RESULTS The preliminary prediction model A was Logit (YA)=2.657X1+1.153X2+2.125X3+2.828X4-10.771, while the model B was Logit (YB)=2.5X1+1X2+2X3+3X4-10. No significant difference was found between the area under the curve (AUC) of model A (0.920, 95% CI: 0.875-0.953) and model B (0.919, 95% CI: 0.874-0.952) (Z=0.035, P=0.972). When ETLC score was more than or equal to 9.5, the sensitivity and specificity for COVID-19 was 76.7% (46/60) and 90.1% (137/152), respectively, and the positive and negative predictive values were 75.4% (46/61) and 90.7% (137/151), respectively. CONCLUSIONS The ETLC score is helpful for efficiently identifying patients with suspected COVID-19.


Subject(s)
COVID-19/diagnosis , Diagnosis, Computer-Assisted/methods , Primary Health Care/methods , Body Temperature , COVID-19/epidemiology , Humans , Leukocyte Count , Logistic Models , SARS-CoV-2 , Tomography, X-Ray Computed
9.
Sci Rep ; 11(1): 15343, 2021 07 28.
Article in English | MEDLINE | ID: covidwho-1331392

ABSTRACT

COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.


Subject(s)
COVID-19/diagnosis , COVID-19/mortality , Diagnosis, Computer-Assisted/methods , Forecasting/methods , Neural Networks, Computer , Algorithms , Deep Learning , Humans , Probability , SARS-CoV-2/isolation & purification
10.
Comput Math Methods Med ; 2021: 9998379, 2021.
Article in English | MEDLINE | ID: covidwho-1314186

ABSTRACT

In recent years, computerized biomedical imaging and analysis have become extremely promising, more interesting, and highly beneficial. They provide remarkable information in the diagnoses of skin lesions. There have been developments in modern diagnostic systems that can help detect melanoma in its early stages to save the lives of many people. There is also a significant growth in the design of computer-aided diagnosis (CAD) systems using advanced artificial intelligence. The purpose of the present research is to develop a system to diagnose skin cancer, one that will lead to a high level of detection of the skin cancer. The proposed system was developed using deep learning and traditional artificial intelligence machine learning algorithms. The dermoscopy images were collected from the PH2 and ISIC 2018 in order to examine the diagnose system. The developed system is divided into feature-based and deep leaning. The feature-based system was developed based on feature-extracting methods. In order to segment the lesion from dermoscopy images, the active contour method was proposed. These skin lesions were processed using hybrid feature extractions, namely, the Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods to extract the texture features. The obtained features were then processed using the artificial neural network (ANNs) algorithm. In the second system, the convolutional neural network (CNNs) algorithm was applied for the efficient classification of skin diseases; the CNNs were pretrained using large AlexNet and ResNet50 transfer learning models. The experimental results show that the proposed method outperformed the state-of-art methods for HP2 and ISIC 2018 datasets. Standard evaluation metrics like accuracy, specificity, sensitivity, precision, recall, and F-score were employed to evaluate the results of the two proposed systems. The ANN model achieved the highest accuracy for PH2 (97.50%) and ISIC 2018 (98.35%) compared with the CNN model. The evaluation and comparison, proposed systems for classification and detection of melanoma are presented.


Subject(s)
Diagnosis, Computer-Assisted/methods , Melanoma/diagnostic imaging , Skin Neoplasms/diagnostic imaging , Algorithms , Artificial Intelligence , Computational Biology , Databases, Factual/statistics & numerical data , Deep Learning , Dermoscopy , Diagnosis, Computer-Assisted/statistics & numerical data , Early Detection of Cancer/methods , Early Detection of Cancer/statistics & numerical data , Humans , Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Image Interpretation, Computer-Assisted/statistics & numerical data , Neural Networks, Computer , Skin Diseases/classification , Skin Diseases/diagnostic imaging
11.
Sci Rep ; 11(1): 11591, 2021 06 02.
Article in English | MEDLINE | ID: covidwho-1253986

ABSTRACT

Making timely assessments of disease progression in patients with COVID-19 could help offer the best personalized treatment. The purpose of this study was to explore an effective model to predict the outcome of patients with COVID-19. We retrospectively included 188 patients (124 in the training set and 64 in the test set) diagnosed with COVID-19. Patients were divided into aggravation and improvement groups according to the disease progression. Three kinds of models were established, including the radiomics, clinical, and combined model. Receiver operating characteristic curves, decision curves, and Delong's test were used to evaluate and compare the models. Our analysis showed that all the established prediction models had good predictive performance in predicting the progress and outcome of COVID-19.


Subject(s)
COVID-19/diagnostic imaging , Tomography, X-Ray Computed , Aged , COVID-19/etiology , Diagnosis, Computer-Assisted/methods , Female , Humans , Male , Middle Aged , Models, Theoretical , Prognosis , ROC Curve
12.
Comput Math Methods Med ; 2021: 5527271, 2021.
Article in English | MEDLINE | ID: covidwho-1226786

ABSTRACT

The reverse transcriptase polymerase chain reaction (RT-PCR) is still the routinely used test for the diagnosis of SARS-CoV-2 (COVID-19). However, according to several reports, RT-PCR showed a low sensitivity and multiple tests may be required to rule out false negative results. Recently, chest computed tomography (CT) has been an efficient tool to diagnose COVID-19 as it is directly affecting the lungs. In this paper, we investigate the application of pre-trained models in diagnosing patients who are positive for COVID-19 and differentiating it from normal patients, who tested negative for coronavirus. The study aims to compare the generalization capabilities of deep learning models with two thoracic radiologists in diagnosing COVID-19 chest CT images. A dataset of 3000 images was obtained from the Near East Hospital, Cyprus, and used to train and to test the three employed pre-trained models. In a test set of 250 images used to evaluate the deep neural networks and the radiologists, it was found that deep networks (ResNet-18, ResNet-50, and DenseNet-201) can outperform the radiologists in terms of higher accuracy (97.8%), sensitivity (98.1%), specificity (97.3%), precision (98.4%), and F1-score (198.25%), in classifying COVID-19 images.


Subject(s)
COVID-19 Testing/methods , COVID-19/diagnostic imaging , Deep Learning , Radiologists , SARS-CoV-2 , Tomography, X-Ray Computed , COVID-19/epidemiology , COVID-19 Testing/statistics & numerical data , Databases, Factual , Diagnosis, Computer-Assisted/methods , Diagnosis, Computer-Assisted/statistics & numerical data , Diagnostic Errors/statistics & numerical data , Expert Testimony/statistics & numerical data , Humans , Lung/diagnostic imaging , Mathematical Concepts , Neural Networks, Computer , Pandemics , Radiologists/statistics & numerical data , Tomography, X-Ray Computed/statistics & numerical data
13.
IEEE J Biomed Health Inform ; 25(6): 1881-1891, 2021 06.
Article in English | MEDLINE | ID: covidwho-1174999

ABSTRACT

In the present epidemic of the coronavirus disease 2019 (COVID-19), radiological imaging modalities, such as X-ray and computed tomography (CT), have been identified as effective diagnostic tools. However, the subjective assessment of radiographic examination is a time-consuming task and demands expert radiologists. Recent advancements in artificial intelligence have enhanced the diagnostic power of computer-aided diagnosis (CAD) tools and assisted medical specialists in making efficient diagnostic decisions. In this work, we propose an optimal multilevel deep-aggregated boosted network to recognize COVID-19 infection from heterogeneous radiographic data, including X-ray and CT images. Our method leverages multilevel deep-aggregated features and multistage training via a mutually beneficial approach to maximize the overall CAD performance. To improve the interpretation of CAD predictions, these multilevel deep features are visualized as additional outputs that can assist radiologists in validating the CAD results. A total of six publicly available datasets were fused to build a single large-scale heterogeneous radiographic collection that was used to analyze the performance of the proposed technique and other baseline methods. To preserve generality of our method, we selected different patient data for training, validation, and testing, and consequently, the data of same patient were not included in training, validation, and testing subsets. In addition, fivefold cross-validation was performed in all the experiments for a fair evaluation. Our method exhibits promising performance values of 95.38%, 95.57%, 92.53%, 98.14%, 93.16%, and 98.55% in terms of average accuracy, F-measure, specificity, sensitivity, precision, and area under the curve, respectively and outperforms various state-of-the-art methods.


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , COVID-19/virology , Diagnosis, Computer-Assisted/methods , Humans , Neural Networks, Computer , SARS-CoV-2/isolation & purification , Tomography, X-Ray Computed/methods
14.
Sci Rep ; 11(1): 7166, 2021 03 30.
Article in English | MEDLINE | ID: covidwho-1159542

ABSTRACT

The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR provides false negative results that can be rectified by clinicians by confronting clinical, biological and imaging data. The combination of RT-PCR and chest-CT could improve diagnosis performance, but this would requires considerable resources for its rapid use in all patients with suspected COVID-19. The potential contribution of machine learning in this situation has not been fully evaluated. The objective of this study was to develop and evaluate machine learning models using routine clinical and laboratory data to improve the performance of RT-PCR and chest-CT for COVID-19 diagnosis among post-emergency hospitalized patients. All adults admitted to the ED for suspected COVID-19, and then hospitalized at Rennes academic hospital, France, between March 20, 2020 and May 5, 2020 were included in the study. Three model types were created: logistic regression, random forest, and neural network. Each model was trained to diagnose COVID-19 using different sets of variables. Area under the receiving operator characteristics curve (AUC) was the primary outcome to evaluate model's performances. 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. The AUC values of chest-CT and RT-PCR increased from 0.778 to 0.892 and from 0.852 to 0.930, respectively, with the contribution of machine learning. After generalization, machine learning models will allow increasing chest-CT and RT-PCR performances for COVID-19 diagnosis.


Subject(s)
COVID-19 Testing/methods , COVID-19/diagnosis , COVID-19/etiology , Diagnosis, Computer-Assisted/methods , Machine Learning , Area Under Curve , COVID-19/diagnostic imaging , Humans , Proof of Concept Study , Reverse Transcriptase Polymerase Chain Reaction , Tomography, X-Ray Computed
15.
Comput Math Methods Med ; 2021: 6633755, 2021.
Article in English | MEDLINE | ID: covidwho-1140372

ABSTRACT

AIM: COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. METHODS: In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. RESULTS: The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. CONCLUSION: This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.


Subject(s)
COVID-19/diagnostic imaging , Community-Acquired Infections/diagnostic imaging , Diagnosis, Computer-Assisted/methods , Imaging, Three-Dimensional/methods , Neural Networks, Computer , Pneumonia/diagnostic imaging , Tuberculosis, Pulmonary/diagnostic imaging , Algorithms , COVID-19/complications , Community-Acquired Infections/complications , Databases, Factual , Humans , Medical Informatics , Pneumonia/complications , Radiography, Thoracic , Reproducibility of Results , Retrospective Studies , Software , Stochastic Processes , Tomography, X-Ray Computed , Tuberculosis, Pulmonary/complications
16.
Biomed Res Int ; 2021: 8840835, 2021.
Article in English | MEDLINE | ID: covidwho-1133375

ABSTRACT

This study established an interpretable machine learning model to predict the severity of coronavirus disease 2019 (COVID-19) and output the most crucial deterioration factors. Clinical information, laboratory tests, and chest computed tomography (CT) scans at admission were collected. Two experienced radiologists reviewed the scans for the patterns, distribution, and CT scores of lung abnormalities. Six machine learning models were established to predict the severity of COVID-19. After parameter tuning and performance comparison, the optimal model was explained using Shapley Additive explanations to output the crucial factors. This study enrolled and classified 198 patients into mild (n = 162; 46.93 ± 14.49 years old) and severe (n = 36; 60.97 ± 15.91 years old) groups. The severe group had a higher temperature (37.42 ± 0.99°C vs. 36.75 ± 0.66°C), CT score at admission, neutrophil count, and neutrophil-to-lymphocyte ratio than the mild group. The XGBoost model ranked first among all models, with an AUC, sensitivity, and specificity of 0.924, 90.91%, and 97.96%, respectively. The early stage of chest CT, total CT score of the percentage of lung involvement, and age were the top three contributors to the prediction of the deterioration of XGBoost. A higher total score on chest CT had a more significant impact on the prediction. In conclusion, the XGBoost model to predict the severity of COVID-19 achieved excellent performance and output the essential factors in the deterioration process, which may help with early clinical intervention, improve prognosis, and reduce mortality.


Subject(s)
COVID-19/diagnostic imaging , COVID-19/etiology , Diagnosis, Computer-Assisted/methods , Adult , Aged , Blood Cell Count , COVID-19/blood , Dyspnea/virology , Female , Fever/virology , Humans , Machine Learning , Male , Models, Biological , Neutrophils , Severity of Illness Index , Tomography, X-Ray Computed
17.
Stroke ; 52(5): 1682-1690, 2021 05.
Article in English | MEDLINE | ID: covidwho-1117688

ABSTRACT

BACKGROUND AND PURPOSE: The degree to which the coronavirus disease 2019 (COVID-19) pandemic has affected systems of care, in particular, those for time-sensitive conditions such as stroke, remains poorly quantified. We sought to evaluate the impact of COVID-19 in the overall screening for acute stroke utilizing a commercial clinical artificial intelligence platform. METHODS: Data were derived from the Viz Platform, an artificial intelligence application designed to optimize the workflow of patients with acute stroke. Neuroimaging data on suspected patients with stroke across 97 hospitals in 20 US states were collected in real time and retrospectively analyzed with the number of patients undergoing imaging screening serving as a surrogate for the amount of stroke care. The main outcome measures were the number of computed tomography (CT) angiography, CT perfusion, large vessel occlusions (defined according to the automated software detection), and severe strokes on CT perfusion (defined as those with hypoperfusion volumes >70 mL) normalized as number of patients per day per hospital. Data from the prepandemic (November 4, 2019 to February 29, 2020) and pandemic (March 1 to May 10, 2020) periods were compared at national and state levels. Correlations were made between the inter-period changes in imaging screening, stroke hospitalizations, and thrombectomy procedures using state-specific sampling. RESULTS: A total of 23 223 patients were included. The incidence of large vessel occlusion on CT angiography and severe strokes on CT perfusion were 11.2% (n=2602) and 14.7% (n=1229/8328), respectively. There were significant declines in the overall number of CT angiographies (-22.8%; 1.39-1.07 patients/day per hospital, P<0.001) and CT perfusion (-26.1%; 0.50-0.37 patients/day per hospital, P<0.001) as well as in the incidence of large vessel occlusion (-17.1%; 0.15-0.13 patients/day per hospital, P<0.001) and severe strokes on CT perfusion (-16.7%; 0.12-0.10 patients/day per hospital, P<0.005). The sampled cohort showed similar declines in the rates of large vessel occlusions versus thrombectomy (18.8% versus 19.5%, P=0.9) and comprehensive stroke center hospitalizations (18.8% versus 11.0%, P=0.4). CONCLUSIONS: A significant decline in stroke imaging screening has occurred during the COVID-19 pandemic. This analysis underscores the broader application of artificial intelligence neuroimaging platforms for the real-time monitoring of stroke systems of care.


Subject(s)
Artificial Intelligence , COVID-19/epidemiology , Diagnosis, Computer-Assisted/methods , Stroke/epidemiology , Aged , Aged, 80 and over , COVID-19/complications , Computed Tomography Angiography , Female , Hospitalization , Humans , Male , Middle Aged , Perfusion , Retrospective Studies , Stroke/complications , Tomography, X-Ray Computed , Workflow
18.
PLoS One ; 15(11): e0242013, 2020.
Article in English | MEDLINE | ID: covidwho-949090

ABSTRACT

BACKGROUND: Pneumothorax can lead to a life-threatening emergency. The experienced radiologists can offer precise diagnosis according to the chest radiographs. The localization of the pneumothorax lesions will help to quickly diagnose, which will be benefit for the patients in the underdevelopment areas lack of the experienced radiologists. In recent years, with the development of large neural network architectures and medical imaging datasets, deep learning methods have become a methodology of choice for analyzing medical images. The objective of this study was to the construct convolutional neural networks to localize the pneumothorax lesions in chest radiographs. METHODS AND FINDINGS: We developed a convolutional neural network, called CheXLocNet, for the segmentation of pneumothorax lesions. The SIIM-ACR Pneumothorax Segmentation dataset was used to train and validate CheXLocNets. The training dataset contained 2079 radiographs with the annotated lesion areas. We trained six CheXLocNets with various hyperparameters. Another 300 annotated radiographs were used to select parameters of these CheXLocNets as the validation set. We determined the optimal parameters by the AP50 (average precision at the intersection over union (IoU) equal to 0.50), a segmentation evaluation metric used by several well-known competitions. Then CheXLocNets were evaluated by a test set (1082 normal radiographs and 290 disease radiographs), based on the classification metrics: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV); segmentation metrics: IoU and Dice score. For the classification, CheXLocNet with best sensitivity produced an AUC of 0.87, sensitivity of 0.78 (95% CI 0.73-0.83), and specificity of 0.78 (95% CI 0.76-0.81). CheXLocNet with best specificity produced an AUC of 0.79, sensitivity of 0.46 (95% CI 0.40-0.52), and specificity of 0.92 (95% CI 0.90-0.94). For the segmentation, CheXLocNet with best sensitivity produced an IoU of 0.69 and Dice score of 0.72. CheXLocNet with best specificity produced an IoU of 0.77 and Dice score of 0.79. We combined them to form an ensemble CheXLocNet. The ensemble CheXLocNet produced an IoU of 0.81 and Dice score of 0.82. Our CheXLocNet succeeded in automatically detecting pneumothorax lesions, without any human guidance. CONCLUSIONS: In this study, we proposed a deep learning network, called, CheXLocNet, for the automatic segmentation of chest radiographs to detect pneumothorax. Our CheXLocNets generated accurate classification results and high-quality segmentation masks for the pneumothorax at the same time. This technology has the potential to improve healthcare delivery and increase access to chest radiograph expertise for the detection of diseases. Furthermore, the segmentation results can offer comprehensive geometric information of lesions, which can benefit monitoring the sequential development of lesions with high accuracy. Thus, CheXLocNets can be further extended to be a reliable clinical decision support tool. Although we used transfer learning in training CheXLocNet, the parameters of CheXLocNet was still large for the radiograph dataset. Further work is necessary to prune CheXLocNet suitable for the radiograph dataset.


Subject(s)
Neural Networks, Computer , Pneumothorax/diagnostic imaging , Deep Learning , Diagnosis, Computer-Assisted/methods , Humans , Image Processing, Computer-Assisted/methods , Radiography/methods
19.
Med Image Anal ; 68: 101913, 2021 02.
Article in English | MEDLINE | ID: covidwho-943427

ABSTRACT

The efficient diagnosis of COVID-19 plays a key role in preventing the spread of this disease. The computer-aided diagnosis with deep learning methods can perform automatic detection of COVID-19 using CT scans. However, large scale annotation of CT scans is impossible because of limited time and heavy burden on the healthcare system. To meet the challenge, we propose a weakly-supervised deep active learning framework called COVID-AL to diagnose COVID-19 with CT scans and patient-level labels. The COVID-AL consists of the lung region segmentation with a 2D U-Net and the diagnosis of COVID-19 with a novel hybrid active learning strategy, which simultaneously considers sample diversity and predicted loss. With a tailor-designed 3D residual network, the proposed COVID-AL can diagnose COVID-19 efficiently and it is validated on a large CT scan dataset collected from the CC-CCII. The experimental results demonstrate that the proposed COVID-AL outperforms the state-of-the-art active learning approaches in the diagnosis of COVID-19. With only 30% of the labeled data, the COVID-AL achieves over 95% accuracy of the deep learning method using the whole dataset. The qualitative and quantitative analysis proves the effectiveness and efficiency of the proposed COVID-AL framework.


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , Diagnosis, Computer-Assisted/methods , Pneumonia, Viral/diagnostic imaging , Tomography, X-Ray Computed , Datasets as Topic , Humans , Pneumonia, Viral/virology , SARS-CoV-2
20.
Med Image Anal ; 68: 101910, 2021 02.
Article in English | MEDLINE | ID: covidwho-943426

ABSTRACT

The coronavirus disease, named COVID-19, has become the largest global public health crisis since it started in early 2020. CT imaging has been used as a complementary tool to assist early screening, especially for the rapid identification of COVID-19 cases from community acquired pneumonia (CAP) cases. The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features. To tackle this challenge, we propose an Uncertainty Vertex-weighted Hypergraph Learning (UVHL) method to identify COVID-19 from CAP using CT images. In particular, multiple types of features (including regional features and radiomics features) are first extracted from CT image for each case. Then, the relationship among different cases is formulated by a hypergraph structure, with each case represented as a vertex in the hypergraph. The uncertainty of each vertex is further computed with an uncertainty score measurement and used as a weight in the hypergraph. Finally, a learning process of the vertex-weighted hypergraph is used to predict whether a new testing case belongs to COVID-19 or not. Experiments on a large multi-center pneumonia dataset, consisting of 2148 COVID-19 cases and 1182 CAP cases from five hospitals, are conducted to evaluate the prediction accuracy of the proposed method. Results demonstrate the effectiveness and robustness of our proposed method on the identification of COVID-19 in comparison to state-of-the-art methods.


Subject(s)
COVID-19/diagnostic imaging , Community-Acquired Infections/diagnostic imaging , Diagnosis, Computer-Assisted/methods , Machine Learning , Pneumonia, Viral/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Tomography, X-Ray Computed , China , Community-Acquired Infections/virology , Datasets as Topic , Diagnosis, Differential , Humans , Pneumonia, Viral/virology , SARS-CoV-2
SELECTION OF CITATIONS
SEARCH DETAIL