scholarly journals Diagnostic classification of coronavirus disease 2019 (COVID-19) and other pneumonias using radiomics features in CT chest images

2020 ◽  
Author(s):  
Ning Yang ◽  
Faming Liu ◽  
Chunlong Li ◽  
Wenqing Xiao ◽  
Shuangcong Xie ◽  
...  
Keyword(s):  
Correlation Analysis ◽  
Area Under The Curve ◽  
Region Of Interest ◽  
Texture Features ◽  
Support Vector ◽  
C Reactive Protein ◽  
Reactive Protein ◽  
Svm Model ◽  
Multiple Comparison Correction

Abstract We propose a classification method using the radiomics features of CT chest images to identify patients with coronavirus disease 2019 (COVID-19) and other pneumonias. The chest CT images of two groups of participants (90 COVID-19 patients and 90 other pneumonias patients) were collected, and the two groups of data were manually drawn to outline the region of interest (ROI) of pneumonias. The radiomics method was used to extract textural features and histogram features of the ROI and obtain a radiomics features vector from each sample. Finally, using the radiomics features as an input, a support vector machine (SVM) model was constructed to classify patients with COVID-19 and patients with other pneumonias. This model used 20 rounds of 10-fold cross-validation for training and testing. In the COVID-19 patients, correlation analysis (multiple comparison correction—Bonferroni correction, p<0.05/7) was also conducted to determine whether the textural and histogram features were correlated with the laboratory test index of blood, i.e., blood oxygen, white blood cell, lymphocytes, neutrophils, C-reactive protein, hypersensitive C-reactive protein, and erythrocyte sedimentation rate. The results showed that the proposed method had a classification accuracy as high as 88.33%, sensitivity of 83.56%, specificity of 93.11%, and an area under the curve of 0.947. This proved that the radiomics features were highly distinguishable, and this SVM model can effectively identify and diagnose patients with COVID-19 and other pneumonias. The correlation analysis results showed that some texture features were positively correlated with WBC, NE, and CRP and also negatively related to SPO2H and NE.

scholarly journals Diagnostic classification of coronavirus disease 2019 (COVID-19) and other pneumonias using radiomics features in CT chest images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ning Yang ◽  
Faming Liu ◽  
Chunlong Li ◽  
Wenqing Xiao ◽  
Shuangcong Xie ◽  
...  
Keyword(s):  
Correlation Analysis ◽  
Validation Cohort ◽  
Support Vector ◽  
Textural Features ◽  
Single Shot ◽  
C Reactive Protein ◽  
Final Model ◽  
Reactive Protein ◽  
Independent Validation ◽  
Svm Model

AbstractWe propose a classification method using the radiomics features of CT chest images to identify patients with coronavirus disease 2019 (COVID-19) and other pneumonias. The chest CT images of two groups of participants (90 COVID-19 patients who were confirmed as positive by nucleic acid test of RT-PCR and 90 other pneumonias patients) were collected, and the two groups of data were manually drawn to outline the region of interest (ROI) of pneumonias. The radiomics method was used to extract textural features and histogram features of the ROI and obtain a radiomics features vector from each sample. Then, we divided the data into two independent radiomic cohorts for training (70 COVID-19 patients and 70 other pneumonias patients), and validation (20 COVID-19 patients and 20 other pneumonias patients) by using support vector machine (SVM). This model used 20 rounds of tenfold cross-validation for training. Finally, single-shot testing of the final model was performed on the independent validation cohort. In the COVID-19 patients, correlation analysis (multiple comparison correction—Bonferroni correction, P < 0.05/7) was also conducted to determine whether the textural and histogram features were correlated with the laboratory test index of blood, i.e., blood oxygen, white blood cell, lymphocytes, neutrophils, C-reactive protein, hypersensitive C-reactive protein, and erythrocyte sedimentation rate. The final model showed good discrimination on the independent validation cohort, with an accuracy of 89.83%, sensitivity of 94.22%, specificity of 85.44%, and AUC of 0.940. This proved that the radiomics features were highly distinguishable, and this SVM model can effectively identify and diagnose patients with COVID-19 and other pneumonias. The correlation analysis results showed that some textural features were positively correlated with WBC, and NE, and also negatively related to SPO2H and NE. Our results showed that radiomic features can classify COVID-19 patients and other pneumonias patients. The SVM model can achieve an excellent diagnosis of COVID-19.

scholarly journals Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models

2021 ◽  
Vol 27 (4) ◽  
pp. 298-306
Author(s):  
Audrey K. C. Huong ◽  
Kim Gaik Tay ◽  
Xavier T. I. Ngu
Keyword(s):  
Image Classification ◽  
Pap Smear ◽  
False Negative ◽  
Area Under The Curve ◽  
Superior Performance ◽  
Support Vector ◽  
Training Time ◽  
Binary Coding ◽  
Svm Model

Objectives: Different complex strategies of fusing handcrafted descriptors and features from convolutional neural network (CNN) models have been studied, mainly for two-class Papanicolaou (Pap) smear image classification. This paper explores a simplified system using combined binary coding for a five-class version of this problem.Methods: This system extracted features from transfer learning of AlexNet, VGG19, and ResNet50 networks before reducing this problem into multiple binary sub-problems using error-correcting coding. The learners were trained using the support vector machine (SVM) method. The outputs of these classifiers were combined and compared to the true class codes for the final prediction.Results: Despite the superior performance of VGG19-SVM, with mean ± standard deviation accuracy and sensitivity of 80.68% ± 2.00% and 80.86% ± 0.45%, respectively, this model required a long training time. There were also false-negative cases using both the VGGNet-SVM and ResNet-SVM models. AlexNet-SVM was more efficient in terms of running speed and prediction consistency. Our findings also showed good diagnostic ability, with an area under the curve of approximately 0.95. Further investigation also showed good agreement between our research outcomes and that of the state-of-the-art methods, with specificity ranging from 93% to 100%.Conclusions: We believe that the AlexNet-SVM model can be conveniently applied for clinical use. Further research could include the implementation of an optimization algorithm for hyperparameter tuning, as well as an appropriate selection of experimental design to improve the efficiency of Pap smear image classification.

scholarly journals Diagnostic Value of C-Reactive Protein in Discrimination between Uncomplicated and Complicated Parapneumonic Effusion

Diagnostics ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 829
Author(s):  
Yana Kogan ◽  
Edmond Sabo ◽  
Majed Odeh
Keyword(s):  
Area Under The Curve ◽  
Diagnostic Value ◽  
Parapneumonic Effusion ◽  
C Reactive Protein ◽  
Diagnostic Efficacy ◽  
Reactive Protein ◽  
Significant Difference ◽  
Study Population ◽  
Complicated Parapneumonic Effusion

Objectives: The role of serum C-reactive protein (CRPs) and pleural fluid CRP (CRPpf) in discriminating uncomplicated parapneumonic effusion (UCPPE) from complicated parapneumonic effusion (CPPE) is yet to be validated since most of the previous studies were on small cohorts and with variable results. The role of CRPs and CRPpf gradient (CRPg) and of their ratio (CRPr) in this discrimination has not been previously reported. The study aims to assess the diagnostic efficacy of CRPs, CRPpf, CRPr, and CRPg in discriminating UCPPE from CPPE in a relatively large cohort. Methods: The study population included 146 patients with PPE, 86 with UCPPE and 60 with CPPE. Levels of CRPs and CRPpf were measured, and the CRPg and CRPr were calculated. The values are presented as mean ± SD. Results: Mean levels of CRPs, CRPpf, CRPg, and CRPr of the UCPPE group were 145.3 ± 67.6 mg/L, 58.5 ± 38.5 mg/L, 86.8 ± 37.3 mg/L, and 0.39 ± 0.11, respectively, and for the CPPE group were 302.2 ± 75.6 mg/L, 112 ± 65 mg/L, 188.3 ± 62.3 mg/L, and 0.36 ± 0.19, respectively. Levels of CRPs, CRPpf, and CRPg were significantly higher in the CPPE than in the UCPPE group (p < 0.0001). No significant difference was found between the two groups for levels of CRPr (p = 0.26). The best cut-off value calculated by the receiver operating characteristic (ROC) analysis for discriminating UCPPE from CPPE was for CRPs, 211.5 mg/L with area under the curve (AUC) = 94% and p < 0.0001, for CRPpf, 90.5 mg/L with AUC = 76.3% and p < 0.0001, and for CRPg, 142 mg/L with AUC = 91% and p < 0.0001. Conclusions: CRPs, CRPpf, and CRPg are strong markers for discrimination between UCPPE and CPPE, while CRPr has no role in this discrimination.

scholarly journals A Comparative Study on Application of Computer Vision and Fluorescence Imaging Spectroscopy for Detection of Huanglongbing Citrus Disease in the USA and Brazil

2013 ◽  
Vol 2013 ◽  
pp. 1-6 ◽  
Author(s):  
Caio B. Wetterich ◽  
Ratnesh Kumar ◽  
Sindhuja Sankaran ◽  
José Belasque Junior ◽  
Reza Ehsani ◽  
...  
Keyword(s):  
Computer Vision ◽  
Fluorescence Imaging ◽  
Imaging Spectroscopy ◽  
Texture Features ◽  
Support Vector ◽  
Infected Leaf ◽  
Segmented Images ◽  
The Usa ◽  
Citrus Disease

The overall objective of this work was to develop and evaluate computer vision and machine learning technique for classification of Huanglongbing-(HLB)-infected and healthy leaves using fluorescence imaging spectroscopy. The fluorescence images were segmented using normalized graph cut, and texture features were extracted from the segmented images using cooccurrence matrix. The extracted features were used as an input into the classifier, support vector machine (SVM). The classification results were evaluated based on classification accuracies and number of false positives and false negatives. The results indicated that the SVM could classify HLB-infected leaf fluorescence intensities with up to 90% classification accuracy. Though the fluorescence intensities from leaves collected in Brazil and the USA were different, the method shows potential for detecting HLB.

Identification and Classification of Fungal Colonies in Moldy Paddy Based on Computer Vision

2018 ◽  
Vol 61 (5) ◽  
pp. 1497-1504
Author(s):  
Zhenjie Wang ◽  
Ke Sun ◽  
Lihui Du ◽  
Jian Yuan ◽  
Kang Tu ◽  
...  
Keyword(s):  
Computer Vision ◽  
Discriminant Analysis ◽  
Texture Features ◽  
Fungal Species ◽  
Projection Algorithm ◽  
Support Vector ◽  
Linear Discriminant ◽  
Sequential Selection ◽  
The Individual

Abstract. In this study, computer vision was used for the identification and classification of fungi on moldy paddy. To develop a rapid and efficient method for the classification of common fungal species found in stored paddy, computer vision was used to acquire images of individual colonies of growing fungi for three consecutive days. After image processing, the color, shape, and texture features were acquired and used in a subsequent discriminant analysis. Both linear (i.e., linear discriminant analysis and partial least squares discriminant analysis) and nonlinear (i.e., random forest and support vector machine [SVM]) pattern recognition models were employed for the classification of fungal colonies, and the results were compared. The results indicate that when using all of the features for three consecutive days, the performance of the nonlinear tools was superior to that of the linear tools, especially in the case of the SVM models, which achieved an accuracy of 100% on the calibration sets and an accuracy of 93.2% to 97.6% on the prediction sets. After sequential selection of projection algorithm, ten common features were selected for building the classification models. The results showed that the SVM model achieved an overall accuracy of 95.6%, 98.3%, and 99.0% on the prediction sets on days 2, 3, and 4, respectively. This work demonstrated that computer vision with several features is suitable for the identification and classification of fungi on moldy paddy based on the form of the individual colonies at an early growth stage during paddy storage. Keywords: Classification, Computer vision, Fungal colony, Feature selection, SVM.

C-reactive Protein Is a More Sensitive and Specific Marker for Diagnosing Bacterial Infections in Systemic Lupus Erythematosus Compared to S100A8/A9 and Procalcitonin

2012 ◽  
Vol 39 (4) ◽  
pp. 728-734 ◽  
Author(s):  
HYOUN-AH KIM ◽  
JA-YOUNG JEON ◽  
JEONG-MI AN ◽  
BO-RAM KOH ◽  
CHANG-HEE SUH
Keyword(s):  
Systemic Lupus Erythematosus ◽  
Lupus Erythematosus ◽  
Bacterial Infections ◽  
Area Under The Curve ◽  
Specific Marker ◽  
Operating Characteristics ◽  
C Reactive Protein ◽  
Systemic Lupus ◽  
Serum Samples ◽  
Reactive Protein

Objective.C-reactive protein (CRP), S100A8/A9, and procalcitonin have been suggested as markers of infection in patients with systemic lupus erythematosus (SLE). We investigated the clinical significance of these factors for indication of infection in SLE.Methods.Blood samples were prospectively collected from 34 patients with SLE who had bacterial infections and 39 patients with SLE who had disease flares and no evidence of infection. A second set of serum samples was collected after the infections or flares were resolved.Results.CRP levels of SLE patients with infections were higher than those with flares [5.9 mg/dl (IQR 2.42, 10.53) vs 0.06 mg/dl (IQR 0.03, 0.15), p < 0.001] and decreased after the infection was resolved. S100A8/A9 and procalcitonin levels of SLE patients with infection were also higher [4.69 μg/ml (IQR 2.25, 12.07) vs 1.07 (IQR 0.49, 3.05) (p < 0.001) and 0 ng/ml (IQR 0–0.38) vs 0 (0–0) (p < 0.001), respectively]; these levels were also reduced once the infection disappeared. In the receiver-operating characteristics analysis of CRP, S100A8/A9, and procalcitonin, the area under the curve was 0.966 (95% CI 0.925–1.007), 0.732 (95% CI 0.61–0.854), and 0.667 (95% CI 0.534–0.799), respectively. CRP indicated the presence of an infection with a sensitivity of 100% and a specificity of 90%, with a cutoff value of 1.35 mg/dl.Conclusion.Our data suggest that CRP is the most sensitive and specific marker for diagnosing bacterial infections in SLE.

Pattern recognition of enrichment levels of SELEX-based candidate aptamers for human C-reactive protein

2017 ◽  
Vol 62 (3) ◽  
Author(s):  
Xinliang Yu ◽  
Ruqin Yu ◽  
Xiaohai Yang
Keyword(s):  
Pattern Recognition ◽  
Latent Variables ◽  
Molecular Descriptors ◽  
Principal Component ◽  
Support Vector ◽  
C Reactive Protein ◽  
Reactive Protein ◽  
Systematic Evolution ◽  
Model C ◽  
Exponential Enrichment

AbstractSelecting aptamers for human C-reactive protein (CRP) would be of critical importance in predicting the risk for cardiovascular disease. The enrichment level of DNA aptamers is an important parameter for selecting candidate aptamers for further affinity and specificity determination. This paper is the first report on pattern recognition used for CRP aptamer enrichment levels in the systematic evolution of ligands by exponential enrichment (SELEX) process, by applying structure-activity relationship models. After generating 10 rounds of graphene oxide (GO)-SELEX and 1670 molecular descriptors, eight molecular descriptors were selected and five latent variables were then obtained with principal component analysis (PCA), to develop a support vector classification (SVC) model. The SVC model (C=8.1728 and

Automatic Fruit Disease Classification Using Images

2014 ◽  
pp. 82-100 ◽  
Author(s):  
Shiv Ram Dubey ◽  
Anand Singh Jalal
Keyword(s):  
Support Vector Machine ◽  
Apple Scab ◽  
Texture Features ◽  
Disease Classification ◽  
Economic Losses ◽  
Support Vector ◽  
Test Case ◽  
Agricultural Industry ◽  
Fruit Disease

Diseases in fruit cause devastating problems in economic losses and production in the agricultural industry worldwide. In this chapter, a method to detect and classify fruit diseases automatically is proposed and experimentally validated. The image processing-based proposed approach is composed of the following main steps: in the first step K-Means clustering technique is used for the defect segmentation, in the second step some color and texture features are extracted from the segmented defected part, and finally diseases are classified into one of the classes by using a multi-class Support Vector Machine. The authors have considered diseases of apple as a test case and evaluated the approach for three types of apple diseases, namely apple scab, apple blotch, and apple rot, along with normal apples. The experimental results express that the proposed solution can significantly support accurate detection and automatic classification of fruit diseases. The classification accuracy for the proposed approach is achieved up to 93% using textural information and multi-class support vector machine.

Automatic Detection and Classification of Ischemic Stroke Using K-Means Clustering and Texture Features

2016 ◽  
pp. 441-461
Author(s):  
N. Hema Rajini ◽  
R. Bhavani
Keyword(s):  
Ischemic Stroke ◽  
Life Support ◽  
Texture Features ◽  
Support Vector ◽  
Clustering Technique ◽  
Computed Tomography Images ◽  
Brain Extraction ◽  
Third Stage ◽  
The Brain

Computed tomography images are widely used in the diagnosis of ischemic stroke because of its faster acquisition and compatibility with most life support devices. This chapter presents a new approach to automated detection of ischemic stroke using k-means clustering technique which separates the lesion region from healthy tissues and classification of ischemic stroke using texture features. The proposed method has five stages, pre-processing, tracing midline of the brain, extraction of texture features and feature selection, classification and segmentation. In the first stage noise is suppressed using a median filtering and skull bone components of the images are removed. In the second stage, midline shift of the brain is calculated. In the third stage, fourteen texture features are extracted and optimal features are selected using genetic algorithm. In the fourth stage, support vector machine, artificial neural network and decision tree classifiers have been used. Finally, the ischemic stroke region is extracted by using k-means clustering technique.

Sign in / Sign up

Export Citation Format

Share Document