scholarly journals Integration of Deep and Ensemble Learning for Detecting COVID-19 in Computed Tomography Images

2020 ◽  
Author(s):  
Ali Haidar ◽  
Lois Holloway
Keyword(s):  
Computed Tomography ◽  
Decision Trees ◽  
Ct Images ◽  
Gradient Boosting ◽  
Deep Convolutional Neural Networks ◽  
Adaptive Boosting ◽  
Computed Tomography Images ◽  
Extreme Gradient Boosting ◽  
Bagged Decision Trees ◽  
Additive Regression

Abstract This paper presents an approach for detecting covid-19 in Computed Tomography (CT) images by integrating deep convolutional neural networks and ensembles of decision trees. The proposed approach consisted of three steps. In the first step, the CT images slices were collected and processed. In the second step, a deep convolutional neural network was trained to predict covid-19 in the CT images. In the third step, deep features were extracted and were used to train an ensemble of decision trees. Six types/packages of ensembles of decision trees were investigated: extreme gradient boosting (XGBoost), bagged decision trees (BDT), random forest (RF), adaptive boosting decision trees (Adaboost), gradient boosting decision trees (GBDT), and dropouts meet multiple additive regression trees (DART). The accuracy, sensitivity, specificity, f1-score, precision, and area under the ROC curve (AUC) were calculated to compare the models against each other. The proposed approach revealed the highest performance with a RF that reported 0.87 accuracy, 0.87 f1-score, and 0.90 AUC. The developed models revealed similar performance when compared to previously published models. This highlights the efficiency of combining deep networks with ensembles of decision trees for detecting covid-19.

scholarly journals Integration of Deep and Ensemble Learning for Detecting COVID-19 in Computed Tomography Images

2020 ◽  
Author(s):  
Ali Haidar ◽  
Lois Holloway
Keyword(s):  
Computed Tomography ◽  
Decision Trees ◽  
Ct Images ◽  
Gradient Boosting ◽  
Deep Convolutional Neural Networks ◽  
Adaptive Boosting ◽  
Computed Tomography Images ◽  
Extreme Gradient Boosting ◽  
Bagged Decision Trees ◽  
Additive Regression

Abstract This paper presents an approach for detecting covid-19 in Computed Tomography (CT) images by integrating deep convolutional neural networks and ensembles of decision trees. The proposed approach consisted of three steps. In the first step, the CT images slices were collected and processed. In the second step, a deep convolutional neural network was trained to predict covid-19 in the CT images. In the third step, deep features were extracted and were used to train an ensemble of decision trees. Six types/packages of ensembles of decision trees were investigated: extreme gradient boosting (XGBoost), bagged decision trees (BDT), random forest (RF), adaptive boosting decision trees (Adaboost), gradient boosting decision trees (GBDT), and dropouts meet multiple additive regression trees (DART). The accuracy, sensitivity, specificity, f1-score, precision, and area under the ROC curve (AUC) were calculated to compare the models against each other. The proposed approach revealed the highest performance with a RF that reported 0.87 accuracy, 0.87 f1-score, and 0.90 AUC. The developed models revealed similar performance when compared to previously published models. This highlights the efficiency of combining deep networks with ensembles of decision trees for detecting covid-19.

scholarly journals Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images

2021 ◽  
Vol 17 (4) ◽  
pp. 1-16
Author(s):  
Xiaowe Xu ◽  
Jiawei Zhang ◽  
Jinglan Liu ◽  
Yukun Ding ◽  
Tianchen Wang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Denoising ◽  
Ct Images ◽  
High Dose ◽  
Ct Image ◽  
Paired Data ◽  
High Quality ◽  
Computed Tomography Images ◽  
Significant Difference ◽  
Global Cycle

As one of the most commonly ordered imaging tests, the computed tomography (CT) scan comes with inevitable radiation exposure that increases cancer risk to patients. However, CT image quality is directly related to radiation dose, and thus it is desirable to obtain high-quality CT images with as little dose as possible. CT image denoising tries to obtain high-dose-like high-quality CT images (domain Y ) from low dose low-quality CT images (domain X ), which can be treated as an image-to-image translation task where the goal is to learn the transform between a source domain X (noisy images) and a target domain Y (clean images). Recently, the cycle-consistent adversarial denoising network (CCADN) has achieved state-of-the-art results by enforcing cycle-consistent loss without the need of paired training data, since the paired data is hard to collect due to patients’ interests and cardiac motion. However, out of concerns on patients’ privacy and data security, protocols typically require clinics to perform medical image processing tasks including CT image denoising locally (i.e., edge denoising). Therefore, the network models need to achieve high performance under various computation resource constraints including memory and performance. Our detailed analysis of CCADN raises a number of interesting questions that point to potential ways to further improve its performance using the same or even fewer computation resources. For example, if the noise is large leading to a significant difference between domain X and domain Y , can we bridge X and Y with a intermediate domain Z such that both the denoising process between X and Z and that between Z and Y are easier to learn? As such intermediate domains lead to multiple cycles, how do we best enforce cycle- consistency? Driven by these questions, we propose a multi-cycle-consistent adversarial network (MCCAN) that builds intermediate domains and enforces both local and global cycle-consistency for edge denoising of CT images. The global cycle-consistency couples all generators together to model the whole denoising process, whereas the local cycle-consistency imposes effective supervision on the process between adjacent domains. Experiments show that both local and global cycle-consistency are important for the success of MCCAN, which outperforms CCADN in terms of denoising quality with slightly less computation resource consumption.

scholarly journals Machine Learning Models for Sarcopenia Identification Based on Radiomic Features of Muscles in Computed Tomography

2021 ◽  
Vol 18 (16) ◽  
pp. 8710
Author(s):  
Young Jae Kim
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Ct Images ◽  
Erector Spinae ◽  
Support Vector ◽  
Gray Level ◽  
Learning Models ◽  
Extreme Gradient Boosting ◽  
Nsclc Patients ◽  
Machine Learning Models

The diagnosis of sarcopenia requires accurate muscle quantification. As an alternative to manual muscle mass measurement through computed tomography (CT), artificial intelligence can be leveraged for the automation of these measurements. Although generally difficult to identify with the naked eye, the radiomic features in CT images are informative. In this study, the radiomic features were extracted from L3 CT images of the entire muscle area and partial areas of the erector spinae collected from non-small cell lung carcinoma (NSCLC) patients. The first-order statistics and gray-level co-occurrence, gray-level size zone, gray-level run length, neighboring gray-tone difference, and gray-level dependence matrices were the radiomic features analyzed. The identification performances of the following machine learning models were evaluated: logistic regression, support vector machine (SVM), random forest, and extreme gradient boosting (XGB). Sex, coarseness, skewness, and cluster prominence were selected as the relevant features effectively identifying sarcopenia. The XGB model demonstrated the best performance for the entire muscle, whereas the SVM was the worst-performing model. Overall, the models demonstrated improved performance for the entire muscle compared to the erector spinae. Although further validation is required, the radiomic features presented here could become reliable indicators for quantifying the phenomena observed in the muscles of NSCLC patients, thus facilitating the diagnosis of sarcopenia.

scholarly journals Modeling hydrogen solubility in hydrocarbons using extreme gradient boosting and equations of state

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mohammad-Reza Mohammadi ◽  
Fahime Hadavimoghaddam ◽  
Maryam Pourmahdi ◽  
Saeid Atashrouz ◽  
Muhammad Tajammal Munir ◽  
...  
Keyword(s):  
Molecular Weight ◽  
Equations Of State ◽  
Optimal Operation ◽  
Operating Conditions ◽  
Hydrogen Solubility ◽  
Gradient Boosting ◽  
Accurate Estimation ◽  
Support Vector ◽  
Adaptive Boosting ◽  
Extreme Gradient Boosting

AbstractDue to industrial development, designing and optimal operation of processes in chemical and petroleum processing plants require accurate estimation of the hydrogen solubility in various hydrocarbons. Equations of state (EOSs) are limited in accurately predicting hydrogen solubility, especially at high-pressure or/and high-temperature conditions, which may lead to energy waste and a potential safety hazard in plants. In this paper, five robust machine learning models including extreme gradient boosting (XGBoost), adaptive boosting support vector regression (AdaBoost-SVR), gradient boosting with categorical features support (CatBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP) optimized by Levenberg–Marquardt (LM) algorithm were implemented for estimating the hydrogen solubility in hydrocarbons. To this end, a databank including 919 experimental data points of hydrogen solubility in 26 various hydrocarbons was gathered from 48 different systems in a broad range of operating temperatures (213–623 K) and pressures (0.1–25.5 MPa). The hydrocarbons are from six different families including alkane, alkene, cycloalkane, aromatic, polycyclic aromatic, and terpene. The carbon number of hydrocarbons is ranging from 4 to 46 corresponding to a molecular weight range of 58.12–647.2 g/mol. Molecular weight, critical pressure, and critical temperature of solvents along with pressure and temperature operating conditions were selected as input parameters to the models. The XGBoost model best fits all the experimental solubility data with a root mean square error (RMSE) of 0.0007 and an average absolute percent relative error (AAPRE) of 1.81%. Also, the proposed models for estimating the solubility of hydrogen in hydrocarbons were compared with five EOSs including Soave–Redlich–Kwong (SRK), Peng–Robinson (PR), Redlich–Kwong (RK), Zudkevitch–Joffe (ZJ), and perturbed-chain statistical associating fluid theory (PC-SAFT). The XGBoost model introduced in this study is a promising model that can be applied as an efficient estimator for hydrogen solubility in various hydrocarbons and is capable of being utilized in the chemical and petroleum industries.

scholarly journals A Study on Machine Vision Techniques for the Inspection of Health Personnels’ Protective Suits for the Treatment of Patients in Extreme Isolation

Electronics ◽  
2019 ◽  
Vol 8 (7) ◽  
pp. 743 ◽  
Author(s):  
Alice Stazio ◽  
Juan G. Victores ◽  
David Estevez ◽  
Carlos Balaguer
Keyword(s):  
Logistic Regression ◽  
Machine Vision ◽  
Training Data ◽  
Gradient Boosting ◽  
Support Vector ◽  
Classification Algorithms ◽  
Adaptive Boosting ◽  
Blood Stains ◽  
Extreme Gradient Boosting ◽  
Vector Machines

The examination of Personal Protective Equipment (PPE) to assure the complete integrity of health personnel in contact with infected patients is one of the most necessary tasks when treating patients affected by infectious diseases, such as Ebola. This work focuses on the study of machine vision techniques for the detection of possible defects on the PPE that could arise after contact with the aforementioned pathological patients. A preliminary study on the use of image classification algorithms to identify blood stains on PPE subsequent to the treatment of the infected patient is presented. To produce training data for these algorithms, a synthetic dataset was generated from a simulated model of a PPE suit with blood stains. Furthermore, the study proceeded with the utilization of images of the PPE with a physical emulation of blood stains, taken by a real prototype. The dataset reveals a great imbalance between positive and negative samples; therefore, all the selected classification algorithms are able to manage this kind of data. Classifiers range from Logistic Regression and Support Vector Machines, to bagging and boosting techniques such as Random Forest, Adaptive Boosting, Gradient Boosting and eXtreme Gradient Boosting. All these algorithms were evaluated on accuracy, precision, recall and F 1 score; and additionally, execution times were considered. The obtained results report promising outcomes of all the classifiers, and, in particular Logistic Regression resulted to be the most suitable classification algorithm in terms of F 1 score and execution time, considering both datasets.

scholarly journals Application of machine learning algorithms for flood susceptibility assessment and risk management

2021 ◽  
Author(s):  
R. Madhuri ◽  
S. Sistla ◽  
K. Srinivasa Raju
Keyword(s):  
Climate Change ◽  
Machine Learning ◽  
Influencing Factors ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Climate Change Scenarios ◽  
Adaptive Boosting ◽  
Extreme Gradient Boosting ◽  
Normalised Difference Vegetation Index

Abstract Assessing floods and their likely impact in climate change scenarios will enable the facilitation of sustainable management strategies. In this study, five machine learning (ML) algorithms, namely (i) Logistic Regression, (ii) Support Vector Machine, (iii) K-nearest neighbor, (iv) Adaptive Boosting (AdaBoost) and (v) Extreme Gradient Boosting (XGBoost), were tested for Greater Hyderabad Municipal Corporation (GHMC), India, to evaluate their clustering abilities to classify locations (flooded or non-flooded) for climate change scenarios. A geo-spatial database, with eight flood influencing factors, namely, rainfall, elevation, slope, distance from nearest stream, evapotranspiration, land surface temperature, normalised difference vegetation index and curve number, was developed for 2000, 2006 and 2016. XGBoost performed the best, with the highest mean area under curve score of 0.83. Hence, XGBoost was adopted to simulate the future flood locations corresponding to probable highest rainfall events under four Representative Concentration Pathways (RCPs), namely, 2.6, 4.5, 6.0 and 8.5 along with other flood influencing factors for 2040, 2056, 2050 and 2064, respectively. The resulting ranges of flood risk probabilities are predicted as 39–77%, 16–39%, 42–63% and 39–77% for the respective years.

scholarly journals Comparison of the performance of machine learning algorithms in breast cancer screening and detection: A protocol

2019 ◽  
Vol 8 (3) ◽  
Author(s):  
Zakia Salod ◽  
Yashik Singh
Keyword(s):  
Breast Cancer ◽  
Screening Method ◽  
Parameter Tuning ◽  
Developed Countries ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
K Nearest Neighbors ◽  
Adaptive Boosting ◽  
Triple Assessment ◽  
Extreme Gradient Boosting

Background: Breast Cancer (BC) is a known global crisis. TheWorld Health Organization reports a global 2.09 million inci-dences and 627,000 deaths in 2018 relating to BC. The traditionalBC screening method in developed countries is mammography,whilst developing countries employ breast self-examination andclinical breast examination. The prominent gold standard for BCdetection is triple assessment: i) clinical examination, ii) mam-mography and/or ultrasonography; and iii) Fine Needle AspirateCytology. However, the introduction of cheaper, efficient and non-invasive methods of BC screening and detection would be benefi-cial. Design and methods: We propose the use of eight machinelearning algorithms: i) Logistic Regression; ii) Support VectorMachine; iii) K-Nearest Neighbors; iv) Decision Tree; v) RandomForest; vi) Adaptive Boosting; vii) Gradient Boosting; viii)eXtreme Gradient Boosting, and blood test results using BCCoimbra Dataset (BCCD) from University of California Irvineonline database to create models for BC prediction. To ensure themodels’ robustness, we will employ: i) Stratified k-fold Cross-Validation; ii) Correlation-based Feature Selection (CFS); and iii)parameter tuning. The models will be validated on validation andtest sets of BCCD for full features and reduced features. Featurereduction has an impact on algorithm performance. Seven metricswill be used for model evaluation, including accuracy. Expected impact of the study for public health: The CFStogether with highest performing model(s) can serve to identifyimportant specific blood tests that point towards BC, which mayserve as an important BC biomarker. Highest performing model(s)may eventually be used to create an Artificial Intelligence tool toassist clinicians in BC screening and detection.

scholarly journals Radiomic prediction of radiation pneumonitis on pretreatment planning computed tomography images prior to lung cancer stereotactic body radiation therapy

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Taka-aki Hirose ◽  
Hidetaka Arimura ◽  
Kenta Ninomiya ◽  
Tadamasa Yoshitake ◽  
Jun-ichi Fukunaga ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Radiation Therapy ◽  
Stereotactic Body Radiation Therapy ◽  
Prediction Models ◽  
Ct Images ◽  
Imaging Biomarkers ◽  
Stereotactic Body Radiation ◽  
Computed Tomography Images ◽  
Radiation Induced

AbstractThis study developed a radiomics-based predictive model for radiation-induced pneumonitis (RP) after lung cancer stereotactic body radiation therapy (SBRT) on pretreatment planning computed tomography (CT) images. For the RP prediction models, 275 non-small-cell lung cancer patients consisted of 245 training (22 with grade ≥ 2 RP) and 30 test cases (8 with grade ≥ 2 RP) were selected. A total of 486 radiomic features were calculated to quantify the RP texture patterns reflecting radiation-induced tissue reaction within lung volumes irradiated with more than x Gy, which were defined as LVx. Ten subsets consisting of all 22 RP cases and 22 or 23 randomly selected non-RP cases were created from the imbalanced dataset of 245 training patients. For each subset, signatures were constructed, and predictive models were built using the least absolute shrinkage and selection operator logistic regression. An ensemble averaging model was built by averaging the RP probabilities of the 10 models. The best model areas under the receiver operating characteristic curves (AUCs) calculated on the training and test cohort for LV5 were 0.871 and 0.756, respectively. The radiomic features calculated on pretreatment planning CT images could be predictive imaging biomarkers for RP after lung cancer SBRT.

scholarly journals Rapid screening for COVID-19 by applying artificial intelligence to chest computed tomography images: A feasibility study

2021 ◽  
Vol 5 ◽  
pp. 239920262110136
Author(s):  
Pedro Galván ◽  
José Fusillo ◽  
Felipe González ◽  
Oraldo Vukujevic ◽  
Luciano Recalde ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Computed Tomography ◽  
Pleural Effusion ◽  
Feasibility Study ◽  
Ct Images ◽  
Public Hospitals ◽  
Rt Pcr ◽  
Chest Computed Tomography ◽  
Computed Tomography Images ◽  
Respiratory Conditions

Aim: The aim of the study was to present the results and impact of the application of artificial intelligence (AI) in the rapid diagnosis of COVID-19 by telemedicine in public health in Paraguay. Methods: This is a descriptive, multi-centered, observational design feasibility study based on an AI tool for the rapid detection of COVID-19 in chest computed tomography (CT) images of patients with respiratory difficulties attending the country’s public hospitals. The patients’ digital CT images were transmitted to the AI diagnostic platform, and after a few minutes, radiologists and pneumologists specialized in COVID-19 downloaded the images for evaluation, confirmation of diagnosis, and comparison with the genetic diagnosis (reverse transcription polymerase chain reaction (RT-PCR)). It was also determined the percentage of agreement between two similar AI systems applied in parallel to study the viability of using it as an alternative method of screening patients with COVID-19 through telemedicine. Results: Between March and August 2020, 911 rapid diagnostic tests were carried out on patients with respiratory disorders to rule out COVID-19 in 14 hospitals nationwide. The average age of patients was 50.7 years, 62.6% were male and 37.4% female. Most of the diagnosed respiratory conditions corresponded to the age group of 27–59 years (252 studies), the second most frequent corresponded to the group over 60 years, and the third to the group of 19–26 years. The most frequent findings of the radiologists/pneumologists were severe pneumonia, bilateral pneumonia with pleural effusion, bilateral pulmonary emphysema, diffuse ground glass opacity, hemidiaphragmatic paresis, calcified granuloma in the lower right lobe, bilateral pleural effusion, sequelae of tuberculosis, bilateral emphysema, and fibrotic changes, among others. Overall, an average of 86% agreement and 14% diagnostic discordance was determined between the two AI systems. The sensitivity of the AI system was 93% and the specificity 80% compared with RT-PCR. Conclusion: Paraguay has an AI-based telemedicine screening system for the rapid stratified detection of COVID-19 from chest CT images of patients with respiratory conditions. This application strengthens the integrated network of health services, rationalizing the use of specialized human resources, equipment, and inputs for laboratory diagnosis.

Sign in / Sign up

Export Citation Format

Share Document