scholarly journals Classification of COVID-19 Chest CT Images Based on Ensemble Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Xiaoshuo Li ◽  
Wenjun Tan ◽  
Pan Liu ◽  
Qinghua Zhou ◽  
Jinzhu Yang
Keyword(s):  
Deep Learning ◽  
Medical Personnel ◽  
Classification Performance ◽  
Cascade Classifier ◽  
Data Set ◽  
Global Pandemic ◽  
Good Classification Performance ◽  
Ct Image Analysis ◽  
Assisted Diagnosis ◽  
Novel Coronavirus

Novel coronavirus pneumonia (NCP) has become a global pandemic disease, and computed tomography-based (CT) image analysis and recognition are one of the important tools for clinical diagnosis. In order to assist medical personnel to achieve an efficient and fast diagnosis of patients with new coronavirus pneumonia, this paper proposes an assisted diagnosis algorithm based on ensemble deep learning. The method combines the Stacked Generalization ensemble learning with the VGG16 deep learning to form a cascade classifier, and the information constituting the cascade classifier comes from multiple subsets of the training set, each of which is used to collect deviant information about the generalization behavior of the data set, such that this deviant information fills the cascade classifier. The algorithm was experimentally validated for classifying patients with novel coronavirus pneumonia, patients with common pneumonia (CP), and normal controls, and the algorithm achieved a prediction accuracy of 93.57%, sensitivity of 94.21%, specificity of 93.93%, precision of 89.40%, and F1-score of 91.74% for the three categories. The results show that the method proposed in this paper has good classification performance and can significantly improve the performance of deep neural networks for multicategory prediction tasks.

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

scholarly journals Forecasting the COVID-19 Outbreak: An Application of Arima and Fuzzy Time Series Models

2020 ◽  
Author(s):  
Prashant Verma ◽  
Mukti Khetan ◽  
Shikha Dwivedi ◽  
Shweta Dixit
Keyword(s):  
Time Series ◽  
Health Care Systems ◽  
Medical Personnel ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Data Set ◽  
Care Systems ◽  
Novel Coronavirus ◽  
Time Series Methodology ◽  
Near Future

Abstract Purpose: The whole world is surfaced with an inordinate challenge of mankind due to COVID-19, caused by 2019 novel coronavirus (SARS-CoV-2). After taking hundreds of thousands of lives, millions of people are still in the substantial grasp of this virus. This virus is highly contagious with reproduction number R0, as high as 6.5 worldwide and between 1.5 to 2.6 in India. So, the number of total infections and the number of deaths will get a day-to-day hike until the curve flattens. Under the current circumstances, it becomes inevitable to develop a model, which can anticipate future morbidities, recoveries, and deaths. Methods: We have developed some models based on ARIMA and FUZZY time series methodology for the forecasting of COVID-19 infections, mortalities and recoveries in India and Maharashtra explicitly, which is the most affected state in India, following the COVID-19 statistics till “Lockdown 3.0” (17th May 2020). Results: Both models suggest that there will be an exponential uplift in COVID-19 cases in the near future. We have forecasted the COVID-19 data set for next seven days. The forecasted values are in good agreement with real ones for all six COVID-19 scenarios for Maharashtra and India as a whole as well.Conclusion: The forecasts for the ARIMA and FUZZY time series models will be useful for the policymakers of the health care systems so that the system and the medical personnel can be prepared to combat the pandemic.

Covid-19 Detection using Deep Convolutional Neural Networks from X-Ray Images

2021 ◽  
Vol 4 (2) ◽  
pp. 139-143
Author(s):  
Abdullah Ajmal ◽  
Sundas Ibrar ◽  
Wakeel Ahmad ◽  
Syed Muhammad Adnan Shah
Keyword(s):  
Deep Learning ◽  
Global Economy ◽  
Data Augmentation ◽  
Diagnostic Techniques ◽  
Deep Convolutional Neural Networks ◽  
Data Set ◽  
Daily Lives ◽  
X Ray ◽  
The World ◽  
Novel Coronavirus

Abstract— The Novel Coronavirus generally, knows as COVID-19 which first appeared in Wuhan city of China in December 2019, spread quickly around the world and became a pandemic. It has caused an overwhelming effect on daily lives, Public health, and the global economy. Many people have been affected and have died. It is critical to control and prevent the spread of COVID-19 disease by applying quick alternative diagnostic techniques. COVID-19 cases are rising day by day around the world, the on-time diagnosis of COVID-19 patients is an increasingly long and difficult process. COVID-19 patient test kits are costly and not available for every individual in poor countries. For this purpose, screening patients with the established techniques like Chest X-ray images seems to be an effective method. This study used a deep learning data augmentation on a publicly available data set and train advanced CNN models on it. The proposed model was tested using a state-of-the-art evaluation measures and obtained better results. Our model, the COVID-19 images is available at (https://github.com/ieee8023/covid-chestxray-dataset) and for Non-COVID-19 images is available at (https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia). The maximum accuracy achieved in the validation was 96.67%. Our model of COVID-19 detection achieved an average F measure of 98%, and an Area Under Curve (AUC) of 99%. The results demonstrate that deep learning proved to be an effective and easily deployable approach for COVID-19 detection.

scholarly journals An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Chi-Long Chen ◽  
Chi-Chung Chen ◽  
Wei-Hsiang Yu ◽  
Szu-Hua Chen ◽  
Yu-Chan Chang ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Characteristic Curve ◽  
Digital Pathology ◽  
Classification Performance ◽  
Multiple Instance Learning ◽  
Data Set ◽  
Memory Mechanism ◽  
Strong Localization ◽  
Training Approach

AbstractDeep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping.

scholarly journals IMPROVING LULC CLASSIFICATION FROM SATELLITE IMAGERY USING DEEP LEARNING – EUROSAT DATASET

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 369-376
Author(s):  
H. Yassine ◽  
K. Tout ◽  
M. Jaber
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Satellite Imagery ◽  
Vegetation Index ◽  
Near Infrared ◽  
Spectral Feature ◽  
Classification Performance ◽  
Training Data ◽  
Data Set ◽  
Sentinel 2

Abstract. Machine learning (ML) has proven useful for a very large number of applications in several domains. It has realized a remarkable growth in remote-sensing image analysis over the past few years. Deep Learning (DL) a subset of machine learning were applied in this work to achieve a better classification of Land Use Land Cover (LULC) in satellite imagery using Convolutional Neural Networks (CNNs). EuroSAT benchmarking data set is used as training data set which uses Sentinel-2 satellite images. Sentinel-2 provides images with 13 spectral feature bands, but surprisingly little attention has been paid to these features in deep learning models. The majority of applications focused only on using RGB due to high availability of the RGB models in computer vision. While RGB gives an accuracy of 96.83% using CNN, we are presenting two approaches to improve the classification performance of Sentinel-2 images. In the first approach, features are extracted from 13 spectral feature bands of Sentinel-2 instead of RGB which leads to accuracy of 98.78%. In the second approach features are extracted from 13 spectral bands of Sentinel-2 in addition to calculated indices used in LULC like Blue Ratio (BR), Vegetation index based on Red Edge (VIRE) and Normalized Near Infrared (NNIR), etc. which gives a better accuracy of 99.58%.

scholarly journals Transfer learning to detect COVID-19 automatically from X-ray images, using convolutional neural networks

2020 ◽  
Author(s):  
Mundher Taresh ◽  
Ningbo Zhu ◽  
Talal Ahmed Ali Ali
Keyword(s):  
Deep Learning ◽  
Confusion Matrix ◽  
High Accuracy ◽  
Classification Model ◽  
Statistical Parameters ◽  
Data Set ◽  
X Ray ◽  
X Ray Imaging ◽  
Chest X Ray ◽  
Novel Coronavirus

AbstractNovel coronavirus pneumonia (COVID-19) is a contagious disease that has already caused thousands of deaths and infected millions of people worldwide. Thus, all technological gadgets that allow the fast detection of COVID-19 infection with high accuracy can offer help to healthcare professionals. This study is purposed to explore the effectiveness of artificial intelligence (AI) in the rapid and reliable detection of COVID-19 based on chest X-ray imaging. In this study, reliable pre-trained deep learning algorithms were applied to achieve the automatic detection of COVID-19-induced pneumonia from digital chest X-ray images.Moreover, the study aims to evaluate the performance of advanced neural architectures proposed for the classification of medical images over recent years. The data set used in the experiments involves 274 COVID-19 cases, 380 viral pneumonia, and 380 healthy cases, which was collected from the available X-ray images on public medical repositories. The confusion matrix provided a basis for testing the post-classification model. Furthermore, an open-source library PyCM* was used to support the statistical parameters. The study revealed the superiority of Model VGG16 over other models applied to conduct this research where the model performed best in terms of overall scores and based-class scores. According to the research results, deep learning with X-ray imaging is useful in the collection of critical biological markers associated with COVID-19 infection. The technique is conducive for the physicians to make a diagnosis of COVID-19 infection. Meanwhile, the high accuracy of this computer-aided diagnostic tool can significantly improve the speed and accuracy of COVID-19 diagnosis.

scholarly journals Review on Deep Learning Based Automatic Detection of COVID-19 from Chest-X Ray Images

2021 ◽  
pp. 10-14
Author(s):  
Debaraj Rana ◽  
Swarna Prabha Jena ◽  
Subrat Kumar Pradhan
Keyword(s):  
Deep Learning ◽  
Virus Disease ◽  
Health Sector ◽  
Cost Effective ◽  
Data Set ◽  
X Ray ◽  
Time Consumption ◽  
Corona Virus ◽  
Global Pandemic ◽  
Chest X Ray

The Global pandemic declared Corona Virus Disease (COVID 19) has affected severely tothe health of human being over the globe. More than 15 crore around worldwide have been affected by the Novel Corona virus and it is progressing rapidly. Mainly in the health sector, the hospitals are not properly equipped with proper diagnosis system which can detect the disease accurately with less time consumption. The Chest X Ray image are taking less time and cost effective which can be used for detection of COVID 19 even the severity can also be determine form the CXR images. In the current research many researchers are focusing on implementation of Deep learning method for accurate and quick detection of COVID 19 which can help the radiologist for evaluation of the disease. In this review, proposed Deep learning methodology from the literature have been discussed with their experimental data set. This review could help to develop modified architecture which gives more improvement in the diagnosis in term of computational complexity and time consumption

scholarly journals Predicting environmentally responsive transgenerational differential DNA methylated regions (epimutations) in the genome using a hybrid deep-machine learning approach

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Pegah Mavaie ◽  
Lawrence Holder ◽  
Daniel Beck ◽  
Michael K. Skinner
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Classification Performance ◽  
Entire Genome ◽  
Molecular Features ◽  
Environmentally Responsive ◽  
Machine Learning Approach ◽  
Good Classification Performance ◽  
Deep Learning Network ◽  
Rat Genome

Abstract Background Deep learning is an active bioinformatics artificial intelligence field that is useful in solving many biological problems, including predicting altered epigenetics such as DNA methylation regions. Deep learning (DL) can learn an informative representation that addresses the need for defining relevant features. However, deep learning models are computationally expensive, and they require large training datasets to achieve good classification performance. Results One approach to addressing these challenges is to use a less complex deep learning network for feature selection and Machine Learning (ML) for classification. In the current study, we introduce a hybrid DL-ML approach that uses a deep neural network for extracting molecular features and a non-DL classifier to predict environmentally responsive transgenerational differential DNA methylated regions (DMRs), termed epimutations, based on the extracted DL-based features. Various environmental toxicant induced epigenetic transgenerational inheritance sperm epimutations were used to train the model on the rat genome DNA sequence and use the model to predict transgenerational DMRs (epimutations) across the entire genome. Conclusion The approach was also used to predict potential DMRs in the human genome. Experimental results show that the hybrid DL-ML approach outperforms deep learning and traditional machine learning methods.

scholarly journals Deep Learning Framework with ECG Feature-Based Kernels for Heart Disease Classification

2021 ◽  
Vol 27 (1) ◽  
pp. 48-59
Author(s):  
Thanh-Nghia Nguyen ◽  
Thanh-Hai Nguyen
Keyword(s):  
Heart Disease ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Classification Performance ◽  
Disease Classification ◽  
Kernel Size ◽  
S Waves ◽  
Learning Framework ◽  
Good Classification Performance ◽  
Fully Connected

Heart disease classification with high accuracy can support the physician’s correct decision on patients. This paper proposes a kernel size calculation based on P, Q, R, and S waves of one heartbeat to enhance classification accuracy in a deep learning framework. In addition, Electrocardiogram (ECG) signals were filtered using wavelet transform with dmey wavelet, in which the shape of the dmey is closed to that of one heartbeat. With this selected dmey, each heartbeat was standardized with 300 samples for calculation of kernel sizes so that it contains most features in each heartbeat. Therefore, in this research, with 103,459 heart rhythms from the MIT-BIH Arrhythmia Database, the proposed approach for calculation of kernel sizes is effective with seven convolutional layers and other fully connected layers in a Deep Neural Network (DNN). In particular, with five types of heart disease, the result of the high classification accuracy is about 99.4 %. It means that the proposed kernel size calculation in the convolutional layers can achieve good classification performance and it may be developed for classifying different types of disease.

Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines

2019 ◽  
Vol 19 (5) ◽  
pp. 1440-1452 ◽  
Author(s):  
Mahtab Mohtasham Khani ◽  
Sahand Vahidnia ◽  
Leila Ghasemzadeh ◽  
Y Eren Ozturk ◽  
Mustafa Yuvalaklioglu ◽  
...  
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Gas Turbines ◽  
Crack Detection ◽  
Image Data ◽  
Classification Performance ◽  
Data Set ◽  
Structural Health ◽  
Repair Costs ◽  
Classical Image

Gas turbine maintenance requires consistent inspections of cracks and other structural anomalies. The inspections provide information regarding the overall condition of the structures and yield information for estimating structural health and repair costs. Various image processing techniques have been used in the past to address the problem of automated visual crack detection with varying degrees of success. In this work, we propose a novel crack detection framework that utilizes techniques from both classical image processing and deep learning methodologies. The main contribution of this work is demonstrating that applying filters to image data in the pre-processing phase can significantly boost the classification performance of a convolutional neural network–based model. The developed architecture outperforms compared works by yielding a 96.26% classification accuracy on a data set of cracked surface images collected from gas turbines.

Sign in / Sign up

Export Citation Format

Share Document