An accurate neural network algorithm to diagnose Covid-19 from CT images (original) (raw)
Related papers
Detection of COVID-19 from Chest X-Ray Images using CNN and ANN Approach
International Journal of Advanced Computer Science and Applications
The occurrence of coronavirus (COVID-19), which causes respiratory illnesses, is higher than in 2003. (SARS). COVID-19 and SARS are both spreading over regions and infecting living beings, with more than 73,435 deaths and more than 2000 deaths documented as of August 12, 2020. In contrast, SARS killed 774 lives in 2003, whereas COVID-19 claimed more in the shortest amount of time. However, the fundamental difference between them is that, after 17 years of SARS, a powerful new tool has developed that could be utilized to combat the virus and keep it within reasonable boundaries. One of these tools is machine learning (ML). Recently, machine learning (ML) has caused a paradigm shift in the healthcare industry, and its use in the COVID-19 outbreak could be profitable, especially in forecasting the location of the next outbreak. The use of AI in COVID-19 diagnosis and monitoring can be accelerated, reducing the time and cost of these processes. As a result, this study uses ANN and CNN techniques to detect COVID-19 from chest x-ray pictures, with 95% and 75% accuracy, respectively. Machine learning has greatly enhanced monitoring, diagnosis, monitoring, analysis, forecasting, touch tracking, and medication/vaccine production processes for the Covid-19 disease outbreak, reducing human involvement in nursing treatment.
Covid-19 Chest X-ray Images: Lung Segmentation and Diagnosis using Neural Networks
International journal on computational science & applications, 2020
COVID-19 has caused worldwide disturbances and the machine learning community has been finding ways to combat the disease. Applications of neural networks in image processing tasks allow COVID-19 Chest X-ray images to be meaningfully processed. In this study, the V7 Darwin COVID-19 Chest X-ray Dataset is used to train a U-Net based network that performs lung-region segmentation and a convolutional neural network that performs diagnosis on Chest X-ray images. This dataset is larger than most of the datasets used to develop existing COVID-19 related neural networks. The lung segmentation network achieved an accuracy of 0.9697 on the training set and an accuracy of 0.9575, an Intersectionover-union of 0.8666, and a dice coefficient of 0.9273 on the validation set. The diagnosis network achieved an accuracy of 0.9620 on the training set and an accuracy of 0.9666 and AUC of 0.985 on the validation set.
IRJET- Detecting Covid-19 In Chest X-ray Images Using Neural Networks
IRJET, 2021
In this paper we study the applications of Artificial Intelligence, particularly, neural networks in predicting whether a patient is inflicted with Covid-19, the illness caused by the SARS-CoV-2 virus. Convolutional Neural Networks (CNN), a subtype of deep neural networks are the most suitable for image analysis. In this study, the Convolutional neural network algorithm is applied to chest X-ray images of patients afflicted with various respiratory pathologies to determine if they are suffering from Covid-19. Another key aspect is differentiating between Covid-19 and other lung illnesses like viral pneumonia.
Automated Detection of COVID-19 from CT Scans using Convolutional Neural Networks
Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods, 2021
COVID-19 is an infectious disease that causes respiratory problems similar to those caused by SARS-CoV (2003). Currently, swab samples are being used for its diagnosis. The most common testing method used is the RT-PCR method, which has high specificity but variable sensitivity. AIbased detection has the capability to overcome this drawback. In this paper, we propose a prospective method wherein we use chest CT scans to diagnose the patients for COVID-19 pneumonia. We use a set of open-source images, available as individual CT slices, and full CT scans from a private Indian Hospital to train our model. We build a 2D segmentation model using the U-Net architecture, which gives the output by marking out the region of infection. Our model achieves a sensitivity of 0.964 (95% CI: 0.88-1) and a specificity of 0.884 (95% CI: 0.82-0.94). Additionally, we derive a logic for converting our slice-level predictions to scan-level, which helps us reduce the false positives.
Bioscience Biotechnology Research Communications, 2021
At recent times as the COVID 19 pandemic surges in global level, this research article aims at presenting an efficient support system for the physicians in diagnosing the COVID 19 disease using deep learning architectures. The automated diagnosis is made available primarily based on evaluation of medical images (Chest CT images) in diagnosing COVID-19. This COVID 19 affects the normal functioning of the lungs and it damages the tiny air sacs called alveoli. The Chest CT, especially in case of diagnosis of severely infected patients has higher importance and also for immediate COVID 19 screening before certain emergency surgeries and treatment procedures. Till now, the diagnosis of chest CT depends on the visual analysis of radiologists, which may be prone to error at times. First of all, chest CT holds hundreds of slices, which takes a while to diagnose. Next, COVID-19, as a pulmonary disease, has a similar instance with diverse varieties of pneumonia. This research attempts to diagnose the severity of COVID-19 by detecting the abnormalities based on the radiomics features of the chest CT images (pre-processed). These features help to discriminate between the normal opaque region, GGO's, and high intensity region including blood vessels and other consolidations. This (classification of chest CT image using radiomic features for COVID 19 diagnosis using neural network) approach can lessen subjective variability and improves diagnostic efficiency when compared to modern-day qualitative evaluation techniques.
Detecting SARS-CoV-2 From Chest X-Ray Using Artificial Intelligence
IEEE Access, 2021
Chest radiographs (X-rays) combined with Deep Convolutional Neural Network (CNN) methods have been demonstrated to detect and diagnose the onset of COVID-19, the disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). However, questions remain regarding the accuracy of those methods as they are often challenged by limited datasets, performance legitimacy on imbalanced data, and have their results typically reported without proper confidence intervals. Considering the opportunity to address these issues, in this study, we propose and test six modified deep learning models, including VGG16, InceptionResNetV2, ResNet50, MobileNetV2, ResNet101, and VGG19 to detect SARS-CoV-2 infection from chest X-ray images. Results are evaluated in terms of accuracy, precision, recall, and f-score using a small and balanced dataset (Study One), and a larger and imbalanced dataset (Study Two). With 95% confidence interval, VGG16 and MobileNetV2 show that, on both datasets, the model could identify patients with COVID-19 symptoms with an accuracy of up to 100%. We also present a pilot test of VGG16 models on a multi-class dataset, showing promising results by achieving 91% accuracy in detecting COVID-19, normal, and Pneumonia patients. Furthermore, we demonstrated that poorly performing models in Study One (ResNet50 and ResNet101) had their accuracy rise from 70% to 93% once trained with the comparatively larger dataset of Study Two. Still, models like InceptionResNetV2 and VGG19's demonstrated an accuracy of 97% on both datasets, which posits the effectiveness of our proposed methods, ultimately presenting a reasonable and accessible alternative to identify patients with COVID-19. INDEX TERMS Artificial intelligence, COVID-19, coronavirus, SARS-CoV-2, deep learning, chest X-ray, imbalanced data, small data. I. INTRODUCTION The Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), previously known as the Novel Coronavirus, was first reported in Wuhan, China and rapidly spread around the world, pushing the World Health Organization (WHO) to declare the outbreak of the virus as a global pandemic and health emergency on March 11, 2020. According to official data, 19 million people have been infected worldwide, with the number of deaths surpassing 700, 000, and 12 million The associate editor coordinating the review of this manuscript and approving it for publication was Derek Abbott. recovery cases reported by August 6, 2020 [1]. In the United States, the first case was reported on January 20, 2020, which evolved into a current number of confirmed cases, deaths, and recovered patients reaching more than 5 million, 162, 000, and 2.5 million, respectively (August 6, 2020 data) [1]. COVID-19 can be transmitted in several ways. The virus can spread quickly among humans via community transmission, such as close contact between individuals, and the transfer of respiratory droplets produced via coughing, sneezing, and talking. Several symptoms have been reported so far, including fever, tiredness, and dry cough as the most common. Additionally, aches, pain, nasal congestion, runny
Automated Detection of Covid-19 Coronavirus Cases Using Deep Neural Networks with CT Images
Al-Azhar University Journal of Virus Researches and Studies, 2020
Early detection of COVID-19 based on chest CT will enable timely treatment of patients and help control the spread of the disease. With rapid spreading of COVID-19 in many countries, however, CT volumes of suspicious patients are increasing at a speed much faster than the availability of human experts. Here, we propose an artificial intelligence (AI) system for fast COVID-19 diagnosis with an accuracy comparable to experienced radiologists. A large dataset was constructed by collecting 746 CT volumes of 359 patients with confirmed COVID-19 and 387 negative cases from publicly available chest CT datasets. In this paper, we propose a deep learning architecture to detect Covid-19 Coronavirus in CT Images. This architecture contains one network to classify images as either Covid-19 or Non-Covid-19. The experiment results evaluated by three parameters including accuracy, sensitivity, and specificity. For the ResNet-50 deep learning, these outcomes refer to the maximum sensitivity being 91.69% by the training dataset for the ResNet-50. ResNet-50 can be considered as a high sensitivity model to characterize and diagnose Covid-19 Coronavirus and can be used as an adjuvant tool in radiology departments.
Artificial Intelligence for the Detection of Coronavirus Disease (COVID-19) from Chest X-Ray Images
2021
The COVID-19 pandemic keeps on devastatingly affecting the wellbeing and prosperity of the worldwide populace. To reduce the rapid spread of the COVID-19 virus primary screening of the infected patient repeatedly is a need. Medical imaging is an essential tool for faster diagnosis to fight against the virus. Early diagnosis on chest radiography shows the Coronavirus disease (COVID-19) infected images shows variations from the Normal images. Deep Convolution Neural Networks shows an outstanding performance in the medical image analysis of Computed Tomography (CT) and Chest XRay (CXR) images. Therefore, in this paper, we designed a Deep Convolution Neural Network that detects COVID-19 infected samples from Pneumonia and Normal Chest XRay (CXR) images. We also construct the dataset that contains 6023 CXR images in which 5368 images are used for training and 655 images are used for testing the model for the three categories such as COVID-19, Normal, and Pneumonia. The proposed model sho...
Automated Covid-19 Detection System with CNN using Chest X-Ray and CT-Scans
Covid19 is the menace of this century. World Health Organization (WHO) declared it pandemic in February, 2020. This RNA virus has catastrophic impact of the entire human civilization since it was initially reported to have been erupted from Wuhan, a city in Hubei province of China in late December 2019. In the first wave millions of people died in many countries. Even the developed countries like USA, France, Italy, United Kingdom etc. were in shock and could not prevent loss of human lives with their well-established medical infrastructure. Strict lockdown, quarantines were imposed. The hospitals were outnumbered by the severely ill patients who needed ventilation support. Many died without treatment, dead bodies were on the streets and mass graves became a practice. Developing and underdeveloped countries faced even more disastrous situations. Since then the virus is mutating and giving new challenges to human society in developing a cure. Until now RTPCR and other test are carried out to detect the disease. But they take somewhat longer time. So researchers are using artificial intelligence based techniques especially deep learning methods to develop new models using the CT scans (CTS) and chest X-ray (CXR) images of the patients to detect the disease in real time. This work focuses on the methods developed so far for detecting Covid-19 using convolutional neural network and compare their performances.
Perspective of AI system for COVID-19 detection using chest images: a review
Multimedia Tools and Applications
Coronavirus Disease 2019 (COVID-19) is an evolving communicable disease caused due to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) which has led to a global pandemic since December 2019. The virus has its origin from bat and is suspected to have transmitted to humans through zoonotic links. The disease shows dynamic symptoms, nature and reaction to the human body thereby challenging the world of medicine. Moreover, it has tremendous resemblance to viral pneumonia or Community Acquired Pneumonia (CAP). Reverse Transcription Polymerase Chain Reaction (RT-PCR) is performed for detection of COVID-19. Nevertheless, RT-PCR is not completely reliable and sometimes unavailable. Therefore, scientists and researchers have suggested analysis and examination of Computing Tomography (CT) scans and Chest X-Ray (CXR) images to identify the features of COVID-19 in patients having clinical manifestation of the disease, using expert systems deploying learning algorithms such as Machine Learning (ML) and Deep Learning (DL). The paper identifies and reviews various chest image features using the aforementioned imaging modalities for reliable and faster detection of COVID-19 than laboratory processes. The paper also reviews and compares the different aspects of ML and DL using chest images, for detection of COVID-19.