Autonomous Smart Device for COVID-19 Detection Using Artificial Intelligence

2022 ◽  
pp. 128-147
Author(s):  
Rajani P. K. ◽  
Neha Motagi ◽  
Komal Nair ◽  
Rupali Narayankar
Keyword(s):  
Artificial Intelligence ◽  
Error Concealment ◽  
Virus Detection ◽  
Accurate Prediction ◽  
Smart Device ◽  
X Rays ◽  
X Ray ◽  
Early Stages ◽  
Biomedical Device ◽  
The World

Corona is a pandemic disease and is spreading all over the world. There is also lack of corona virus detection machines. If it is detected at very early stages without pathological intervention, then further spreading of the disease can be controlled, and many of human lives can be saved. So, the proposed biomedical device can be used for fast and accurate prediction of COVID-19 from chest x-rays. X-ray can also be taken from anywhere and sent through any communication medium. Even if error is added, it can be removed using error concealment algorithms. Automated AI-based systems will be used for prediction of normal, COVID-19, and pneumonic cases from x-ray images. It makes detection of COVID-19 infection less costly and portable. This device can be stored in less stringent conditions, making it more effective.

A Study on SARS-CoV-2 (COVID-19) and Machine Learning Based Approach to Detect COVID-19 Through X-Ray Images

2020 ◽  
pp. 2140010
Author(s):  
Anuj Kumar Gupta ◽  
Manvinder Sharma ◽  
Ankit Sharma ◽  
Vikas Menon
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Confusion Matrix ◽  
Training Model ◽  
X Rays ◽  
Wuhan City ◽  
X Ray ◽  
Entire World ◽  
Day By Day ◽  
A New Species

From origin in Wuhan city of China, a highly communicable and deadly virus is spreading in the entire world and is known as COVID-19. COVID-19 is a new species of coronavirus which is affecting respiratory system of human. The virus is known as severe acute respiratory syndrome (SARS) coronavirus 2 abbreviated as SARS-CoV-2 and generally known as coronavirus disease COVID-19. This is growing day by day in countries. The symptoms include fever, cough and difficulty in breathing. As there is no vaccine made for this virus and COVID-19 tests are not readily available, this is causing panic. Various Artificial Intelligence-based algorithms and frameworks are being developed to detect this virus, but it has not been tested. People are taking advantages of others by providing duplicate COVID-19 test kits. A work is carried out with deep learning to detect presence of COVID 19. With the use of Convolutional Neural networks, the model is trained with dataset of COVID-19 positive and negative X-Rays. The accuracy of training model is 99% and the confusion matrix shows 98% values that are predicted truly. Hence, the model is able to detect the presence of COVID-19.

scholarly journals Convolutional Support Vector Models: Prediction of Coronavirus Disease Using Chest X-rays

Information ◽  
2020 ◽  
Vol 11 (12) ◽  
pp. 548
Author(s):  
Mateus Maia ◽  
Jonatha S. Pimentel ◽  
Ivalbert S. Pereira ◽  
João Gondim ◽  
Marcos E. Barreto ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Predictive Performance ◽  
Polynomial Kernel ◽  
Support Vector ◽  
X Rays ◽  
X Ray ◽  
Applied Study ◽  
The World ◽  
Simulated Images

The disease caused by the new coronavirus (COVID-19) has been plaguing the world for months and the number of cases are growing more rapidly as the days go by. Therefore, finding a way to identify who has the causative virus is impressive, in order to find a way to stop its proliferation. In this paper, a complete and applied study of convolutional support machines will be presented to classify patients infected with COVID-19 using X-ray data and comparing them with traditional convolutional neural network (CNN). Based on the fitted models, it was possible to observe that the convolutional support vector machine with the polynomial kernel (CSVMPol) has a better predictive performance. In addition to the results obtained based on real images, the behavior of the models studied was observed through simulated images, where it was possible to observe the advantages of support vector machine (SVM) models.

The Machine is Doing the Work: Interview with Nicholas Mirzoeff

2018 ◽  
pp. 4-7
Author(s):  
Lenart Kučić ◽  
Nicholas Mirzoeff
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cloud Computing ◽  
Machine Vision ◽  
Communication Technologies ◽  
The Body ◽  
X Rays ◽  
Optical Performance ◽  
The World ◽  
Learning Machine

Optical and mechanical tools were the first major “augmentation” of human senses. The microscope approached the worlds that were too small for the optical performance of the eye. The telescope touched the too far-off space; X-rays radiated the inaccessible interior of the body. Such augmentations were not innocent, as they demanded a different interpretation of the world, which would correspond to images of infinitely small, remote or hidden. Similar augmentation is now happening with cloud computing, machine vision and artificial intelligence. With these tools, it may be possible to compile and analyze billions of digital images created daily by people and machines. But who will analyze these images and for what purpose? Will they help us to better understand society and learn from past mistakes? Or have they already been hijacked by attention-merchants and political demagogues who are effectively spreading old ideologies with new communication technologies? Keywords: augmented photography, communication technologies, machine learning, machine vision, reality

scholarly journals CAE-COVIDX: automatic covid-19 disease detection based on x-ray images using enhanced deep convolutional and autoencoder

2021 ◽  
Vol 7 (1) ◽  
pp. 49
Author(s):  
Hanafi Hanafi ◽  
Andri Pranolo ◽  
Yingchi Mao
Keyword(s):  
Confusion Matrix ◽  
Virus Detection ◽  
Image Features ◽  
World Health ◽  
X Rays ◽  
X Ray ◽  
First Case ◽  
Long Time ◽  
Novel Method ◽  
Health Organization

Since the first case in 2019, Corona Virus has been spreading all over the world. World Health Organization (WHO) announced that COVID-19 had become an international pandemic. There is an essential section to handle the spreading of the virus by immediate virus detection for patients. Traditional medical detection requires a long time, a specific laboratory, and a high cost. A method for detecting Covid-19 faster compared to common approaches, such as RT-PCR detection, is needed. The method demonstrated that it could produce an X-ray image with higher accuracy and consumed less time. We propose a novel method to extract image features and to classify COVID-19 using deep CNN combined with Autoencoder (AE) dubbed CAE-COVIDX. We evaluated and compared it with the traditional CNN and existing framework VGG16 involving 400 normal images of non-COVID19 and 400 positive COVID-19 diseases. The performance evaluation was conducted using accuracy, confusion matrix, and loss evaluation. Based on experiment results, the CAE-COVIDX framework outperforms previous methods in several testing scenarios. This framework's ability to detect Covid-19 in various nonstandard image X-rays could effectively help medical employers diagnose Covid-19 patients. It is an important factor to decrease the spreading of Covid-19 massively.

scholarly journals IVAN PULUJ AND THE DISCOVERY OF X-RAYS

2021 ◽  
Vol 64 (1) ◽  
Author(s):  
Ulyana Pidvalna ◽  
◽  
Roman Plyatsko ◽  
Vassyl Lonchyna ◽  
◽  
...  
Keyword(s):  
International Exhibition ◽  
Bone Lesions ◽  
X Rays ◽  
High Quality ◽  
X Ray ◽  
Exact Date ◽  
Starting Point ◽  
The World ◽  
New Type ◽  
The Given

On January 5, 1896, the Austrian newspaper Die Presse published an article entitled “A Sensational Discovery”. It was dedicated to the discovery of X-rays made on November 8, 1895 by the German physicist Wilhelm Conrad Röntgen. Having taken into account the contribution of other scientists, the precondition of the given epochal, yet unexpected, discovery was, first and foremost, the work of the Ukrainian scientist Ivan Puluj. It was Puluj who laid the foundation for X-ray science. He explained the nature of X-rays, discovered that they can ionize atoms and molecules, and defined the place of X-ray emergence and their distribution in space. In 1881, Puluj constructed a cathode lamp (“Puluj’s tube”) which was fundamentally a new type of light source. In the same year, in recognition of this discovery, Puluj received an award at the International Exhibition in Paris. Investigating the processes in cathode-ray tubes, Ivan Puluj set the stage for two ground-breaking discoveries in physics, namely X-rays and electrons. Puluj used his cathode lamp in medicine as a source of intense X-rays which proved to be highly efficient. The exact date of the first X-ray images received by Puluj remains unknown. High-quality photographs of the hand of an eleven-year-old girl, taken on January 18, 1896, are preserved. Multiple X-ray images clearly visualized pathological changes in the examined structures (fractures, calluses, tuberculous bone lesions). High-quality images were obtained by means of the anticathode in the design of Puluj’s lamp, which was the first in the world. The image of the whole skeleton of a stillborn child (published on April 3, 1896 in The Photogram) is considered to be the starting point of using X-rays in anatomy.

scholarly journals Artificial intelligence in the endocrine clinic: automated bone age analysis in arabic children from UAE

2021 ◽  
Vol 8 (7) ◽  
pp. 418-422
Author(s):  
Nandu Kumar Thalange ◽  
Elham Elgabaly Moustafa Ahmed ◽  
Ajay Prasanth D'Souza ◽  
Mireille El Bejjani
Keyword(s):  
Artificial Intelligence ◽  
Retrospective Chart Review ◽  
Bone Age ◽  
Close Correlation ◽  
Pediatric Radiologist ◽  
Growth Disorders ◽  
X Rays ◽  
X Ray ◽  
Experienced Radiologist ◽  
High Utility

Objective: Artificial intelligence (AI) is playing an increasing role in patient assessment. AI bone age analysis is such a tool, but its value in Arabic children presenting to an endocrine clinic has not been explored. We compared results from an experienced pediatric radiologist and the AI bone age system, BoneXpert (BX), (Visiana, Denmark) to assess its utility in a cohort of children presenting to the Al Jalila Children’s Specialty Hospital endocrine service. Materials and Methods: We conducted a retrospective chart review of 47 children with growth disorders, initially assessed by a single experienced radiologist and subsequently by BX, to confirm the usefulness of the BX system in our population. The results of the analyses were analysed using a Bland-Altman plot constructed to compare differences between the radiologist’s interpretation and BX across the available range of bone age. Results: Forty-four of the patient x-ray images were analysed by BX. Three X-ray images were rejected by BX due to post-processing artifacts, which prevented computer interpretation. For the remaining 44 X-rays, there was a close correlation between radiologist and BX results (r=0.93; p <0.00001).  Two radiographs were identified with a large discrepancy in the reported bone ages. Blinded, independent re-evaluation of the radiographs showed the original manually interpreted bone age to have been erroneous, with the BX results corresponding closely to the amended bone age. A small positive bias was noted in bone age (+0.39 years) in the BX analyses, relative to manual interpretation. Conclusions: AI bone age analysis was of high utility in Arabic children from UAE presenting to an endocrine clinic, with results highly comparable to an experienced radiologist. In the two cases where a large discrepancy was found, independent re-evaluation showed AI analysis was correct.

scholarly journals Improving Coronavirus (COVID-19) Diagnosis using Deep Transfer Learning

2020 ◽  
Author(s):  
Arshia Rehman ◽  
Saeeda Naz ◽  
Ahmed Khan ◽  
Ahmad Zaib ◽  
Imran Razzak
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Bacterial Pneumonia ◽  
State Of The Art ◽  
High Accuracy ◽  
X Rays ◽  
Early Screening ◽  
X Ray ◽  
Learning Techniques ◽  
The World

AbstractBackgroundCoronavirus disease (COVID-19) is an infectious disease caused by a new virus. Exponential growth is not only threatening lives, but also impacting businesses and disrupting travel around the world.AimThe aim of this work is to develop an efficient diagnosis of COVID-19 disease by differentiating it from viral pneumonia, bacterial pneumonia and healthy cases using deep learning techniques.MethodIn this work, we have used pre-trained knowledge to improve the diagnostic performance using transfer learning techniques and compared the performance different CNN architectures.ResultsEvaluation results using K-fold (10) showed that we have achieved state of the art performance with overall accuracy of 98.75% on the perspective of CT and X-ray cases as a whole.ConclusionQuantitative evaluation showed high accuracy for automatic diagnosis of COVID-19. Pre-trained deep learning models develop in this study could be used early screening of coronavirus, however it calls for extensive need to CT or X-rays dataset to develop a reliable application.

scholarly journals Imaging and screening in lung cancer

2008 ◽  
Vol 2 (4) ◽  
pp. 193-203
Author(s):  
Matteo Giaj Levra ◽  
Marina Longo ◽  
Enrica Capelletto ◽  
Simonetta Grazia Rapetti ◽  
Silvia Novello
Keyword(s):  
Lung Cancer ◽  
Cause Of Death ◽  
Screening Tests ◽  
X Ray ◽  
Early Stages ◽  
The World

Lung cancer is the main cause of death for neoplasia in the world. Hence it’s growing the necessity to investigate screening tests to detect tumoral lesions at the early stages: several trials have been performed to establish the best method, target and frequence of the screening to offer. CT, X-ray, PET, sputum citology and CAD software are here analyzed, together with the associated statistics and bias.

scholarly journals Artificial intelligence to diagnosis distal radius fracture using biplane plain X-rays

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Kunihiro Oka ◽  
Ryoya Shiode ◽  
Yuichi Yoshii ◽  
Hiroyuki Tanaka ◽  
Toru Iwahashi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diagnostic Accuracy ◽  
Distal Radius ◽  
Diagnostic Tests ◽  
Styloid Process ◽  
Final Diagnosis ◽  
Distal Radius Fractures ◽  
X Rays ◽  
Radius Fractures ◽  
X Ray

Abstract Background Although the automatic diagnosis of fractures using artificial intelligence (AI) has recently been reported to be more accurate than those by orthopedics specialists, big data with at least 1000 images or more are required for deep learning of the convolutional neural network (CNN) to improve diagnostic accuracy. The aim of this study was to develop an AI system capable of diagnosing distal radius fractures with high accuracy even when learning with relatively small data by learning to use bi-planar X-rays images. Methods VGG16, a learned image recognition model, was used as the CNN. It was modified into a network with two output layers to identify the fractures in plain X-ray images. We augmented 369 plain X-ray anteroposterior images and 360 lateral images of distal radius fractures, as well as 129 anteroposterior images and 125 lateral images of normal wrists to conduct training and diagnostic tests. Similarly, diagnostic tests for fractures of the styloid process of the ulna were conducted using 189 plain X-ray anteroposterior images of fractures and 302 images of the normal styloid process. The distal radius fracture is determined by entering an anteroposterior image of the wrist for testing into the trained AI. If it identifies a fracture, it is diagnosed as the same. However, if the anteroposterior image is determined as normal, the lateral image of the same patient is entered. If a fracture is identified, the final diagnosis is fracture; if the lateral image is identified as normal, the final diagnosis is normal. Results The diagnostic accuracy of distal radius fractures and fractures of the styloid process of the ulna were 98.0 ± 1.6% and 91.1 ± 2.5%, respectively. The areas under the receiver operating characteristic curve were 0.991 {n = 540; 95% confidence interval (CI), 0.984–0.999} and 0.956 (n = 450; 95% CI 0.938–0.973). Conclusions Our method resulted in a good diagnostic rate, even when using a relatively small amount of data.

scholarly journals Nanoporous gold: a hierarchical and multiscale 3D test pattern for characterizing X-ray nano-tomography systems

2019 ◽  
Vol 26 (1) ◽  
pp. 194-204 ◽  
Author(s):  
Emanuel Larsson ◽  
Doğa Gürsoy ◽  
Francesco De Carlo ◽  
Erica Lilleodden ◽  
Malte Storm ◽  
...  
Keyword(s):  
Test Pattern ◽  
Hierarchical Structures ◽  
Nanoporous Gold ◽  
Alignment Algorithm ◽  
High Electron ◽  
X Rays ◽  
Full Field ◽  
X Ray ◽  
The World ◽  
Synchrotron Beamlines

Full-field transmission X-ray microscopy (TXM) is a well established technique, available at various synchrotron beamlines around the world as well as by laboratory benchtop devices. One of the major TXM challenges, due to its nanometre-scale resolution, is the overall instrument stability during the acquisition of the series of tomographic projections. The ability to correct for vertical and horizontal distortions of each projection image during acquisition is necessary in order to achieve the effective 3D spatial resolution. The effectiveness of such an image alignment is also heavily influenced by the absorption properties and strong contrast of specific features in the scanned sample. Here it is shown that nanoporous gold (NPG) can be used as an ideal 3D test pattern for evaluating and optimizing the performance of a TXM instrument for hard X-rays at a synchrotron beamline. Unique features of NPG, such as hierarchical structures at multiple length scales and high absorbing capabilities, makes it an ideal choice for characterization, which involves a combination of a rapid-alignment algorithm applied on the acquired projections followed by the extraction of a set of both 2D- and 3D-descriptive image parameters. This protocol can be used for comparing the efficiency of TXM instruments at different synchrotron beamlines in the world or benchtop devices, based on a reference library of scanned NPG samples, containing information about the estimated horizontal and vertical alignment values, 2D qualitative parameters and quantitative 3D parameters. The possibility to tailor the ligament sizes of NPG to match the achievable resolution in combination with the high electron density of gold makes NPG an ideal 3D test pattern for evaluating the status and performance of a given synchrotron-based or benchtop-based TXM setup.

Sign in / Sign up

Export Citation Format

Share Document