Pneumonia Detection Using Deep Learning Architectures

Pneumonia is an infection caused by bacteria and viruses. It can shift from mellow to serious cases. This disease causes severe damages to the lungs since they fill with fluids. This situation causes difficulty in breathing. It further prevents oxygen to reach the blood. Pneumonia is diagnosed with the help of a chest X-rays, which can also use in the diagnosis of diseases like emphysema, lung cancer, and tuberculosis. According to WHO (World Health Organization (WHO). 2001. Standardization of Interpretation of Chest Radiographs for the Diagnosis of Pneumonia in Children. p.4.), Chest X-rays, at present, is the best available method for detecting pneumonia. Feature extraction methods like DiscreteWavelet Transform (DWT),Wavelet Frame Transform (WFT), andWavelet Packet Transform (WPT) can be used followed by any classification algorithm. In this paper, models like Squeezenet, DenseNet, and Resnet34 have been used for image recognition. In our system, the medical images were taken from Kaggle database and were recorded using a suitable imaging system. The images retrieved were then considered for input for the system where the images go through the various phases of image processing like pre-processing, edge detection and feature extraction. Later, a variety of training models are applied to know which model offers the highest accuracy.

Download Full-text

T26248G-transversion mutation in exon7 of the putative methyltransferase Nsun7 gene causes a change in protein folding associated with reduced sperm motility in asthenospermic men

Reproduction Fertility and Development ◽

10.1071/rd13371 ◽

2015 ◽

Vol 27 (3) ◽

pp. 471 ◽

Cited By ~ 17

Author(s):

Nahid Khosronezhad ◽

Abasalt Hosseinzadeh Colagar ◽

Syed Golam Ali Jorsarayi

Keyword(s):

Protein Folding ◽

Sperm Motility ◽

Protein Function ◽

Direct Sequencing ◽

Protein Structures ◽

Single Strand Conformation Polymorphism ◽

Extraction Methods ◽

World Health ◽

Transversion Mutation ◽

Health Organization

The NOP2/Sun domain family, member 7 (Nsun7) gene, which encodes putative methyltransferase Nsun7, has a role in sperm motility in mice. In humans, this gene is located on chromosome 4 with 12 exons. The aim of the present study was to investigate mutations of exon 7 in the normospermic and asthenospermic men. Semen samples were collected from the Fatemezahra IVF centre (Babol, Iran) and analysed on the basis of World Health Organization (WHO) guidelines using general phenol–chloroform DNA extraction methods. Exon 7 was amplified using Sun7-F and Sun7-R primers. Bands on samples from asthenospermic men that exhibited different patterns of movement on single-strand conformation polymorphism gels compared with normal samples were identified and subjected to sequencing for further identification of possible mutations. Direct sequencing of polymerase chain reaction (PCR) products, along with their analysis, confirmed C26232T-transition and T26248G-transversion mutations in asthenospermic men. Comparison of normal and mutant protein structures of Nsun7 indicated that the amino acid serine was converted to alanine, the structure of the helix, coil and strand was changed, and the protein folding and ligand binding sites were changed in samples from asthenospermic men with a transversion mutation in exon 7, indicating impairment of protein function. Because Nsun7 gene products have a role in sperm motility, if an impairment occurs in exon 7 of this gene, it may lead to infertility. The transversion mutation in exon 7 of the Nsun7 gene can be used as an infertility marker in asthenospermic men.

Download Full-text

Incidence of Infection and Mortality in Surgeries of Sports Injuries during COVID-19 Pandemic at GTTH, ahore, Pakistan

10.53350/pjmhs211581846 ◽

2021 ◽

Vol 15 (8) ◽

pp. 1846-1848

Author(s):

Sarmad Khalil ◽

Hizbullah Riaz Ansari ◽

Ali Ijaz Ahmad ◽

Abdullah Ali Mohammad Al-Hutam ◽

Majid Zaheer ◽

...

Keyword(s):

Sports Injuries ◽

Negative Impact ◽

Cruciate Ligament ◽

World Health ◽

X Rays ◽

Keywords Anterior Cruciate Ligament ◽

Anterior Cruciate ◽

Health Organization ◽

Keywords Anterior Cruciate ◽

Related Mortality

Aim: To find out if there was a negative impact or consequence of performing surgeries related to sports injuries during COVID-19 period when most of the hospital services were suspended all over the globe. Study design: Prospective study Place and duration of study: Department Orthopaedic and Spine, Ghurki Trust Teaching Hospital, Lahore from 19thMarch 2020 to 6thAugust 2020. Methodology: Seventy patients with sports injuries were enrolled. The history and thorough clinical examination, X-rays and CBC along with other relevant investigations were recorded. The patients were discharged in 24 to 74 hours period intervals and all the necessary SOPs regarding COVID-19 were strictly followed. Results: None of the patients who underwent procedure developed infection or acquired coronavirus illness after discharge from the hospital or during follow-ups in OPD. Conclusion: The surgeries performed during COVID-19 did not result in wound infection or patient-related mortality. Keywords: Anterior cruciate ligament (ACL), Arthroscopy, COVID-19, Pandemic, Posterior cruciate ligament (PCL), Sports injuries, Infection, World Health Organization (WHO)

Download Full-text

Comparative Analysis of Convolutional Neural Networks Applied in the Detection of Pneumonia Through X-Ray Images of Children

Learning and Nonlinear Models ◽

10.21528/lnlm-vol18-no2-art1 ◽

2021 ◽

Vol 18 (2) ◽

pp. 4-15

Author(s):

Luan Oliveira Silva ◽

◽

Leandro dos Santos Araújo ◽

Victor Ferreira Souza ◽

Raimundo Matos Barros Neto ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Standard Of Care ◽

Classification Problem ◽

World Health ◽

X Rays ◽

Medical Problems ◽

Learning Techniques ◽

Incidence And Mortality ◽

Health Organization

Pneumonia is one of the most common medical problems in clinical practice and is the leading fatal infectious disease worldwide. According to the World Health Organization, pneumonia kills about 2 million children under the age of 5 and is constantly estimated to be the leading cause of infant mortality, killing more children than AIDS, malaria, and measles combined. A key element in the diagnosis is radiographic data, as chest x-rays are routinely obtained as a standard of care and can aid to differentiate the types of pneumonia. However, a rapid radiological interpretation of images is not always available, particularly in places with few resources, where childhood pneumonia has the highest incidence and mortality rates. As an alternative, the application of deep learning techniques for the classification of medical images has grown considerably in recent years. This study presents five implementations of convolutional neural networks (CNNs): ResNet50, VGG-16, InceptionV3, InceptionResNetV2, and ResNeXt50. To support the diagnosis of the disease, these CNNs were applied to solve the classification problem of medical radiographs from people with pneumonia. InceptionResNetV2 obtained the best recall and precision results for the Normal and Pneumonia classes, 93.95% and 97.52% respectively. ResNeXt50 achieved the best precision and f1-score results for the Normal class (94.62% and 94.25% respectively) and the recall and f1-score results for the Pneumonia class (97.80% and 97.65%, respectively).

Download Full-text

Dosimetry and Calorimetry Performance of a Scientific CMOS Camera for Environmental Monitoring

Sensors ◽

10.3390/s20205746 ◽

2020 ◽

Vol 20 (20) ◽

pp. 5746

Author(s):

Alexis Aguilar-Arevalo ◽

Xavier Bertou ◽

Carles Canet ◽

Miguel Angel Cruz-Pérez ◽

Alexander Deisting ◽

...

Keyword(s):

Drinking Water ◽

World Health ◽

X Rays ◽

Cmos Camera ◽

Silicon Sensors ◽

Cmos Sensor ◽

Detectable Rate ◽

Measured Efficiency ◽

Γ Rays ◽

Health Organization

This paper explores the prospect of CMOS devices to assay lead in drinking water, using calorimetry. Lead occurs together with traces of radioisotopes, e.g., 210Pb, producing γ-emissions with energies ranging from 10 keV to several 100 keV when they decay; this range is detectable in silicon sensors. In this paper we test a CMOS camera (Oxford Instruments Neo 5.5) for its general performance as a detector of X-rays and low energy γ-rays and assess its sensitivity relative to the World Health Organization upper limit on lead in drinking water. Energies from 6 keV to 60 keV are examined. The CMOS camera has a linear energy response over this range and its energy resolution is for the most part slightly better than 2%. The Neo sCMOS is not sensitive to X-rays with energies below ∼10 keV. The smallest detectable rate is 40±3mHz, corresponding to an incident activity on the chip of 7±4Bq. The estimation of the incident activity sensitivity from the detected activity relies on geometric acceptance and the measured efficiency vs. energy. We report the efficiency measurement, which is 0.08(2)% (0.0011(2)%) at 26.3keV (59.5keV). Taking calorimetric information into account we measure a minimal detectable rate of 4±1mHz (1.5±1mHz) for 26.3keV (59.5keV) γ-rays, which corresponds to an incident activity of 1.0±6Bq (57±33Bq). Toy Monte Carlo and Geant4 simulations agree with these results. These results show this CMOS sensor is well-suited as a γ- and X-ray detector with sensitivity at the few to 100 ppb level for 210Pb in a sample.

Download Full-text

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

International Journal of Advances in Intelligent Informatics ◽

10.26555/ijain.v7i1.577 ◽

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.

Download Full-text

A Deep Learning Approach to Detect COVID-19 Patients from Chest X-ray Images

AI ◽

10.3390/ai1030027 ◽

2020 ◽

Vol 1 (3) ◽

pp. 418-435

Author(s):

Khandaker Haque ◽

Ahmed Abdelgawad

Keyword(s):

Deep Learning ◽

World Health ◽

X Rays ◽

X Ray ◽

Global Pandemic ◽

Proposed Model ◽

Dental Diseases ◽

Chest X Ray ◽

Artery Disease ◽

Health Organization

Deep Learning has improved multi-fold in recent years and it has been playing a great role in image classification which also includes medical imaging. Convolutional Neural Networks (CNNs) have been performing well in detecting many diseases including coronary artery disease, malaria, Alzheimer’s disease, different dental diseases, and Parkinson’s disease. Like other cases, CNN has a substantial prospect in detecting COVID-19 patients with medical images like chest X-rays and CTs. Coronavirus or COVID-19 has been declared a global pandemic by the World Health Organization (WHO). As of 8 August 2020, the total COVID-19 confirmed cases are 19.18 M and deaths are 0.716 M worldwide. Detecting Coronavirus positive patients is very important in preventing the spread of this virus. On this conquest, a CNN model is proposed to detect COVID-19 patients from chest X-ray images. Two more CNN models with different number of convolution layers and three other models based on pretrained ResNet50, VGG-16 and VGG-19 are evaluated with comparative analytical analysis. All six models are trained and validated with Dataset 1 and Dataset 2. Dataset 1 has 201 normal and 201 COVID-19 chest X-rays whereas Dataset 2 is comparatively larger with 659 normal and 295 COVID-19 chest X-ray images. The proposed model performs with an accuracy of 98.3% and a precision of 96.72% with Dataset 2. This model gives the Receiver Operating Characteristic (ROC) curve area of 0.983 and F1-score of 98.3 with Dataset 2. Moreover, this work shows a comparative analysis of how change in convolutional layers and increase in dataset affect classifying performances.

Download Full-text

Thermogram Breast Cancer Detection: A Comparative Study of Two Machine Learning Techniques

Applied Sciences ◽

10.3390/app10020551 ◽

2020 ◽

Vol 10 (2) ◽

pp. 551 ◽

Cited By ~ 2

Author(s):

Fayez AlFayez ◽

Mohamed W. Abo El-Soud ◽

Tarek Gaber

Keyword(s):

Breast Cancer ◽

Feature Extraction ◽

Cancer Detection ◽

Survival Rates ◽

Histogram Equalization ◽

Breast Cancer Detection ◽

Machine Learning Techniques ◽

World Health ◽

The World ◽

Health Organization

Breast cancer is considered one of the major threats for women’s health all over the world. The World Health Organization (WHO) has reported that 1 in every 12 women could be subject to a breast abnormality during her lifetime. To increase survival rates, it is found that it is very effective to early detect breast cancer. Mammography-based breast cancer screening is the leading technology to achieve this aim. However, it still can not deal with patients with dense breast nor with tumor size less than 2 mm. Thermography-based breast cancer approach can address these problems. In this paper, a thermogram-based breast cancer detection approach is proposed. This approach consists of four phases: (1) Image Pre-processing using homomorphic filtering, top-hat transform and adaptive histogram equalization, (2) ROI Segmentation using binary masking and K-mean clustering, (3) feature extraction using signature boundary, and (4) classification in which two classifiers, Extreme Learning Machine (ELM) and Multilayer Perceptron (MLP), were used and compared. The proposed approach is evaluated using the public dataset, DMR-IR. Various experiment scenarios (e.g., integration between geometrical feature extraction, and textural features extraction) were designed and evaluated using different measurements (i.e., accuracy, sensitivity, and specificity). The results showed that ELM-based results were better than MLP-based ones with more than 19%.

Download Full-text

Commutability of the First World Health Organization International Standard for Human Cytomegalovirus

Journal of Clinical Microbiology ◽

10.1128/jcm.01495-15 ◽

2015 ◽

Vol 53 (10) ◽

pp. 3325-3333 ◽

Cited By ~ 60

Author(s):

R. T. Hayden ◽

J. Preiksaitis ◽

Y. Tong ◽

X. Pang ◽

Y. Sun ◽

...

Keyword(s):

Extraction Methods ◽

World Health ◽

Quantitative Detection ◽

Entire Group ◽

Acid Extraction ◽

International Standard ◽

Interlaboratory Variability ◽

Testing Center ◽

Health Organization ◽

Human Cmv

Quantitative detection of cytomegalovirus (CMV) DNA has become a standard part of care for many groups of immunocompromised patients; recent development of the first WHO international standard for human CMV DNA has raised hopes of reducing interlaboratory variability of results. Commutability of reference material has been shown to be necessary if such material is to reduce variability among laboratories. Here we evaluated the commutability of the WHO standard using 10 different real-time quantitative CMV PCR assays run by eight different laboratories. Test panels, including aliquots of 50 patient samples (40 positive samples and 10 negative samples) and lyophilized CMV standard, were run, with each testing center using its own quantitative calibrators, reagents, and nucleic acid extraction methods. Commutability was assessed both on a pairwise basis and over the entire group of assays, using linear regression and correspondence analyses. Commutability of the WHO material differed among the tests that were evaluated, and these differences appeared to vary depending on the method of statistical analysis used and the cohort of assays included in the analysis. Depending on the methodology used, the WHO material showed poor or absent commutability with up to 50% of assays. Determination of commutability may require a multifaceted approach; the lack of commutability seen when using the WHO standard with several of the assays here suggests that further work is needed to bring us toward true consensus.

Download Full-text

Study on Convolutional Neural Network to Detect COVID-19 from Chest X-Rays

Mathematical Problems in Engineering ◽

10.1155/2021/3366057 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Azher Uddin ◽

Bayazid Talukder ◽

Mohammad Monirujjaman Khan ◽

Atef Zaguia

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Close Contact ◽

World Health ◽

Contact Tracing ◽

X Rays ◽

Health Crisis ◽

Gastrointestinal Problems ◽

The World ◽

Health Organization

The world is facing a pandemic due to the coronavirus disease 2019 (COVID-19), named as per the World Health Organization. COVID-19 is caused by the virus called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which was initially discovered in late December 2019 in Wuhan, China. Later, the virus had spread throughout the world within a few months. COVID-19 has become a global health crisis because millions of people worldwide are affected by this fatal virus. Fever, dry cough, and gastrointestinal problems are the most common signs of COVID-19. The disease is highly contagious, and affected people can easily spread the virus to those with whom they have close contact. Thus, contact tracing is a suitable solution to prevent the virus from spreading. The method of identifying all persons with whom a COVID-19-affected patient has come into contact in the last 2 weeks is called contact tracing. This study presents an investigation of a convolutional neural network (CNN), which makes the test faster and more reliable, to detect COVID-19 from chest X-ray (CXR) images. Because there are many studies in this field, the designed model focuses on increasing the accuracy level and uses a transfer learning approach and a custom model. Pretrained deep CNN models, such as VGG16, InceptionV3, MobileNetV2, and ResNet50, have been used for deep feature extraction. The performance measurement in this study was based on classification accuracy. The results of this study indicate that deep learning can recognize SARS-CoV-2 from CXR images. The designed model provided 93% accuracy and 98% validation accuracy, and the pretrained customized models such as MobileNetV2 obtained 97% accuracy, InceptionV3 obtained 98%, and VGG16 obtained 98% accuracy, respectively. Among these models, InceptionV3 has recorded the highest accuracy.

Download Full-text

KAJIAN ANALISIS KETIDAKPASTIAN TLD POSTAL IAEA/WHO SEBAGAI STANDAR PROGRAM AUDIT DOSIS

Jurnal Standardisasi ◽

10.31153/js.v11i2.634 ◽

2009 ◽

Vol 11 (2) ◽

pp. 73

Author(s):

Nazaroh Nazaroh

Keyword(s):

Primary Standard ◽

High Energy ◽

Standard Uncertainty ◽

World Health ◽

Calibration Coefficient ◽

Reference Laboratory ◽

X Rays ◽

Energy Agency ◽

Relative Standard ◽

Health Organization

The International Atomic Energy Agency (IAEA) and World Health Organization (WHO) operate the IAEA/WHO TLD postal dose audit programme using thermoluminescence dosimeter (TLDs) for Secondary Standard Dosimetry Laboratory (SSDL) and user every year. As National Reference Laboratory in the field of radiation metrology, PTKMR – BATAN always participates in the postal dose audit programme on therapy level for 60Co beam. On the postal dose audit programme, the uncertainties in the dose determination from TLD measurements have been evaluated by IAEA, which is comprises of uncertainties in the calibration coefficient of the TLD system and uncertainties in factors correcting for dose response non linearity, fading of TL signal, energy response, and influence of TLD holder. The individual uncertainties then have been combined to estimate the total uncertaintiy in the dose evaluated from TLD measurements. The combined relative standard uncertainty in the dose determined from TLD measurements has been estimated to be 1.2% for irradiation with 60Co gamma rays and 1.6% for irradiation with high-energy X-rays. Results from irradiations by Bureau Internationale des Poids et Mesures (BIPM), Primary Standard Dosimetry Laboratory (PSDL), and SSDL compare favourably with the estimated uncertainties, whereas TLD results of radiotherapy centres show higher standard deviations than those derived theoretically. This paper presented the result of TLD postal dose audit for 60Co beam owned by PTKMR-BATAN in the year of 2006-2008.

Download Full-text