scholarly journals XCOVNet: Chest X-ray Image Classification for COVID-19 Early Detection Using Convolutional Neural Networks

2021 ◽  
Author(s):  
Vishu Madaan ◽  
Aditya Roy ◽  
Charu Gupta ◽  
Prateek Agrawal ◽  
Anand Sharma ◽  
...  
Keyword(s):  
Image Classification ◽  
Second Phase ◽  
Two Phase ◽  
X Ray ◽  
The Neural Network ◽  
Rapid Spread ◽  
Chest X Ray ◽  
Polymerase Chain ◽  
Two Phases ◽  
Active Patients

AbstractCOVID-19 (also known as SARS-COV-2) pandemic has spread in the entire world. It is a contagious disease that easily spreads from one person in direct contact to another, classified by experts in five categories: asymptomatic, mild, moderate, severe, and critical. Already more than 66 million people got infected worldwide with more than 22 million active patients as of 5 December 2020 and the rate is accelerating. More than 1.5 million patients (approximately 2.5% of total reported cases) across the world lost their life. In many places, the COVID-19 detection takes place through reverse transcription polymerase chain reaction (RT-PCR) tests which may take longer than 48 h. This is one major reason of its severity and rapid spread. We propose in this paper a two-phase X-ray image classification called XCOVNet for early COVID-19 detection using convolutional neural Networks model. XCOVNet detects COVID-19 infections in chest X-ray patient images in two phases. The first phase pre-processes a dataset of 392 chest X-ray images of which half are COVID-19 positive and half are negative. The second phase trains and tunes the neural network model to achieve a 98.44% accuracy in patient classification.

Chest X-Ray Image Classification on Common Thorax Diseases using GLCM and AlexNet Deep Features

2019 ◽  
Vol 11 (4) ◽  
Author(s):  
Tengku Afiah Mardhiah Tengku Zainul Akmal ◽  
Joel Chia Ming Than ◽  
Haslailee Abdullah ◽  
Norliza Mohd Noor
Keyword(s):  
Image Classification ◽  
X Ray ◽  
Chest X Ray

scholarly journals Machine learning applied on chest x-ray can aid in the diagnosis of COVID-19: a first experience from Lombardy, Italy

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Isabella Castiglioni ◽  
Davide Ippolito ◽  
Matteo Interlenghi ◽  
Caterina Beatrice Monti ◽  
Christian Salvatore ◽  
...  
Keyword(s):  
Deep Learning ◽  
Area Under The Curve ◽  
Clinical Information ◽  
Training Dataset ◽  
Independent Dataset ◽  
X Ray ◽  
Learning Classifier ◽  
Chest X Ray ◽  
Polymerase Chain ◽  
Deep Learning Model

Abstract Background We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. Methods We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. Results At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74–0.81), 0.82 specificity (95% CI 0.78–0.85), and 0.89 area under the curve (AUC) (95% CI 0.86–0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72–0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73–0.87), and 0.81 AUC (95% CI 0.73–0.87). Radiologists’ reading obtained 0.63 sensitivity (95% CI 0.52–0.74) and 0.78 specificity (95% CI 0.61–0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52–0.74) and 0.86 specificity (95% CI 0.71–0.95) in Centre 2. Conclusions This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.

Nanostructured TiO2-Based Composites for Light Absorption

2014 ◽  
Vol 975 ◽  
pp. 207-212
Author(s):  
Dayse I. dos Santos ◽  
Olayr Modesto Jr. ◽  
Luis Vicente A. Scalvi ◽  
Americo S. Tabata
Keyword(s):  
Metal Oxide ◽  
Light Absorption ◽  
Structural Characteristics ◽  
Sol Gel ◽  
Second Phase ◽  
X Ray Diffraction ◽  
Two Phase ◽  
X Ray ◽  
Oxide Powders

Metal oxide nanocomposites were prepared by two different routes: polyol and sol-gel. Characterization by X ray diffraction showed that the first process produces directly a two-phase material, while the sol-gel powder never showed second phase below 600°C. Light spectroscopy of the treated powders indicated similarities for the processed materials. Although the overall material compositions are about the same, different structural characteristics are found for each processing. With the exception of Ti-Zn materials, all the double metal oxide powders showed higher absorbance than either TiO2 powder.

scholarly journals Hoarseness of Voice as a Rare Presentation of Tuberculosis: A Case Report Study

2019 ◽  
Vol 7 (19) ◽  
pp. 3262-3264
Author(s):  
Taher Felemban ◽  
Abdullah Ashi ◽  
Abdullah Sindi ◽  
Mohannad Rajab ◽  
Zuhair Al Jehani
Keyword(s):  
Laryngeal Carcinoma ◽  
Incidental Finding ◽  
Chain Reaction ◽  
Rare Presentation ◽  
Case Presentation ◽  
X Ray ◽  
History Of ◽  
Chest X Ray ◽  
Polymerase Chain ◽  
Laryngeal Tuberculosis

BACKGROUND: Having hoarseness of voice as the first clinical manifestation of tuberculosis is rare. This atypical presentation causes some confusion since other more common conditions, such as laryngeal carcinoma, present similarly and might require more invasive tests to confirm the diagnosis. CASE PRESENTATION: A 38-year-old male presented to the otorhinolaryngology clinic with a four-month history of change in voice. Laryngoscopy demonstrated a right glottic mass, raising suspicion of laryngeal cancer. The computed tomography showed a mass and incidental finding of opacities in lung apices. Chest x-ray demonstrated findings suggestive of tuberculosis. Polymerase chain reaction and culture of sputum samples confirmed the diagnosis and the patient was started on anti-tuberculosis treatment. CONCLUSION: Despite accounting for only 1% of pulmonary tuberculosis cases and having a similar presentation to laryngeal carcinoma, we recommend considering laryngeal tuberculosis when evaluating hoarseness of voice in endemic areas.

scholarly journals Chest CT as a Complement to RT-PCR to Confirm and Follow-up COVID-19 Patients

Medicinus ◽  
2021 ◽  
Vol 8 (1) ◽  
pp. 31
Author(s):  
Aziza Ghanie Icksan ◽  
Muhammad Hafiz ◽  
Annisa Dian Harlivasari
Keyword(s):  
Chest Ct ◽  
Rt Pcr ◽  
High Resolution Computed Tomography ◽  
X Ray ◽  
First Case ◽  
Chest X Ray ◽  
Polymerase Chain

<p><strong>Background : </strong>The first case of COVID-19 in Indonesia was recorded in March 2020. Limitation of reverse-transcription polymerase chain reaction (RT-PCR) has put chest CT as an essential complementary tool in the diagnosis and follow up treatment for COVID-19. Literatures strongly suggested that High-Resolution Computed Tomography (HRCT) is essential in diagnosing typical symptoms of COVID-19 at the early phase of disease due to its superior sensitivity  (97%) compared to chest x-ray (CXR).</p><p>The two cases presented in this case study showed the crucial role of chest CT with HRCT to establish the working diagnosis and follow up COVID-19 patients as a complement to RT-PCR, currently deemed a gold standard.<strong></strong></p>

X-Ray Studies on the Formation of Basic Lead Azides

1961 ◽  
Vol 5 ◽  
pp. 127-132
Author(s):  
Bruno Reitzner ◽  
James E. Abel
Keyword(s):  
Lead Oxide ◽  
Lead Azide ◽  
Second Phase ◽  
X Ray ◽  
Molar Ratios ◽  
Two Phases

AbstractThe reaction between solid lead azide and lead oxide at different molar ratios yields two phases of basic lead azide of the type xPb(N3)2·yPbO with different azide content. The first phase was identified as xPb(N3)2·PbO, investigation of the second phase is still under way. The results up to the present time suggest that the formula for this phase is between Pb(N3)2·2PbO and Pb(N3)2·3PbO, probably 2Pb(N3)2·5PbO. The reaction is catalyzed by traces of water. The formulas of the two lead azide phases are established by X-ray analysts. The phases are identical with those found previously when lead azide was thermally decomposed in atmospheres containing water.

scholarly journals COVID-XNet: A Custom Deep Learning System to Diagnose and Locate COVID-19 in Chest X-ray Images

2020 ◽  
Vol 10 (16) ◽  
pp. 5683 ◽  
Author(s):  
Lourdes Duran-Lopez ◽  
Juan Pedro Dominguez-Morales ◽  
Jesús Corral-Jaime ◽  
Saturnino Vicente-Diaz ◽  
Alejandro Linares-Barranco
Keyword(s):  
Deep Learning ◽  
Imaging Techniques ◽  
Learning System ◽  
Screening Process ◽  
X Ray ◽  
Average Accuracy ◽  
Rapid Spread ◽  
Chest X Ray ◽  
And Control ◽  
Aided Diagnosis

The COVID-19 pandemic caused by the new coronavirus SARS-CoV-2 has changed the world as we know it. An early diagnosis is crucial in order to prevent new outbreaks and control its rapid spread. Medical imaging techniques, such as X-ray or chest computed tomography, are commonly used for this purpose due to their reliability for COVID-19 diagnosis. Computer-aided diagnosis systems could play an essential role in aiding radiologists in the screening process. In this work, a novel Deep Learning-based system, called COVID-XNet, is presented for COVID-19 diagnosis in chest X-ray images. The proposed system performs a set of preprocessing algorithms to the input images for variability reduction and contrast enhancement, which are then fed to a custom Convolutional Neural Network in order to extract relevant features and perform the classification between COVID-19 and normal cases. The system is trained and validated using a 5-fold cross-validation scheme, achieving an average accuracy of 94.43% and an AUC of 0.988. The output of the system can be visualized using Class Activation Maps, highlighting the main findings for COVID-19 in X-ray images. These promising results indicate that COVID-XNet could be used as a tool to aid radiologists and contribute to the fight against COVID-19.

Two-Phase Structure of Fluorinated Powdered Silica Resulting from Deep Processing of Rice Wastes

2018 ◽  
Vol 7 (1) ◽  
pp. 38-44 ◽  
Author(s):  
А. Рашковский ◽  
A. Rashkovskiy ◽  
Е. Политова ◽  
E. Politova ◽  
А. Меркушкин ◽  
...  
Keyword(s):  
Photoelectron Spectroscopy ◽  
Inductively Coupled Plasma ◽  
Physicochemical Analysis ◽  
Nano Particles ◽  
Deep Processing ◽  
X Ray Diffraction ◽  
Two Phase ◽  
X Ray ◽  
Inductively Coupled ◽  
Two Phases

In this investigation the structure of «green» silica maid with rice husk has been studied by methods of physicochemical analysis. By method of X-ray diffraction it has been found that the samples of «green» silica powders are completely amorphous, and the observed amorphous halo consists of two components. By method of scanning electron microscopy it has been revealed that nano-particles of «green» SiO2 can form agglomerates and microstructures with dimensions from 0,1 to 500 microns, containing numerous pores, which presence has been confirmed by sorption measurements. By method of mass spectrometry with inductively coupled plasma has been found the presence of aluminum, titanium and nickel mechanical impurities in the «green» SiO2 powders. By method of X-ray photoelectron spectroscopy significant amount of fluorine atoms in «green» silica (up to 5% (at.)) has been revealed, which could be introduced in SiO2 in the process of its preparation. In such a case, it was found that fluorine interacts with «green» silica by means of two mechanisms, leading to appearance of two phases within fluorinated powders of «green» SiO2.

Anomalous phase composition in the two-phase region of DyFe3−xAlx (x≤1.0)

2010 ◽  
Vol 25 (4) ◽  
pp. 349-354 ◽  
Author(s):  
Y. Q. Chen ◽  
J. K. Liang ◽  
J. Luo ◽  
J. B. Li ◽  
G. H. Rao
Keyword(s):  
Phase Region ◽  
Hexagonal Structure ◽  
Unit Cell Parameters ◽  
Two Phase ◽  
Space Group ◽  
X Ray ◽  
Cell Parameters ◽  
Two Phases ◽  
Xrd Patterns ◽  
Phase Relationships

The structure transitions and phase relationships of DyFe3−xAlx compounds have been investigated by X-ray powder diffraction. Our XRD results show that each of the compounds with x≤0.45 crystallizes in the rhombohedral PuNi3-type structure with space group R3¯m and Z=9; for the 0.8≤x<1.0 compounds, each has a hexagonal structure of the CeNi3 type with space group P63/mmc and Z=6; and each of the samples with 0.45<x<0.8 is a two-phase mixture of the PuNi3- and CeNi3-type structures. The calculated XRD intensities of the DyFe3−xAlx compounds with x=0.2, 0.33, 0.4, and 0.45 indicate that Dy occupies the 3a and 6c sites, Fe and Al distribute randomly on the 18h site, and the 3b and 6c sites are exclusively occupied by Fe, which agrees well with those of our experimental XRD patterns. The XRD intensities of the DyFe3−xAlx compounds with x=0.8 and 1.0 have also been calculated and found to agree with the experimental results with Dy on the 2c and 4f sites, Fe and Al at the 12k site, and Fe at the 2a, 2b, and 2d sites. In the two-phase region with x=0.45–0.8, the values of unit-cell parameters and phase compositions are linearly dependent on the value of x, indicating that the two phases are constituted by the same composition x with different stacking arrangements. This abnormal two-phase equilibrium is further confirmed by the structural analysis of the DyFe2.33Al0.67 (or x=0.67) sample. The samples with x=1.1 and 1.2 were also analyzed, and each found to be a mixture of more than two phases.

Sign in / Sign up

Export Citation Format

Share Document