scholarly journals Detection of COVID-19 from Chest CT Images Using CNN with MLP Hybrid Model

2021 ◽  
Author(s):  
Sakthi Jaya Sundar Rajasekar ◽  
Vasumathi Narayanan ◽  
Varalakshmi Perumal
Keyword(s):  
Ct Scan ◽  
Intelligent System ◽  
Hybrid Learning ◽  
Laboratory Equipment ◽  
Gold Standard Method ◽  
Negative Results ◽  
Global Health Care ◽  
Trained Manpower ◽  
Mlp Model ◽  
Health Care Centers

COVID-19 when left undetected can lead to a hazardous infection spread, leading to an unfortunate loss of life. It’s of utmost importance to diagnose COVID-19 in Infected patients at the earliest, to avoid further complications. RT-PCR, the gold standard method is routinely used for the diagnosis of COVID-19 infection. Yet, this method comes along with few limitations such as its time-consuming nature, a scarcity of trained manpower, sophisticated laboratory equipment and the possibility of false positive and negative results. Physicians and global health care centers use CT scan as an alternate for the diagnosis of COVID-19. But this process of detection too, might demand more manual work, effort and time. Thus, automating the detection of COVID-19 using an intelligent system has been a recent research topic, in the view of pandemic. This will also help in saving the physician’s time for carrying out further treatment. In this paper, a hybrid learning model has been proposed to identify the COVID-19 infection using CT scan images. The Convolutional Neural Network (CNN) was used for feature extraction and Multilayer Perceptron was used for classification. This hybrid learning model’s results were also compared with traditional CNN and MLP models in terms of Accuracy, F1-Score, Precision and Recall. This Hybrid CNN-MLP model showed an Accuracy of 94.89% when compared with CNN and MLP giving 86.95% and 80.77% respectively.

COVID-19: how nuclear medicine can provide a differential diagnosis in very dubious case

Coronaviruses ◽  
2020 ◽  
Vol 01 ◽  
Author(s):  
Maria Silvia De Feo ◽  
Viviana Frantellizzi ◽  
Giuseppe De Vincentis
Keyword(s):  
Infectious Disease ◽  
Differential Diagnosis ◽  
Ct Scan ◽  
Imaging Technique ◽  
False Negative ◽  
Clinical Signs ◽  
Negative Results ◽  
Infectious Disease Department ◽  
False Negative Results ◽  
99Mtc Hmpao

Background: We present the case of a 55-year-old woman, admitted to the Infectious Disease Department of Policlinico Umberto I, Rome, in mid-March 2020, with suspicion of COVID-19 infection. Objective: The rRT-PCR was negative and the following CT scan, performed to exclude false-negative results and help diagnosis, was inconclusive. Methods: It was decided to submit the patient to 99mTc-HMPAO-labelled leukocyte scan. Results: This exam led to the diagnosis of infective endocarditis. Conclusion: In the present pandemic scenario, 99mTc-HMPAO-labelled leukocyte scan represents a reliable imaging technique for differential diagnosis with COVID-19 in patients with confusing clinical signs, possible false-negative rRT-PCR results and inconclusive CT scan.

scholarly journals A Comparative Study of Clinical vs. Digital Exophthalmometry Measurement Methods

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Tháıs de Sous Pereira ◽  
Cristina Hiromi Kuniyoshi ◽  
Cristiane de Almeida Leite ◽  
Eloisa M. M. S. Gebrim ◽  
Mário L. R. Monteiro ◽  
...  
Keyword(s):  
Ct Scan ◽  
Pearson Correlation ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Measurement Methods ◽  
Gold Standard Method ◽  
Mean Values ◽  
Ct Measurements ◽  
Mean Differences ◽  
No Gold Standard

Background. A number of orbital diseases may be evaluated based on the degree of exophthalmos, but there is still no gold standard method for the measurement of this parameter. In this study we compare two exophthalmometry measurement methods (digital photography and clinical) with regard to reproducibility and the level of correlation and agreement with measurements obtained with Computerized Tomography (CT) measurements. Methods. Seventeen patients with bilateral proptosis and 15 patients with normal orbits diseases were enrolled. Patients underwent orbital CT, Hertel exophthalmometry (HE) and standardized frontal and side facial photographs by a single trained photographer. Exophthalmometry measurements with HE, the digital photographs and axial CT scans were obtained twice by the same examiner and once by another examiner. Pearson correlation coefficient (PCC) was used to assess correlations between methods. Validity between methods was assessed by mean differences, interintraclass correlation coefficients (ICC’s), and Bland–Altman plots. Results. Mean values were significantly higher in the proptosis group (34 orbits) than in the normal group (30 orbits), regardless of the method. Within each group, mean digital exophthalmometry measurements (24.32 ± 5.17 mm and 18.62 ± 3.87 mm) were significantly greater than HE measurements (20.87 ± 2.53 mm and 17.52 ± 2.67 mm) with broader range of standard deviation. Inter-/intraclass correlation coefficients were 0.95/0.93 for clinical, 0.92/0.74 for digital, and 0.91/0.95 for CT measurements. Correlation coefficients between HE and CT scan measurements in both groups of subjects (r = 0.84 and r = 0.91, p<0.05) were greater than those between digital and CT scan measurements (r = 0.61 and r = 0.75, p<0.05). On the Bland–Altman plots, HE showed better agreement to CT measurements compared to the digital photograph method in both groups studied. Conclusions. Although photographic digital exophthalmometry showed strong correlation and agreement with CT scan measurements, it still performs worse than and is not as accurate as clinical Hertel exophthalmometry. This trail is registered with NCT01999790.

scholarly journals Evaluation of the Accuracy of Panoramic Radiograph in the Definition of Maxillary Sinus Septa

2002 ◽  
Vol 45 (4) ◽  
pp. 173-175 ◽  
Author(s):  
Samer Kasabah ◽  
Radovan Slezák ◽  
Antonín Šimůnek ◽  
Jiří Krug ◽  
Miguel Cevallos Lecaro
Keyword(s):  
Ct Scan ◽  
Maxillary Sinus ◽  
Panoramic Radiography ◽  
Panoramic Radiograph ◽  
The Other ◽  
Negative Results ◽  
Other Hand ◽  
Maxillary Sinus Septa ◽  
False Diagnosis ◽  
Definition Of

The purpose of this study was to determine the accuracy of panoramic radiography in identification of maxillary sinus septa. Out of 68 sinuses were radiographically examined using both panoramic and computerized tomographic radiographs (CT scan). Using CT scan, 24 (35.9 %) out of 68 cases maxillae showed at least one septum, 22 sinuses (32.3 %) showed one septum, whereas two sinuses (2.9 %) exhibited two septa. Panoramic radiograph led to a false diagnosis regarding the presence or absence of sinus septa in 18 of 68 sinuses (26.5 %). On the other hand, they gave negative diagnosis of sinus septa in 12 of 24 septa (50 %). There was fully agreement between the two methods (positive septa) only in 12 of 24 septa (50 %). We cannot depend on panoramic radiograph for the detection of sinus septa because it can lead to false or negative results.

scholarly journals COVID-19 pneumonia: a pictorial review of CT findings and differential diagnosis

2021 ◽  
Vol 52 (1) ◽  
Author(s):  
Fattane Shirani ◽  
Azin Shayganfar ◽  
Somayeh Hajiahmadi
Keyword(s):  
Differential Diagnosis ◽  
Ct Scan ◽  
Screening Tool ◽  
False Negative ◽  
Imaging Findings ◽  
Rt Pcr ◽  
Negative Results ◽  
Ct Findings ◽  
Pictorial Review ◽  
False Negative Results

Abstract Background The gold standard for verifying COVID-19 mostly depends on microbiological tests like real-time polymerase chain reaction (RT-PCR). However, the availability of RT-PCR kits can be known as a problem and false negative results may be encountered. Although CT scan is not a screening tool for the diagnosis of COVID-19 pneumonia, given the widespread acquisition of it in the pandemic state, familiarity with different CT findings and possible differential diagnosis is essential in this regard. Main text In this review, we introduced the typical and atypical CT features of COVID-19 pneumonia, and discussed the main differential diagnosis of COVID-19 pneumonia. Conclusions The imaging findings in this viral pneumonia showed a broad spectrum, and there are no pathognomonic imaging findings for COVID-19 pneumonia. Although CT scan is not a diagnostic and screening tool, familiarity with different imaging findings and their differential diagnosis can be helpful in a rapid and accurate decision-making.

COVID-19 Detection on Chest X-Ray and CT Scan Images Using Multi-image Augmented Deep Learning Model

2020 ◽  
Author(s):  
Kiran Purohit ◽  
Abhishek Kesarwani ◽  
Dakshina Ranjan Kisku ◽  
Mamata Dalui
Keyword(s):  
Ct Scan ◽  
False Negative ◽  
Radical Change ◽  
Testing Time ◽  
Rt Pcr ◽  
X Ray ◽  
Negative Results ◽  
False Negative Results ◽  
Chest X Ray ◽  
Coronavirus Infection

AbstractCOVID-19 is posed as very infectious and deadly pneumonia type disease until recent time. Despite having lengthy testing time, RT-PCR is a proven testing methodology to detect coronavirus infection. Sometimes, it might give more false positive and false negative results than the desired rates. Therefore, to assist the traditional RT-PCR methodology for accurate clinical diagnosis, COVID-19 screening can be adopted with X-Ray and CT scan images of lung of an individual. This image based diagnosis will bring radical change in detecting coronavirus infection in human body with ease and having zero or near to zero false positives and false negatives rates. This paper reports a convolutional neural network (CNN) based multi-image augmentation technique for detecting COVID-19 in chest X-Ray and chest CT scan images of coronavirus suspected individuals. Multi-image augmentation makes use of discontinuity information obtained in the filtered images for increasing the number of effective examples for training the CNN model. With this approach, the proposed model exhibits higher classification accuracy around 95.38% and 98.97% for CT scan and X-Ray images respectively. CT scan images with multi-image augmentation achieves sensitivity of 94.78% and specificity of 95.98%, whereas X-Ray images with multi-image augmentation achieves sensitivity of 99.07% and specificity of 98.88%. Evaluation has been done on publicly available databases containing both chest X-Ray and CT scan images and the experimental results are also compared with ResNet-50 and VGG-16 models.

scholarly journals Os odontoideum: a rare cause of syncope

2019 ◽  
Vol 12 (11) ◽  
pp. e230945
Author(s):  
Christopher Shane Buntting ◽  
Ashraf Dower ◽  
Haider Seghol ◽  
Saeed Kohan
Keyword(s):  
Emergency Department ◽  
Ct Scan ◽  
Dynamic Instability ◽  
Vasovagal Syncope ◽  
Arterial Disease ◽  
Arterial System ◽  
Os Odontoideum ◽  
Lateral Mass ◽  
Negative Results ◽  
Neurological Pathology

Syncopal events are a concerning presentation and timely evaluation is warranted. Common aetiologies include cardiac and neurological pathology such as arrhythmias, vertebrobasilar arterial disease and vasovagal syncope. We describe the case of a 65-year-old man who presented to our emergency department with symptoms of vertigo and syncope. He was investigated extensively for both cardiac and neurological causes of his symptoms which returned negative results. An outpatient CT scan demonstrated the presence of Os odontoideum and dynamic instability of the atlantoaxial junction, with presumed dynamic obstruction of the vertebral arterial system. This was successfully managed with a posterior atlantoaxial lateral mass fusion with resolution of syncopal symptoms.

scholarly journals Traumatic Intraparenchymal Pseudoaneurysm on Initial Imaging Predicts Injury Progression in Patients with Nonoperative Major Blunt Liver Injury

2017 ◽  
Author(s):  
Duraid Younan ◽  
T. Mark Beasley ◽  
Andrew Papoy ◽  
Geoffrey Douglas ◽  
Patrick Bosarge
Keyword(s):  
Liver Injury ◽  
Ct Scan ◽  
Management Plan ◽  
Liver Trauma ◽  
Imaging Data ◽  
Blunt Liver Injury ◽  
Negative Results ◽  
Liver Injuries ◽  
Injury Progression ◽  
Repeat Imaging

Abstract Objective: Identify factors that would predict which patients would benefit from repeat imaging after major blunt liver injury. Summary of Background Data: Most patients who present with hemodynamic stability and no evidence of peritonitis after blunt liver injury are successfully managed nonoperatively. Little information is available regarding the utility of reimaging major blunt liver injuries for patients who are managed nonoperatively. Methods: A retrospective review of patients admitted to a level I trauma center with major blunt liver injuries (AAST grades 3-5) was conducted. Inclusion criteria were those admitted from July 2012 to June 2014 with blunt liver trauma who survived the first 24 hours and underwent repeat imaging. Data included demographics, procedures performed and computerized tomography (CT) scan findings. Findings on the second CT scan were categorized as Unchanged, Worse, Improved, or Negative. Results: 128 patients had blunt major liver injuries; 66 patients underwent repeat imaging. The mean time to repeat CT was 1.95 days. On repeat CT 47 were "Unchanged", 3 "Worse", 14 "Improved" and 2 "Negative". Three patients underwent angiography. One required embolization of a pseudoaneurysm. In 63 patients (95%), the second CT did not change the management plan. The presence of a pseudoaneurysm was significantly related to a worsening of the second CT (p=0.0475). Patients with admission hematocrit (Hct) below 32% were more likely to have a worsened second CT (p=0.0370). Conclusions: A pseudoaneurysm on admission CT and Hct &lt;32% predict major liver injury progression suggesting that routine reimaging is warranted in this group.

scholarly journals False-negative Molecular Diagnosis of SARS-CoV-2 in Samples with Amplification Inhibitors

2020 ◽  
Author(s):  
Marcelo Fruehwirth ◽  
Açucena Veleh Rivas ◽  
Andressa Faria Rahyn Fitz ◽  
Aline Cristiane Cechinel Assing Batista ◽  
Cleypson Vinicius Silveira ◽  
...  
Keyword(s):  
Internal Control ◽  
False Negative ◽  
Rna Extraction ◽  
N Gene ◽  
Gold Standard Method ◽  
Negative Results ◽  
False Negative Results ◽  
Average Variation ◽  
Wrong Diagnosis ◽  
Inhibitor Compounds

Although rRT-PCR is the gold standard method for SARS-CoV-2 detection, some factors, such as amplification inhibitors presence, lead to false-negative results. Here we describe differences between rRT-PCR results for SARS-CoV-2 infection in normal and diluted samples, simulating the need for dilution due to amplification inhibitors presence. Viral RNA extraction of nasopharyngeal swabs samples from 20 patients previously detected as 'Negative' and 21 patients detected as 'Positive' for SARS-CoV-2 was realized with the EasyExtract DNA-RNA (Interprise&reg;). rRT-PCR was realized with OneStep/COVID-19 (IBMP) kit with normal and diluted (80&micro;l of H₂O RNAse free) samples, totaling 82 tests. The results indicate that there is an average variation (ɑ &lt; 0.05) delaying Cq between the amplification results of internal control (IC), N Gene (NG), and ORF-1ab (OF) of 1.811 Cq, 3.840 Cq, and 3.842 Cq, respectively. The extraction kit does not completely purify the inhibitor compounds, therefore non-amplification by inhibitors may occur. In this study, we obtained a 19.04% false-negative diagnosis after sample dilution, and this process reduces the efficiency of rRT-PCR to 29.80% for detecting SARS-CoV-2. Knowing the rRT-PCR standards of diluted samples can help in the identification of false-negative cases, and consequently avoid a wrong diagnosis.

scholarly journals Neutrophil-to-lymphocyte ratio (NLR) greater than 6.5 may reflect the progression of COVID-19 towards an unfavorable clinical outcome

2020 ◽  
Author(s):  
Ali Pirsalehi ◽  
Sina Salari ◽  
Ahmadreza Baghestani ◽  
Mohammad Vahidi ◽  
Laya Jalilian Khave ◽  
...  
Keyword(s):  
Intensive Care ◽  
Clinical Outcome ◽  
False Negative ◽  
Neutrophil To Lymphocyte Ratio ◽  
Molecular Testing ◽  
Gold Standard Method ◽  
Lymphocyte Ratio ◽  
Negative Results ◽  
Short Period ◽  
Unfavorable Clinical Outcome

Background and Objectives: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which was first described during a pneumonia outbreak in Wuhan, has attracted tremendous attention in a short period of time as the death toll and the number of confirmed cases is growing unceasingly. Although molecular testing is the gold standard method of SARS-CoV-2 detection, the existence of the false-negative results presents a major limitation to this method. Materials and Methods: This retrospective Double-Centre study was conducted on 1320 COVID-19 patients recruited at Taleghani and Shohadae Tajrish Hospitals in Tehran, Iran. We analyzed the leukocyte, lymphocyte and neutrophil counts of hospitalized cases both on admission and at discharge. We also evaluated the alteration of these parameters within a seven-day follow-up. Results: Of the whole, 1077 (81.6%) neither were admitted to intensive care unit (ICU) nor experienced death, and were defined as the mild-moderate group. Of 243 severe cases, while 59 (24.3%) were admitted to ICU and cured with the intensive care services, 184 (75.7%) patients died of the disease, either with or without ICU admission. Calculation of neutrophil-to-lymphocyte ratio (NLR) revealed that the mild-moderate cases had a lower ratio at discharge. On the other hand, the ratio was significantly higher in the death group as compared to the ICU group; highlighting the fact that patients with a higher degree of neutrophilia and a greater level of lymphopenia have a poor prognosis. Conclusion: We suggest that NLR greater than 6.5 may reflect the progression of the disease towards an unfavorable clinical outcome, with this notion that the ratios higher than 9 may strongly result in death.

scholarly journals Intelligent System to Find the Health Care Centers for Senior Citizens Based on Disease and Nearest Locations using GPS

2021 ◽  
Vol 12 (2) ◽  
Author(s):  
Gurram Sunitha, Et. al.
Keyword(s):  
Health Care ◽  
Intelligent System ◽  
Senior Citizens ◽  
Smart Phone ◽  
Smart Phones ◽  
Care Centre ◽  
Health Care Centre ◽  
Emergency Responders ◽  
Care Facilities ◽  
Health Care Centers

It is not convenient nowadays for senior citizens to find an accessible and appropriate health care centre that can meet their needs. Therefore, this initiative helps senior citizens to look for a suitable facility depending on their location and their current illness. The scheme is simple and easily produces results. By using GPS feature or Internet network by using position coordinates and pre-built coordinate databases of nursing care facilities, the details of the nearest facility can be obtained along with the name of the location and buildings with smart phones. The software also provides a tracking service for consumers (senior citizens) so that, by forming a technical relationship with medical centres, it can offer a range of high-quality facilities. The contribution of this system is that through the O2O service, emergency responders can intelligently find a correct hospital that can treat the illness or accident of patients with a smart phone.

Sign in / Sign up

Export Citation Format

Share Document