scholarly journals Detection of COVID-19 from Chest X-ray and CT Scan Images using Improved Stacked Sparse Autoencoder

2021 ◽  
Vol 29 (3) ◽  
Author(s):  
Syahril Ramadhan Saufi ◽  
Muhd Danial Abu Hasan ◽  
Zair Asrar Ahmad ◽  
Mohd Salman Leong ◽  
Lim Meng Hee
Keyword(s):  
Ct Scan ◽  
The Novel ◽  
Essential Information ◽  
X Ray ◽  
Chest X Ray ◽  
Sparse Autoencoder ◽  
Stacked Sparse Autoencoder ◽  
Novel Coronavirus ◽  
Deep Learning Model ◽  
Chest Ct Scan

The novel Coronavirus 2019 (COVID-19) has spread rapidly and has become a pandemic around the world. So far, about 44 million cases have been registered, causing more than one million deaths worldwide. COVID-19 has had a devastating impact on every nation, particularly the economic sector. To identify the infected human being and prevent the virus from spreading further, easy, and precise screening is required. COVID-19 can be potentially detected by using Chest X-ray and computed tomography (CT) images, as these images contain essential information of lung infection. This radiology image is usually examined by the expert to detect the presence of COVID-19 symptom. In this study, the improved stacked sparse autoencoder is used to examine the radiology images. According to the result, the proposed deep learning model was able to achieve a classification accuracy of 96.6% and 83.0% for chest X-ray and chest CT-scan images, respectively.

scholarly journals (F)utility of computed tomography of the chest in the presence of pleural effusion

2017 ◽  
Vol 2 (4) ◽  
pp. 181-186 ◽  
Author(s):  
Tilak Pathak ◽  
Malvinder S. Parmar
Keyword(s):  
Computed Tomography ◽  
Pleural Effusion ◽  
Ct Scan ◽  
Clinical Management ◽  
Chest Ct ◽  
X Ray ◽  
Contrast Enhanced ◽  
Plain Chest ◽  
Chest X Ray ◽  
Chest Ct Scan

AbstractBackgroundPleural effusion is common and can cause significant morbidity. The chest X-ray is often the initial radiological test, but additional tests may be required to reduce uncertainty and to provide additional diagnostic information. However, additional exposure and unnecessary costs should be prevented. The objective of the study was to assess the clinical benefit of an additional chest computed tomography (CT) scan over plain chest X-ray alone in the management of patients with pleural effusion.MethodsRetrospective analysis in 94 consecutive patients with pleural effusion who underwent chest X-ray and CT scan over an 18-month period in a single institution. All chest X-ray and CT scan reports were compared and correlated with clinical parameters in order to assess their utility in the clinical management. No blinding was applied.ResultsIn 75 chest CT scan reports (80 %), information provided by the radiologist did not change clinical management when compared to plain chest X-ray alone and did not provide any additional information over chest X-ray. Only 2/49 (4 %) of the native chest CT scan reports provided clinically relevant information as compared to 17/45 (38 %) contrast-enhanced chest CT scan reports (p<0.001).ConclusionsIn this retrospective cohort of patients with pleural effusion, an additional chest CT scan was not useful in the majority of patients. However, if a chest CT scan is required, then a contrast-enhanced study after pleural aspiration should be performed. Further prospective studies are required to confirm these findings.

Ultrasound Detection of Pneumothorax Compared with Chest X-Ray and Computed Tomography Scan

2011 ◽  
Vol 77 (4) ◽  
pp. 480-483 ◽  
Author(s):  
Khanjan Nagarsheth ◽  
Stanley Kurek
Keyword(s):  
Ct Scan ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Chest Ct ◽  
Trauma Patients ◽  
X Rays ◽  
Thoracic Ultrasound ◽  
X Ray ◽  
Chest X Ray ◽  
Chest Ct Scan

Pneumothorax after trauma can be a life threatening injury and its care requires expeditious and accurate diagnosis and possible intervention. We performed a prospective, single blinded study with convenience sampling at a Level I trauma center comparing thoracic ultrasound with chest X-ray and CT scan in the detection of traumatic pneumothorax. Trauma patients that received a thoracic ultrasound, chest X-ray, and chest CT scan were included in the study. The chest X-rays were read by a radiologist who was blinded to the thoracic ultrasound results. Then both were compared with CT scan results. One hundred and twenty-five patients had a thoracic ultrasound performed in the 24-month period. Forty-six patients were excluded from the study due to lack of either a chest X-ray or chest CT scan. Of the remaining 79 patients there were 22 positive pneumothorax found by CT and of those 18 (82%) were found on ultrasound and 7 (32%) were found on chest X-ray. The sensitivity of thoracic ultrasound was found to be 81.8 per cent and the specificity was found to be 100 per cent. The sensitivity of chest X-ray was found to be 31.8 per cent and again the specificity was found to be 100 per cent. The negative predictive value of thoracic ultrasound for pneumothorax was 0.934 and the negative predictive value for chest X-ray for pneumothorax was found to be 0.792. We advocate the use of chest ultrasound for detection of pneumothorax in trauma patients.

scholarly journals Lung Involvement Found on Chest CT Scan in a Pre-Symptomatic Person with SARS-CoV-2 Infection: A Case Report

2020 ◽  
Vol 5 (2) ◽  
pp. 56 ◽  
Author(s):  
Ali Asadollahi-Amin ◽  
Mehrdad Hasibi ◽  
Fatemeh Ghadimi ◽  
Hosnieh Rezaei ◽  
SeyedAhmad SeyedAlinaghi
Keyword(s):  
Ct Scan ◽  
Stable Condition ◽  
Lung Field ◽  
The Novel ◽  
Lung Involvement ◽  
Compassionate Use ◽  
Unrelated Condition ◽  
Novel Coronavirus ◽  
Care Worker ◽  
Chest Ct Scan

The novel coronavirus SARS-CoV-2 infection is spreading worldwide, and there are many reports of acute respiratory distress syndrome caused by this infection. However, asymptomatic lung involvement has not been reported. We hereby present the case of a 44-year-old health-care worker, who was found to be infected with the SARS-CoV-2 virus after a CT-scan performed for an unrelated condition revealed a lesion in the lung field compatible with COVID-19 infection. His condition deteriorated initially, but eventually improved with supportive treatment and the compassionate use of antivirals and antimalarials and is now in a stable condition.

Postoperative follow-up of lung cancer: Randomized trial comparing two follow-up programs in completely resected non-small cell lung cancer (IFCT-0302).

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. TPS7111-TPS7111
Author(s):  
Virginie Westeel ◽  
Fabrice Barlesi ◽  
Jean Domas ◽  
Philippe Girard ◽  
Pascal Foucher ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Physical Examination ◽  
Ct Scan ◽  
Fiberoptic Bronchoscopy ◽  
Chest Ct ◽  
Small Cell Lung ◽  
X Ray ◽  
Chest X Ray ◽  
Chest Ct Scan

TPS7111 Background: There are no robust data published on the follow-up after surgery for non-small cell lung cancer (NSCLC). Current international guidelines are informed by expert opinion. Most of them recommend regular follow-up with clinic visit and thoracic imaging, either chest X-ray of Chest CT-scan. The IFCT-0302 trial addresses the question whether a surveillance program with chest CT-scan and fiberoptic bronchoscopy can improve survival compared to a follow-up only based on physical examination and chest x-ray. There is no such trial ongoing over the world. Methods: The IFCT-0302 trial is a multicenter open-label controlled randomized phase III trial. The objective of the trial is to compare two follow-up programs after surgery for stage I-IIIa NSCLC. The primary endpoint is overall survival. Patients are randomly assigned to arm 1, minimal follow-up, including physical examination and chest x-ray; or arm 2, a follow-up consisting of physical examination and chest x-ray plus chest CT scan and fiberoptic bronchoscopy (optional for adenocarcinomas). In both arms, follow-up procedures are performed every 6 months during the first two postoperative years, and every year between the third and the fifth years. The main eligibility criteria include: completely resected stage I-IIIA (6th UICC TNM classification) or T4 (in case of nodules in the same lobe as the tumor) N0 M0 NSCLC, surgery within the previous 8 weeks. Patients who have received and/or who will receive pre/post-operative chemotherapy and/or radiotherapy are eligible. Statistical considerations: 1,744 patients is required. Accrual status: 1,568 patients from 119 French centers had been included. The end of accrual can be expected for September 2012. Ancillary study: Blood samples are collected in 1000 patients for genomic high density SNP micro-array analysis. This collection will contribute to the French genome wide association study (gwas) of lung cancer gene susceptibility, and the genetic factors predictive of survival and lung cancer recurrence will be analyzed.

scholarly journals The use of lung ultrasound during the COVID-19 pandemic

2020 ◽  
Vol 27 (SP1) ◽  
pp. e64-e75
Author(s):  
Aly Youssef ◽  
Marta Cavalera ◽  
Carlotta Azzarone ◽  
Carla Serra ◽  
Elena Brunelli ◽  
...  
Keyword(s):  
Health System ◽  
Pulmonary Infection ◽  
Lung Ultrasound ◽  
The Novel ◽  
Chain Reaction ◽  
X Ray ◽  
Rapid Learning ◽  
Chest X Ray ◽  
Polymerase Chain ◽  
Novel Coronavirus

The novel coronavirus disease (COVID-19) is a challenge to every health system. Unfortunately, it is unlikely that this pandemic will disappear soon. No health system, with its present resources and workflow, is capable enough to deal with a full-blown wave of this pandemic. Acquisition of specific new skills may be fundamental in delivering appropriate health care for our patients. The gold standard for diagnosis of the COVID-19 infection is real-time reverse transcription polymerase chain reaction. Radiological investigations (chest X-ray or high-resolution computerized tomography [CT]) can be helpful both for diagnosis and management, but they have many limitations. Ultrasound has been suggested as a reliable and accurate tool for assessing the lungs in COVID-19 patients. Lung ultrasound (LUS) can show specific signs of inter-stitial pneumonia, which is characteristic of COVID-19 pulmonary infection. In addition, nonradiologist specialists with experience in ultrasound can be trained on LUS with a relatively rapid learning curve. In pregnancy, LUS can be particularly useful due to the avoidance of exposure to ionizing radiation. In this review, we present the advantages, techniques, and limitations of the use of LUS during the COVID-19 pandemic, with specific focus on pregnancy.

CLINICAL CORRELATION AND AGREEMENT BETWEEN THE CHEST CT SCAN AND CHEST X-RAY FINDINGS IN TUBERCULIN-POSITIVE CHILDREN: A PROSPECTIVE CROSS SECTIONAL STUDY

CHEST Journal ◽  
2009 ◽  
Vol 136 (4) ◽  
pp. 40S
Author(s):  
Beverly D. Delacruz ◽  
Nerissa A. Deleon ◽  
Milagros S. Bautista ◽  
Fernando Ayuyao ◽  
Teresita Deguia
Keyword(s):  
Ct Scan ◽  
Cross Sectional Study ◽  
Chest Ct ◽  
Clinical Correlation ◽  
Sectional Study ◽  
Cross Sectional ◽  
X Ray ◽  
Chest X Ray ◽  
Chest Ct Scan

scholarly journals Multiobjective Genetic Algorithm and Convolutional Neural Network Based COVID-19 Identification in Chest X-Ray Images

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Prashant Kumar Shukla ◽  
Jasminder Kaur Sandhu ◽  
Anamika Ahirwar ◽  
Deepika Ghai ◽  
Priti Maheshwary ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Diagnostic Testing ◽  
The Novel ◽  
Screening Process ◽  
X Ray ◽  
Multiobjective Genetic Algorithm ◽  
Global Pandemic ◽  
Chest X Ray ◽  
Novel Coronavirus ◽  
Fold Cross Validation

COVID-19 is a new disease, caused by the novel coronavirus SARS-CoV-2, that was firstly delineated in humans in 2019.Coronaviruses cause a range of illness in patients varying from common cold to advanced respiratory syndromes such as Severe Acute Respiratory Syndrome (SARS-CoV) and Middle East Respiratory Syndrome (MERS-CoV). The SARS-CoV-2 outbreak has resulted in a global pandemic, and its transmission is increasing at a rapid rate. Diagnostic testing and approaches provide a valuable tool for doctors and support them with the screening process. Automatic COVID-19 identification in chest X-ray images can be useful to test for COVID-19 infection at a good speed. Therefore, in this paper, a framework is designed by using Convolutional Neural Networks (CNN) to diagnose COVID-19 patients using chest X-ray images. A pretrained GoogLeNet is utilized for implementing the transfer learning (i.e., by replacing some sets of final network CNN layers). 20-fold cross-validation is considered to overcome the overfitting quandary. Finally, the multiobjective genetic algorithm is considered to tune the hyperparameters of the proposed COVID-19 identification in chest X-ray images. Extensive experiments show that the proposed COVID-19 identification model obtains remarkably better results and may be utilized for real-time testing of patients.

Sign in / Sign up

Export Citation Format

Share Document