scholarly journals COVID-19 Symptoms Detection Based on NasNetMobile with Explainable AI Using Various Imaging Modalities

2020 ◽  
Vol 2 (4) ◽  
pp. 490-504
Author(s):  
Md Manjurul Ahsan ◽  
Kishor Datta Gupta ◽  
Mohammad Maminur Islam ◽  
Sajib Sen ◽  
Md. Lutfar Rahman ◽  
...  
Keyword(s):  
Ct Scan ◽  
Initial Screening ◽  
X Ray ◽  
Learning Techniques ◽  
Alternative Approach ◽  
Number Of Patients ◽  
The Usa ◽  
Chest X Ray ◽  
Interpretable Model ◽  
Potential Opportunity

The outbreak of COVID-19 has caused more than 200,000 deaths so far in the USA alone, which instigates the necessity of initial screening to control the spread of the onset of COVID-19. However, screening for the disease becomes laborious with the available testing kits as the number of patients increases rapidly. Therefore, to reduce the dependency on the limited test kits, many studies suggested a computed tomography (CT) scan or chest radiograph (X-ray) based screening system as an alternative approach. Thereby, to reinforce these approaches, models using both CT scan and chest X-ray images need to develop to conduct a large number of tests simultaneously to detect patients with COVID-19 symptoms. In this work, patients with COVID-19 symptoms have been detected using eight distinct deep learning techniques, which are VGG16, InceptionResNetV2, ResNet50, DenseNet201, VGG19, MobilenetV2, NasNetMobile, and ResNet15V2, using two datasets: one dataset includes 400 CT scan and another 400 chest X-ray images. Results show that NasNetMobile outperformed all other models by achieving an accuracy of 82.94% in CT scan and 93.94% in chest X-ray datasets. Besides, Local Interpretable Model-agnostic Explanations (LIME) is used. Results demonstrate that the proposed models can identify the infectious regions and top features; ultimately, it provides a potential opportunity to distinguish between COVID-19 patients with others.

scholarly journals COVID-19 infection map generation and detection from chest X-ray images

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Aysen Degerli ◽  
Mete Ahishali ◽  
Mehmet Yamac ◽  
Serkan Kiranyaz ◽  
Muhammad E. H. Chowdhury ◽  
...  
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
Clinical Use ◽  
X Ray ◽  
Learning Techniques ◽  
Map Generation ◽  
Severity Grading ◽  
Chest X Ray ◽  
Novel Method ◽  
Aided Diagnosis

AbstractComputer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human–machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

scholarly journals Deep learning-based meta-classifier approach for COVID-19 classification using CT scan and chest X-ray images

2021 ◽  
Author(s):  
Vinayakumar Ravi ◽  
Harini Narasimhan ◽  
Chinmay Chakraborty ◽  
Tuan D. Pham
Keyword(s):  
Deep Learning ◽  
Ct Scan ◽  
X Ray ◽  
Chest X Ray

scholarly journals Therapeutic effect of cycloserine combined with anti-tuberculosis drugs in the treatment of multidrug-resistant tuberculosis

2022 ◽  
Vol 20 (2) ◽  
pp. 419-424
Author(s):  
Yang Zhao ◽  
Mabin Si ◽  
Zhihui Li ◽  
Xiulei Yu
Keyword(s):  
Ct Scan ◽  
Multidrug Resistant ◽  
Chest Ct ◽  
Case Detection Rate ◽  
X Ray ◽  
Resistant Tuberculosis ◽  
Multidrug Resistant Tuberculosis ◽  
Before And After ◽  
Mdr Tb ◽  
Chest X Ray

Purpose: The present study analyzes the comprehensive therapeutic effect of cycloserine, in combination with anti-tuberculosis drugs using chest X-ray and chest CT (computed tomography) scan techniques. Methods: A total of 90 patients, diagnosed with multidrug resistant tuberculosis (MDR TB) were subjected to chest x-ray and CT scan before and after treatment in the two groups. Different views such as sagittal, coronal, lung window and multiplanar imaging of mediastinal window were taken. Some parameters such as case detection rate (CDR) in chest X-ray and CT scan and comprehensive curative effect were observed in two groups. Further, the changes in chest CT signs in addition to absorption of focus, cavity closure and changes in CT extra pulmonary signs were also observed. Results: The clinical profile of the patients and the course of disease were statistically insignificant (p > 0.05). Total effectiveness rate and case detection rate (CDR) values exhibited a significant difference between the groups (p < 0.05). Lung consolidation, nodules and cavities significantly improved in both groups before and after the treatment (p < 0.05). Both groups showed significant improvements in extrapulmonary signs in CT scan (p < 0.05) after the treatment. Conclusion: Based on the study outcomes, the CT scan method has good potentials for diagnosing and treating MDR TB at the early stages. Further, it can clarify the signs and outcomes of the disease at early stages, thus providing the medical fraternity a great opportunity to cure the disease.

scholarly journals CLINICAL CHARACTERISTICS OF CHILDREN WITH CYSTIC FIBROSIS IN KHARKIV REGION

2017 ◽  
Vol 3 (4) ◽  
pp. 166-169
Author(s):  
Ekateryna Yanovska ◽  
Victoria Klimenko ◽  
Elena Pasichnik
Keyword(s):  
Cystic Fibrosis ◽  
Respiratory Tract ◽  
Ct Scan ◽  
Clinical Characteristics ◽  
Epithelial Lining ◽  
Bacteriological Examination ◽  
Epithelial Lining Fluid ◽  
X Ray ◽  
Chest X Ray ◽  
Microbiological Status

The work is devoted to the study of the clinical and paraclinical peculiarities in children with CF (including respiratory tract microbiocenosis) in Kharkiv region. Also it is about the correlation of microbiological status of CF patients with the disease morbidity.Under the supervision were 30 children with cystic fibrosis. They conducted clinical, paraclinical (bacteriological examination of sputum and epithelial lining fluid, chest X-ray, CT scan of lungs) were performed.Clinical and paraclinic (bacteriological examination of sputum and epithelial lining fluid, chest X-ray, CT scan of lungs) were performed.During observations revealed that the condition severity of CF patients is associated with chronic P. aeruginosa infection, and B. cepacia. And also, that none of patients in Kharkiv region has determined  any of pathognomonic respiratory causative microorganisms – M. Tuberculosis and non-tuberculous micobacteria, H. influenza, Ralstonia picketi, condition of infecting by P. Aeruginosa is not identified, and this is the evidence of insufficient laboratory diagnostics.Key words: cystiс fibrosis, children, microflora В.А. Клименко, К.О. Яновська, О.В. ПасічникКЛІНІЧНА ХАРАКТЕРИСТИКА ДІТЕЙ З МУКОВІСЦИДОЗОМ В ХАРКІВСЬКОМУ РЕГІОНІРобота присвячена вивченню клініко-параклінічних особливостей дітей з МВ (в тому числі - мікробіоценоз респіраторного тракту) в Харківському регіоні. А також визначенню кореляції мікробіологічного статусу хворих МВ з тяжкістю перебігу захворювання.Під наглядом були 30 дітей, хворих на муковісцидоз. Їм проведені клінічні, параклінічні (бактеріологічне дослідження мокротиння і промивних вод бронхів, рентгенограма органів грудної клітки, комп'ютерна томографія легенів) дослідження.В ході спостережень виявлено, що тяжкість стану хворих МВ асоційована з хронічною інфекцією P. aeruginosa і B. cepacia. А також, що в Харківському регіоні з патогномонічних респіраторних збудників МВ у жодного хворого не виявлено M. Tuberculosis і non-tuberculous micobacteria, H. influenza, Ralstonia picketi, не визначається статус інфікування P. aeruginosa, що свідчить про незадовільну лабораторну діагностику.Ключові слова: муковісцидоз, діти, мікрофлора. В.А.  Клименко, Е.А. Яновская, Е.В. ПасичникКЛИНИЧЕСКАЯ ХАРАКТЕРИСТИКА ДЕТЕЙ С МУКОВИСЦИДОЗОМ В ХАРЬКОВСКОМ РЕГИОНЕРабота посвящена изучению клинико-параклинических особенностей детей с МВ (в том числе – микробиоценоз респираторного тракта) в Харьковском регионе. А также определению корреляции микробиологического статуса больных МВ с тяжестью течения заболевания.Под наблюдением были 30 детей, больных муковисцидозом. Им проведены клинические, параклинические (бактериологическое исследование мокроты и промывных вод бронхов, рентгенограмма органов грудной клетки, компьютерная томография легких) исследования.В ходе наблюдений выявлено, что тяжесть состояния больных МВ ассоциирована с хронической инфекцией P. aeruginosa и B. cepacia.  А также, что в Харьковском регионе из патогномоничных респираторных возбудителей МВ ни у одного больного не выявлено M. Tuberculosis и non-tuberculous micobacteria, H. influenza, Ralstonia picketi, не определяется статус инфицирования P. aeruginosa, что свидетельствует о неудовлетворительной лабораторной диагностике.Ключевые слова: муковисцидоз, дети,  микрофлора.

Chest X-Ray Image-Based Testing Using Machine Learning Techniques

Covid-19 ◽  
2021 ◽  
pp. 241-278
Author(s):  
Parag Verma ◽  
Ankur Dumka ◽  
Alaknanda Ashok ◽  
Amit Dumka ◽  
Anuj Bhardwaj
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
X Ray ◽  
Learning Techniques ◽  
Chest X Ray

scholarly journals LO68: Patterns and predictors of emergency physician productivity

CJEM ◽  
2018 ◽  
Vol 20 (S1) ◽  
pp. S30-S31
Author(s):  
S. Campbell ◽  
S. Weerasinghe
Keyword(s):  
Emergency Department ◽  
Quality Of Care ◽  
Ct Scan ◽  
Resource Utilization ◽  
Emergency Physician ◽  
X Ray ◽  
Workload Measurement ◽  
Number Of Patients ◽  
Return Visits

Introduction: Emergency Physician (EP) performance comprises both quality of care and quantity of patients seen in a set time. Emergency Department (ED) overcrowding increases the importance of the ability of EPs to see patients as rapidly as is safely possible. Maximizing efficiency requires an understanding of variables that are associated with individual physician performance. While using the incidence of return visits within 48 hours as a quality measure is controversial, repeat visits do consume ED resources. Methods: We analysed the practice variables of 85 EPs working at a single academic ED, for the period from June 1, 2013 to May 31, 2017, using data from an emergency department information system (EDIS). Variables analysed included: number of shifts worked, number of patients seen per hour (pt/hr), an adjusted workload measurement (assigning a higher score to CTAS 1-3 patients), percentage of patients whose care involved an ED learner, and the percentage of patients who returned to the ED within 48 hours of ED discharge. Resource utilization was measured by percentage of diagnostic imaging (ultra sound (US), CT scan (CT), x-ray (XR)) ordered and percentage of patients referred to consulting services. We performed principal component analyses to identify bench marks of resource use, demographic (age, EM qualification, gender) and other practice related predictors of performances. Results: Mean pt/hr differed significantly by EM Qualification for CTAS 2-4, with 1.71/hr (95% Confidence Interval=1.63-1.77) by FRCPS physicians, compared to 1.89/hr by CCFP(EM) (CI=1.81-1.97). There were no differences for CTAS 1 and 5. Other variables associated with a significantly lower pt/hr, included a greater use of imaging, (CT: p=0.0003, XR: p=0.0008) although this was did not reach statistical significance with US (p=0.06%). Female gender, older age, number of patient consultations for CTAS 3 and more patients seen by a learner were all associated with lower pt/hr. Pt/hr was a better predictor (R2=45%) for EP resource utilization than adjusted workload measurement (R2 =35%). Higher use of CT was associated with fewer return visits in <48 hrs (0.13% lower). Male gender, younger age, number of patient consultation for CTAS 3 and fewer patients seen by a learner were all associated with an increase in return visits. Conclusion: We found a significant difference in pt/hr rates and return visits within 48 hours between EPs with different age ranges, gender, and EM certification. Increased use of CT scan and x-ray, and consultation for patients CTAS 3 were associated with lower pt/hr. Return visit rates also varied in association with diagnostic imagine use, age, gender and number of patients seen by a learner. Further research is needed to assess the association with these variables on quality of care.

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.

Sign in / Sign up

Export Citation Format

Share Document