Chest X-ray Examination Research Articles

Chondromyxoid Fibroma of a Rib

Chondromyxoid fibroma (CMF) is an uncommon bone tumor, accounting for <1% of all bone tumors. It generally affects the metaphysis of the long bone of the lower limb and seldom involves the small bones, but the involvement of the flat bones, like ribs, is infrequent. A teenage girl complained of pain on the right side of the chest for the past 6 months, dull aching, and persistent without any diurnal variation. The chest X-ray examination showed a nodular, hyperdense lesion on the lateral chest wall near the 5-7th rib on the right side. A computed tomography scan confirmed the lesion from the sixth rib with ground-glass matrix and cortical thinning with a smooth margin, without any soft-tissue involvement. An enblock excision of the lesion was done. Histopathological studies showed a well-circumscribed tumor with reactive bone formation at the periphery with lobules of chondromyxoid tissue separated by spindle cells and stellate-shaped cells suggestive of CMF. At 1-year follow-up, she is asymptomatic without any recurrence. CMFs are rare benign tumors that require histopathological study to differentiate from other benign lesions of the bone. In flat tubular bones like the ribs, enblock resection is the mainstay of treatment.

Anomalous Origin of Left Coronary Artery from The Pulmonary Artery of Left Main Coronary Artery (ALCAPA) In A Pediatric Patient: A Rare Case Report

Background: The anomalous origin of the left coronary artery (LCA) from the pulmonary artery (ALCAPA) is a rare congenital anomaly due to abnormal division of the conotruncus into the aorta and pulmonary artery or persistence of the pulmonary bud with involution of the aortic bud that forms the origin of the coronary artery on embryogenesis. Only a small portion of cases survive more than two months of age. The survived cases can appear as asymptomatic, symptomatic, sudden cardiac death of adulthood ALCAPA. Case Description: We present an 8-year-old boy with symptomatic adulthood type ALCAPA. Preliminary chest x-ray examination found cardiomegaly. Unspecific findings were found on Echocardiography including fistula right coronary artery (RCA) and left coronary artery (LCA), with mitral regurgitation, moderate tricuspid regurgitation, and cardiomyopathy. Catheterization confirmed the left coronary artery from the pulmonary artery (ALCAPA) of the left main coronary artery (LMCA) origin. Additional Cardiac computed tomography angiography (CTA) demonstrated the LM originates from the pulmonary trunk accompanied by the presence of collaterals between the RCA and LAD and dilatation and turbulence of the RCA. Conclusion: Early diagnosis and prompt surgical intervention can give excellent results and lead to gradual recovery.

Role of Chest Radiograph in Diagnosis of Acyanotic Congenital Heart Disease

Background: Early diagnosis of acyanotic congenital heart disease could lead to early referral and treatment before the onset of irreversible sequelae. Despite the development of modern imaging methods, conventional chest radiographs remain an important component of diagnostic process in pediatric cardiology. The aim of this study is to determine the accuracy of the results of chest X-ray examination with echocardiography results in patients with suspected acyanotic congenital heart disease at H. Adam Malik General Hospital Medan in 2019-2020.&#x0D; Methods: This study was a retrospective cross-sectional analytical observational study with a diagnostic test design to compare the sensitivity and specificity of conventional chest radiography compared with echocardiography of patients with suspected acyanotic CHD with shunts. The sample population was all children &lt;18 years with suspicion of cyanotic CHD who came for treatment at H. Adam Malik Hospital Medan in the period January 2019 - December 2020. The study used data from medical records at H. Adam Malik Hospital Medan. The collected data is then analysed for diagnostic tests.&#x0D; Results: This study had a sample of 64 people with the highest proportion of samples being women, the average age was 67.9±54.1 months, and the results of echocardiography of the ductus arteriosus were persistent. The results of the diagnostic test showed a sensitivity of 78% and specificity of 80%, 95% PPV value and 40% NPV value, LR+ 3.8 and LR- 0.2.&#x0D; Conclusions: chest X-ray is adequate as a diagnostic tool in acyanotic congenital heart disease with left-to-right shunt. Clinical suspicion accompanied by chest X-ray results suggesting acyanotic congenital heart disease should be further assessed.

The chest X-ray radiologic severity index as a determinant of the severity of COVID-19 pneumonia: study based on the duration of treatment and inpatient rooms.

The chest X-ray examination is an imaging modality that is widely used in screening for COVID-19 pneumonia. The problems with treating COVID-19 pneumonia patients are the high incidence and severity of the disease and the limitations of treatment room facilities. The chest X-ray RadiologicSeverity Index is expected to assist clinicians in obtaining the relationship between the extent of lesions on X-ray and the duration of treatment and hospitalization for COVID-19 pneumonia patients. This study used an observational method using a retrospective approach. The research subjects were COVID-19 pneumonia patients from March 2020 to April 2021 who were hospitalized at Doctor Kariadi General Hospital Semarang. A total of 105 subjects confirmed positive RT-PCR and received serial X-ray examination services during treatment. The calculation of the RSI value was carried out on all X-ray chest X-rays and then statistically analyzed using the paired T test and Mann-Whitney methods.There was no significant relationship between the value of RSI1 and the duration of hospitalization with p = 0.566, as well as the value of RSI2 with the duration of hospitalization with p = 0.715. There is a significant relationship between the values of RSI1 and RSI2 with the use of the intensive care unit with p < 0.000, respectively. There was a significant relationship between the values of RSI1 and RSI2 with the use of ventilators in treatment, with p < 0.000. Furthermore RSI1 and RSI2 have a good result as predictor of intensive care and ventilator usage. The chest X-ray RSI has no significant relationship with the duration of hospitalization. The value of the chest X-ray RSI has a significant relationship with the use of intensive care rooms and the use of ventilators in treatment. The increase in the RSI value can describe the severity of the disease so that it plays a role in planning the treatment room.

Pre-Dialysis B-Line Quantification at Lung Ultrasound Is a Useful Method for Evaluating the Dry Weight and Predicting the Risk of Intradialytic Hypotension.

Intradialytic hypotension (IDH) is a frequent and well-known complication of hemodialysis, occurring in about one third of patients. An integrated approach with different methods is needed to minimize IDH episodes and their complications. In this prospective observational study, recruited patients underwent a multiparametric evaluation of fluid status through a lung ultrasound (LUS) with the quantification of B-lines, a physical examination, blood pressure, NT-proBNP and chest X-rays. The evaluation took place immediately before and at the end of the dialysis session, and the patients were divided into IDH and no-IDH groups. We recruited a total of 107 patients. A pre-dialysis B-line number ≥ 15 showed a high sensitivity in fluid overload diagnosis (94.5%), even higher than a chest X-ray (78%) or physical examination (72%) alone. The identification at the beginning of dialysis of &lt;8 B-lines in the overall cohort or &lt;20 B-lines in patients with NYHA 3-4 class are optimal thresholds for identifying those patients at higher risk of experiencing an IDH episode. In the multivariable analysis, the NYHA class, a low pre-dialysis systolic BP and a low pre-dialysis B-line number were independent risk factors for IDH. At the beginning of dialysis, the B-line quantification at LUS is a valuable and reliable method for evaluating fluid status and predicting IDH episodes. A post-dialysis B-line number &lt;5 may allow for an understanding of whether the IDH episode was caused by dehydration, probably due to due to an overestimation of the dry weight.

Assessment of radiation equivalent dose to pediatric patients during chest radiography

Objectives: The study investigated the equivalent dose delivered during pediatric chest radiography. Material and Methods: This study adopted a prospective and cross-sectional research design and was conducted between April 26 and July 2, 2021, at the University of Calabar Teaching Hospital, Calabar, Cross river state, Nigeria. A total of 85 pediatric patients aged 0–15 years, referred for chest X-ray examination, were recruited into the study. The chest radiography was taken for each child in erect or supine positions. Children, who needed some form of immobilization, were immobilized and respiration (breathing) was observed to take exposures at end-expiration. Exposure factors used ranged between 40 and 80 kVp, 1–2 mAs, source-to-image distance; 110 cm. Patient demographics and chest X-ray exposure factors for each exposure were recorded using a spreadsheet. The equivalent dose was calculated using the NUTECHRX software version. All statistical analyses were performed using the Statistical Package for the Social Sciences (SPSS) version 21.0. Statistical significance was set at P &lt; 0.05. Results: The estimated mean equivalent dose was 0.0046 ± 0.0026 mSv, while the mean of weight (kg), kVp, and mAs was 15.04 ± 14.51 kg, 58.28 ± 10.58V, and 1.79 ± 1.56 mAs, respectively. Mean equivalent dose was 0.00447mSv (uncertainty 0.0027) for female and 0.00464mSv (uncertainty 0.0026) for male, with no significance difference between them. The mAs showed strong positive correlation with equivalent dose (r = 0.71, P = 0.05), while weight demonstrated a strong negative correlation with equivalent dose (r = −0.98, P = 0.05). Conclusion: Current-time product (mAs) and the weight of a child are important determinants of equivalent dose in pediatric chest radiography.

COVID-19 detection on chest X-ray images using Homomorphic Transformation and VGG inspired deep convolutional neural network

COVID-19 had caused the whole world to come to a standstill. The current detection methods are time consuming as well as costly. Using Chest X-rays (CXRs) is a solution to this problem, however, manual examination of CXRs is a cumbersome and difficult process needing specialization in the domain. Most of existing methods used for this application involve the usage of pretrained models such as VGG19, ResNet, DenseNet, Xception, and EfficeintNet which were trained on RGB image datasets. X-rays are fundamentally single channel images, hence using RGB trained model is not appropriate since it increases the operations by involving three channels instead of one. A way of using pretrained model for grayscale images is by replicating the one channel image data to three channel which introduces redundancy and another way is by altering the input layer of pretrained model to take in one channel image data, which comprises the weights in the forward layers that were trained on three channel images which weakens the use of pre-trained weights in a transfer learning approach. A novel approach for identification of COVID-19 using CXRs, Contrast Limited Adaptive Histogram Equalization (CLAHE) along with Homomorphic Transformation Filter which is used to process the pixel data in images and extract features from the CXRs is suggested in this paper. These processed images are then provided as input to a VGG inspired deep Convolutional Neural Network (CNN) model which takes one channel image data as input (grayscale images) to categorize CXRs into three class labels, namely, No-Findings, COVID-19, and Pneumonia. Evaluation of the suggested model is done with the help of two publicly available datasets; one to obtain COVID-19 and No-Finding images and the other to obtain Pneumonia CXRs. The dataset comprises 6750 images in total; 2250 images for each class. Results obtained show that the model has achieved 96.56% for multi-class classification and 98.06% accuracy for binary classification using 5-fold stratified cross validation (CV) method. This result is competitive and up to the mark when compared with the performance shown by existing approaches for COVID-19 classification.

Pneumonia Detection Using Novel Deep Learning Techniques

Pneumonia is one of the leading infectious disease that can kill children and elderly people around the world. The development of an automated system to detect pneumonia would be advantageous, especially to enable treatment of this disease in remote areas without much delay. pneumonia is an lung infectious disease which mainly affects the small air sacs known as alveoli. The main symptoms of pneumonia includes cough, fever and breathing problems . Aged people, children and persons who have medical problems are the main victims of this disease. Around 450 million people are affected by this disease on an average of each and every year. The most commonly used technique for diagnosing this disease is chest X-ray imaging. Chest X-ray examination is complex procedure to detect the disease because it involves lots of vulnerabilities. With latest advances in technologies we can use deep learning algorithms to detect the disease using chest x ray images. To deal with the scarcity of data, we used Deep Transfer Learning and designed the Hybrid Algorithms. The images of the chest X-rays were fed into the individual algorithms for training purposes. Parallel Deep Feature Extractors are used in conjunction with various algorithms. For classifying chest X-ray images into normal and pneumonia, Here we are proposing an hybrid model based on VGG16, VGG19, CNN, and Mobile Net networks. Individual image classification algorithms were combined to form a hybrid model .In comparison to individual algorithms, the new Hybrid Model with Deep Learning achieved higher accuracy than existing methods.

Use of Chest X-Ray (CXR) in Covid-19 Screening as A Modalities

Background: As of March 11, 2020, the number of confirmed cases in China had reached 80,955 with the death toll reaching 3,162. So far, Covid-19 tends to infect people who have comorbid diseases such as heart disease, diabetes mellitus, cancer and chronic respiratory diseases as well as people over 60 years of age. Several cases of Covid-19 have also been reported in pregnant women.&#x0D; Method: Radiographic technologies and tools including chest X-Ray and Computed Tomography (CT) are applied for initial screening and the follow-up because they provide detailed diagnoses with specific pathological features for staging and treatment settings. Not infrequently cases of Covid-19 are found in pregnant women because during pregnancy women’s condition becomes very vulnerable to infection with pneumonia pathogens due to physiological changes during pregnancy that result in a decrease in the immune system. Although the clinical symptoms are the same as for non-pregnant women and there are no aggravating factors, pregnant women are prone to hypoxia.&#x0D; Results: Chest x-ray (CXR) is a radiographic projection tool that can help diagnose conditions or abnormalities in the thoracic cavity. Due to the spread of Covid-19, it is important to recognize the common Covid-19 imaging findings and the abnormal pneumonia that occurs over time on CXR results. CXR can be used to diagnose patients with acute respiratory distress as the first line of evaluation for Covid-19 patients 19.&#x0D; Conclusion: CXR can be a screening modality in Covid-19 patients including pregnant women. However, it is necessary to keep in mind that the CXR examination can have an impact on the fetus. Even though the risk is small, pregnant women who will undergo a Covid-19 examination or evaluation need special attention. In addition, it is necessary to consider other examinations that can be carried out especially on pregnant women, which do not have the effect of radiation

Flecainide-induced pneumonitis: a case report

BackgroundWe report a case of acute respiratory distress associated with a histological pattern of acute fibrinous and organizing pneumonia, and discuss the possible responsibility of flecainide therapy.Case presentationA 61-year-old African woman developed a rapidly progressive dyspnea and required admission in the intensive care unit for orotracheal intubation and mechanical ventilation. Chest X-ray examination revealed bilateral infiltrates predominating in the basal part of both lungs. Lung computed tomography disclosed bilateral ground-glass opacities and septal thickening. After exclusion of the most common causes of infectious or immune pneumonia, a toxic origin was investigated and flecainide toxicity was considered. Lung biopsy was consistent with the unusual pattern of acute fibrinous and organizing pneumonia. Clinical and radiological improvement was noted after corticosteroid therapy, but the patient died from septic complications.ConclusionFlecainide-induced lung injury has rarely been reported in the literature and remains a diagnosis of exclusion. The histological pattern of acute fibrinous and organizing pneumonia has been previously observed with amiodarone. There are no firm guidelines for the treatment of acute fibrinous and organizing pneumonia, but some patients may positively respond to corticosteroids.

Role of point of care lung ultrasound in neonatal respiratory distress in comparison with chest X-ray-a clinico-radiological evaluation

Background: The use of ultrasound for immediate management of life-threatening conditions is one among the main changes of these last decades. Lung ultrasound has become more and more popular in the first decade of the 21st century, both in neonatal and in paediatric age groups. The lung ultrasound may be tool in differential diagnosis of respiratory distress in newborns. Aims and objectives: To assess diagnostic role of point of care lung ultrasound in neonates presented with respiratory distress and analyse the possibility of initiating management protocol based on lung ultrasound finding.Methods: Present non-randomized study-a hospital based analytical cross-sectional study was carried out in 60 patients with respiratory distress for a period of 18 months (January 2020-30 June 2021). Neonates suffering from respiratory distress (Pulmonary cause with Downe’s score &gt;4) were included. Routine investigations, lung USG and chest x-ray examination was recorded. Detailed perinatal history were obtained.Results: Mode of delivery was LSCS among 38.3% and vaginal delivery among 61.7% subjects. The mode of respiratory support was CPAP among 33.3% and ventilator among 66.7% subjects. Mean birth weight of the study population was 2003.51±767.35 grams. Final diagnosis of the present study shows that majority of neonates had respiratory distress syndrome (38.33%) followed by birth asphyxia with respiratory distress (28.33%) followed by TTNB (11.66%). A total of 25.0% neonates had Downes score 4, 16.7% had 5, 25.0% had 6, 26.7% had 7 and 6.7% neonates had 8 score. X-ray findings showed sensitivity 56.67% and positive predictive value 100% were observed. On the basis of USG findings, 93.22% sensitivity and positive predictive value 98.21% were observed.Conclusions: Lung ultrasound is a non-invasive, bedside and repeatable method that could improve the management of neonatal respiratory distress. Neonatal lung ultrasound is a useful predictor of the need for intubation over chest x-ray. Combined lung consolidation, pleural line abnormalities and absence of A line findings were the most specific lung ultrasound findings in RDS which were present among majority of the patients.

THE ROLE OF RIGID BRONCHOSCOPY IN CHILDREN WITH TRACHEOBRONCHIAL FOREIGN BODY ASPIRATION

To assess the role of rigid bronchoscopy in children with tracheobronchial foreign body aspiration (FBA) a retrospective study was carried out in Pediatrics Ward of Bakhtawar Amin Trust Hospital &amp; Medical &amp; Dental College Multan for 1 year. A total of 80 children aged 6 months to 15 years with foreign body aspiration were included in the study. Data was collected from the medical histories of the patients. Rigid bronchoscopy was performed in all patients under anesthesia. All the data was analyzed by using SPSS version 21. The study was conducted on total 80 patients whose mean age was 2.5 years. 66 (82.5%) patients aspirated organic FBs, while 14 (17.5%) aspirated inorganic FBs. Cyanosis (37,46.2%) and stridor (33,41.2%) were the most common symptoms. In 78 (97.5%) patients rigid bronchoscopy was performed. In 75 (93.7%) not post operative event occurred. Medical history of patients with FBA is important for diagnosis. In addition, bronchoscopy is mandatory in patients with history of choking even if chest x-ray and initial examination are normal.

Chest X-Ray ESD and ESAK Assessment in A Few Diagnostic Radiological Facilities in Delta State

Background: The utilization of X-rays in medical procedures has sparked apprehension regarding their potential adverse consequences, despite their undeniable advantages in the realms of diagnosis and therapy. The present study aimed to evaluate the levels of Entrance Skin Dose (ESD) and Entrance Skin Air Kerma (ESAK) associated with chest X-ray examinations conducted in diagnostic radiological facilities located within Delta State. The present study employed a standardized approach to describe the materials and methods used in the research. The dose assessment was performed on a sample of 700 patients who were 18 years of age or older. These patients were selected from 10 operational facilities located throughout the State. The findings of the study are as follows: The effective dose (ESD), ascertained through the utilization of patient anatomical data and exposure parameters, fell within the recommended reference dose limits of 1 mGy (National Nuclear Regulatory Agency) and 0.4 mGy (International Atomic Energy Agency) for the majority of healthcare facilities. Nevertheless, certain centers demonstrated elevated dose levels, which can be attributed to factors such as increased exposure rates, aging x-ray tubes, and inadequate technician competency. The effective dose values (ESD) exhibited a range of 0.018 to 1.671 mGy for males and 0.084 to 1.542 mGy for females. The range of Entrance Skin Air Kerma (ESAK) values for males was found to be between 0.019 and 0.085 mGy, while for females it ranged from 0.016 to 0.098 mGy. These values were observed to be within the recommended dose limits. In conclusion, this study emphasizes the significance of surveillance of radiation exposure and the implementation of quality assurance protocols in order to safeguard patient well-being and mitigate potential hazards linked to chest X-ray procedures conducted in diagnostic radiological establishments.

RadioBERT: A deep learning-based system for medical report generation from chest X-ray images using contextual embeddings

Background:Increasing number of chest X-ray (CXR) examinations in radiodiagnosis departments burdens radiologists’ and makes the timely generation of accurate radiological reports highly challenging. An automatic radiological report generation (ARRG) system is envisaged to generate radiographic reports with minimal human intervention, ease radiologists’ burden, and smoothen the clinical workflow. The success of an ARRG system depends on two critical factors: i) quality of the features extracted by the ARRG system from the CXR images, and ii) quality of the linguistic expression generated by the ARRG system describing the normalities and abnormalities as indicated by the extracted features. Most of the existing ARRG systems miserably fail due to the latter factor and do not generate clinically acceptable reports because they ignore the contextual importance of the medical terms. Objectives:The advent of contextual word embeddings, like ELMo and BERT, has revolutionized several natural language processing (NLP) tasks. A contextual embedding represents a word based on its context. The main objective of this work is to develop an ARRG system that uses contextual word embeddings to generate clinically accurate reports from CXR images. Methods:We present an end-to-end deep neural network that uses contextual word representations for generating clinically useful radiological reports from CXR images. The proposed network, termed as RadioBERT, uses DistilBERT for contextual word representation and leverages transfer learning. Additionally, due to the importance of abnormal observations over the normal ones, the network reorders the generated sentences by applying sentiment analysis to keep abnormal descriptions on the top of the generated report. Results:The empirical study consisting of several experiments performed on the OpenI dataset indicates that CNN+Hierarchical LSTM with DistilBERT embedding improves the benchmark performance. We have been able to achieve the following performance scores: BLEU-1 = 0.772, BLEU-2 = 0.770, BLEU-3 = 0.768, BLEU-4 = 0.767, CIDEr = 0.5563, and ROUGE = 0.897. Conclusion:The proposed method improves the state-of-the-art performance scores by a substantial margin. It is concluded that the use of word embeddings generated by DistilBERT enhances the performance of hierarchical LSTM for producing clinical reports by significant margin.

Suggested Local Diagnostic Reference Levels for Possible Pediatric X-Ray Optimization in Addis Ababa, Ethiopia.

Early childhood radiation exposure carries an enhanced radiation risk of about two to three times as high as in adults. The objective of this study was to determine local diagnostic reference levels for the most frequent pediatric x-ray examinations in Addis Ababa, Ethiopia. A cross-sectional study was conducted on 18 public and private hospitals/clinics in Addis Ababa. A total of 864 pediatric patients, undergoing eight types of routine x-ray examinations with 13 projections were evaluated from December 18/2017 to March 17 /2018. All pediatrics were categorized under four age groups. Anthropometric and radiographic parameters of each patient were recorded .The minimum, maximum, mean and third quartile values of entrance surface dose were analyzed using SPSS version 23. Finally, the suggested local diagnostic reference levels were compared with national and international reference dose values. Of the 864 pediatric patients, chest (AP/PA), lower and upper extremity (AP/PA) accounted for 501(58%), 110 (13%) and 103 (12%) respectively, accounting to 714(83%) of the total pediatric x-ray examinations. The suggested local diagnostic reference levels of chest X-ray (AP/PA) examinations in mGy were: (0.09,0.13,0.17,0.17) for age group (0-<1,1-<5 ,5-<10, and 10-<15), respectively. Similarly, for same age group (0-<1,1-<5 ,5-<10, and 10-<15) the suggested local diagnostic reference levels of lower and upper extremities in mGy were: (0.06,0.08,0.09,0.09) and (0.04,0.05,0.05,0.06), respectively. The suggested local diagnostic reference levels were slightly higher than the national and international guidance levels, indicating the need for establishment of diagnostic reference levels in the country.

PNEUMONIA DETECTION USING CHEST X-RAY IMAGES THROUGH CNN

Pneumonia is a respiratory infection caused by bacteria or viruses. It is a condition in which fluids fill the lung, causing respiratory difficulty. It can be life threatening for people with weak immune systems. It is important to diagnose pneumonia at an early stage which helps in curing it and it increases the survival rate of the patient. Generally Chest X-ray imaging method is used for diagnosing pneumonia. But the examination of chest X-rays is a challenging task and is prone to subjective variability. In this system, we developed a computer-aided diagnosis system for automatic pneumonia detection using chest X-ray images. Various deep learning techniques are integrated into this system to improve their ability to detect the disease from their X-ray images and produce the result faster and efficiently. With the growing technological advancements we have in this day and age, it is possible to use tools based on deep learning frameworks to detect pneumonia based on chest x-ray images. The challenge here would be to aid the diagnosis process which allows for expedited treatment and better clinical outcomes. The proposed system is evaluated on two publicly available pneumonia Xray datasets. This dataset(Kermany dataset)consists of 5856 chest X-ray images from a large population of both adults and children, unevenly distributed among the classes “Pneumonia” and “Normal”. Which obtained an accuracy rate of 0.8958%.

CDC_Net: multi-classification convolutional neural network model for detection of COVID-19, pneumothorax, pneumonia, lung Cancer, and tuberculosis using chest X-rays.

Coronavirus (COVID-19) has adversely harmed the healthcare system and economy throughout the world. COVID-19 has similar symptoms as other chest disorders such as lung cancer (LC), pneumothorax, tuberculosis (TB), and pneumonia, which might mislead the clinical professionals in detecting a new variant of flu called coronavirus. This motivates us to design a model to classify multi-chest infections. A chest x-ray is the most ubiquitous disease diagnosis process in medical practice. As a result, chest x-ray examinations are the primary diagnostic tool for all of these chest infections. For the sake of saving human lives, paramedics and researchers are working tirelessly to establish a precise and reliable method for diagnosing the disease COVID-19 at an early stage. However, COVID-19’s medical diagnosis is exceedingly idiosyncratic and varied. A multi-classification method based on the deep learning (DL) model is developed and tested in this work to automatically classify the COVID-19, LC, pneumothorax, TB, and pneumonia from chest x-ray images. COVID-19 and other chest tract disorders are diagnosed using a convolutional neural network (CNN) model called CDC Net that incorporates residual network thoughts and dilated convolution. For this study, we used this model in conjunction with publically available benchmark data to identify these diseases. For the first time, a single deep learning model has been used to diagnose five different chest ailments. In terms of classification accuracy, recall, precision, and f1-score, we compared the proposed model to three CNN-based pre-trained models, such as Vgg-19, ResNet-50, and inception v3. An AUC of 0.9953 was attained by the CDC Net when it came to identifying various chest diseases (with an accuracy of 99.39%, a recall of 98.13%, and a precision of 99.42%). Moreover, CNN-based pre-trained models Vgg-19, ResNet-50, and inception v3 achieved accuracy in classifying multi-chest diseases are 95.61%, 96.15%, and 95.16%, respectively. Using chest x-rays, the proposed model was found to be highly accurate in diagnosing chest diseases. Based on our testing data set, the proposed model shows significant performance as compared to its competitor methods. Statistical analyses of the datasets using McNemar’s, and ANOVA tests also showed the robustness of the proposed model.

Surveillance Quality Indicators Highlight the Need for Improving Tuberculosis Diagnostics and Monitoring in a Hyperendemic Area of the Brazilian Amazon Region.

The city of Ananindeua, State of Pará, Brazil, is a hyperendemic area for tuberculosis (TB). The present study describes the population characteristics and epidemiological indicators of TB cases from Ananindeua, from 2018 to 2020. The TB cases were screened from the Municipal Health Department of Ananindeua database, and the secondary data were obtained from the Brazilian Notifiable Diseases Information System (SINAN). A high percentage of cases did not undergo a rapid molecular test (74.9%) or culture (84.8%) for diagnosis of TB; a chest X-ray examination for diagnosis of TB was performed in 74.47% of new cases. The SINAN form data was incomplete on susceptibility test results (<0.01–92.7). Sputum smear microscopy for monitoring treatment was recorded in the follow-up form in 34.3% and after the 6th month in 61.1% of cases. The cure rate (60.31%) was below the recommendation by the Brazilian Ministry of Health. The quality indicators showed many weaknesses: (I) lack of availability of smear microscopy as a diagnostic test in a hyper-endemic area; (II) low availability of specific exams such as culture and rapid molecular test (RMT); (III) low adherence to smear microscopy to monitor the evolution of cases during treatment; (IV) absence of drug susceptibility test data; (V) failure to fill in essential variables for TB surveillance.

Image enhancement techniques on deep learning approaches for automated diagnosis of COVID-19 features using CXR images.

The outbreak of novel coronavirus (COVID-19) disease has infected more than 135.6 million people globally. For its early diagnosis, researchers consider chest X-ray examinations as a standard screening technique in addition to RT-PCR test. Majority of research work till date focused only on application of deep learning approaches that is relevant but lacking in better pre-processing of CXR images. Towards this direction, this study aims to explore cumulative effects of image denoising and enhancement approaches on the performance of deep learning approaches. Regarding pre-processing, suitable methods for X-ray images, Histogram equalization, CLAHE and gamma correction have been tested individually and along with adaptive median filter, median filter, total variation filter and gaussian denoising filters. Proposed study compared eleven combinations in exploration of most coherent approach in greedy manner. For more robust analysis, we compared ten CNN architectures for performance evaluation with and without enhancement approaches. These models are InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, Vgg19, NASNetMobile, ResNet101, DenseNet121, DenseNet169, DenseNet201. These models are trained in 4-way (COVID-19 pneumonia vs Viral vs Bacterial pneumonia vs Normal) and 3-way classification scenario (COVID-19 vs Pneumonia vs Normal) on two benchmark datasets. The proposed methodology determines with TVF + Gamma, models achieve higher classification accuracy and sensitivity. In 4-way classification MobileNet with TVF + Gamma achieves top accuracy of 93.25% with 1.91% improvement in accuracy score, COVID-19 sensitivity of 98.72% and F1-score of 92.14%. In 3-way classification our DenseNet201 with TVF + Gamma gains accuracy of 91.10% with improvement of 1.47%, COVID-19 sensitivity of 100% and F1-score of 91.09%. Proposed study concludes that deep learning modes with gamma correction and TVF + Gamma has superior performance compared to state-of-the-art models. This not only minimizes overlapping between COVID-19 and virus pneumonia but advantageous in time required to converge best possible results.

Accidental duodenal foreign body of toothbrush removed laparoscopically: a case report

BackgroundForeign body ingestion is a common case in daily medical care, and it usually passes through the entire gastrointestinal tract naturally and is excreted in the feces. However, long and sharp foreign bodies may be difficult to pass naturally due to their shape. Here, we present a rare case of a duodenal foreign body, a toothbrush, that required laparoscopic surgical removal after a failed endoscopic attempt.Case presentationA 51-year-old male with intellectual disability presented to our hospital due to fever. Initially, he was diagnosed with aspiration pneumonia by chest X-ray and blood examination. However, abdominal X-ray examination suggested a foreign body, and a computed tomography scan revealed a toothbrush in the duodenum. Therefore, upper gastrointestinal endoscopy was immediately attempted to remove it, but it could not be safely removed because the handle part of the toothbrush seemed deeply embedded in the duodenal mucosa. Therefore, this case was diagnosed as duodenal incarceration of the toothbrush, and it was removed by laparoscopic surgery. The operation was performed safely, and the patient’s postoperative course was good without any complications. The extracted toothbrush was 15 cm in length.ConclusionWe experienced a rare case of a duodenal foreign body, which was a toothbrush. The duodenal foreign body was safely removed by laparoscopic surgery for the first time.