Diagnosis Of Lung Infection Research Articles

Advances in medical image analysis: A comprehensive survey of lung infection detection

AbstractThis research investigates advanced approaches in medical image analysis, specifically focusing on segmentation and classification techniques, as well as their integration into multi‐task architectures for lung infections. This research begins by explaining key architectural models used in segmentation and classification tasks. The study extends to the enhancement of these architectures through attention modules and conditional random fields. Relevant datasets and evaluation metrics, incorporating discussions on loss functions are also reviewed. This review encompasses recent advancements in single‐task and multi‐task models, highlighting innovations in semi‐supervised, self‐supervised, few‐shot, and zero‐shot learning techniques. Empirical analysis is conducted on both single‐task and multi‐task architectures, predominantly utilizing the U‐Net framework, and is applied across multiple datasets for segmentation and classification tasks. Results demonstrate the effectiveness of these models and provide insights into the strengths and limitations of different approaches. This research contributes to improved detection and diagnosis of lung infections by offering a comprehensive overview of current methodologies and their practical applications.

AUTOMATIC DETECTION OF COVID-19 AND VIRAL PNEUMONIA IN X-RAY IMAGES USING DEEP LEARNING APPROACH

The early detection and treatment of COVID-19 infection are necessary to save human life. The study aims to propose a time-efficient and accurate method to classify lung infected images by COVID-19 and viral pneumonia using chest X-ray. The proposed classifier applies end-to-end training approach to classify the images of the set of normal, viral pneumonia and COVID-19-infected images. The features of the two infected classes were precisely captured by the extractor path and transferred to the constructor path for precise classification. The classifier accurately reconstructed the classes using the indices and the feature maps. For firm confirmation of the classification results, we used the Matthews correlation coefficient (MCC) along with accuracy and F1 scores (1 and 0.5). The classification accuracy of the COVID-19 class achieved was about ([Formula: see text])% with MCC score ([Formula: see text]). The classifier is distinguished with great precision between the two nearly correlated infectious classes (COVID-19 and viral pneumonia). The statistical test suggests that the obtained results are statistically significant as [Formula: see text]. The proposed method can save time in the diagnosis of lung infections and can help in reducing the burden on the medical system in the time of the pandemic.

COVID-19 Severity Prediction Using Enhanced Whale with Salp Swarm Feature Classification

Computerized tomography (CT) scans and X-rays play an important role in the diagnosis of COVID-19 and pneumonia. On the basis of the image analysis results of chest CT and X-rays, the severity of lung infection is monitored using a tool. Many researchers have done in diagnosis of lung infection in an accurate and efficient takes lot of time and inefficient. To overcome these issues, our proposed study implements four cascaded stages. First, for pre-processing, a mean filter is used. Second, texture feature extraction uses principal component analysis (PCA). Third, a modified whale optimization algorithm is used (MWOA) for a feature selection algorithm. The severity of lung infection is detected on the basis of age group. Fourth, image classification is done by using the proposed MWOA with the salp swarm algorithm (MWOA-SSA). MWOA-SSA has an accuracy of 97%, whereas PCA and MWOA have accuracies of 81% and 86%. The sensitivity rate of the MWOA-SSA algorithm is better that of than PCA (84.4%) and MWOA (95.2%). MWOA-SSA outperforms other algorithms with a specificity of 97.8%. This proposed method improves the effective classification of lung affected images from large datasets.

Rapid diagnosis of lung infections

Nanopore sequencing of the sputum metagenome identifies respiratory pathogens in six hours.

Diagnostic accuracy of lung ultrasonography combined with procalcitonin for the diagnosis of pneumonia: a pilot study.

BackgroundThe diagnostic value of lung ultrasonography (LUS) and procalcitonin (PCT) in the diagnosis of lung infections is known. No studies evaluated the combination of LUS and PCT for the diagnosis of pneumonia in the emergency department (ED). We evaluated the diagnostic accuracy of the combination of LUS and PCT in the diagnosis of pneumonia.MethodsPatients with respiratory symptoms of unexplained origin who underwent a chest CT in ED were included in the study if PCT assay was available. LUS was performed before CT and was targeted to the detection of lung consolidations with the morphologic features of pneumonia. A PCT assay was performed at presentation, and cut-off of 0.25 and of 0.5 ng/ml were used to rule-out and rule-in pneumonia. The final diagnosis of pneumonia was established by independent clinicians, on the basis of clinical chart review including CT results.ResultsWe enrolled 128 patients and pneumonia was the final diagnosis in 61 (47.7%). In 38 patients (29.7%) LUS and PCT were negative (PCT < 0.25 ng/ml). The overall accuracy, sensitivity and negative predictive value of LUS/PCT were 88.8, 96.7 and 94.7% respectively. Sensitivity of the LUS/PCT test was significantly superior to LUS alone (85.2%) and PCT alone (73.8%) (p < 0.05 for both). Specificity and positive predictive value of the combination of positivity of LUS/PCT (PCT > 0.5 ng/ml) were 94% and 83.3% respectively. Specificity of LUS/PCT was not significantly different to LUS alone (88.1%) (p = 0.125).ConclusionsThe sensitivity of the combination of LUS with PCT for the diagnosis of pneumonia was significantly superior when compared with the sensitivity of LUS and PCT alone.

Pentraxin 3 levels from bronchoalveolar lavage of critically ill patients predict lung infection

Timely diagnosis of lung infection in critically ill patients is key to guide therapy and avoid futile antibiotic prescription. The gold standard for diagnosis is microbiological culture of bronchoalveolar lavage fluid (BALf). However, it takes up to 48 hours to disclose results. Pentraxin 3 (PTX3) is an acute phase mediator of infection that can be assayed in a few hours. We described a relationship between BALf PTX3 presence and lung infection in acute respiratory distress syndrome patients. The aim of this study was to validate BALf PTX3 as an early marker of lung infection in critically ill patients.

The role of bronchoalveolar lavage in the diagnosis of bacterial pneumonia

Bronchoalveolar lavage (BAL) has become an invaluable diagnostic tool with important clinical implications in both opportunistic infections and the pulmonary pathology of immunologic disease. Until recently, the use of BAL was limited primarily to two areas: the study of interstitial lung diseases and the diagnosis of lung infections by opportunistic microorganisms in severely immunocompromised patients with lung infiltrates. Over the past decade, the use of BAL has been expanded to include the conventional diagnosis of bacterial pneumonia in non-immunocompromised patients. In the past, different clinical studies proposed using BAL to quantify cultures in the sample obtained as a means of increasing the tool's effectiveness. Recent developments have led to a number of newer applications of BAL, such as bronchoscopic BAL, non-bronchoscopic BAL and protected BAL. The most important use of BAL in the non-immunocompromised patient is the diagnosis of pneumonia in the mechanically ventilated patient.

Gram's stain and culture of sputum in the routine management of pulmonary infection.

Gram's stain (GS) and culture of sputum are used routinely for diagnosis of lung infection. We prospectively studied physicians' use of sputum GS and culture for management of lung infection, the correlation between GS and culture in 224 adequate sputum specimens from patients admitted to our hospital over a 15-month period, and its impact on the antibiotic used. GS correlated with sputum culture in one third of the cases in the most predictive group. Gram-negative rods including Haemophilus influenzae formed the majority of the positive cultures and were also the most poorly predicted by GS. Physicians used broad spectrum antibiotics empirically in most cases. These choices were not altered by the culture results in most instances. It may be reasonable to use broad spectrum antibiotics empirically for lung infection. Sputum GS and culture may be helpful in patients at risk for high morbidity and mortality.