Chest X-ray Research Articles

Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study

BackgroundThe digitisation of healthcare records has generated vast amounts of unstructured data, presenting opportunities for improvements in disease diagnosis when clinical coding falls short, such as in the recording of patient symptoms. This study presents an approach using natural language processing to extract clinical concepts from free-text which are used to automatically form diagnostic criteria for lung cancer from unstructured secondary-care data.MethodsPatients aged 40 and above who underwent a chest x-ray (CXR) between 2016 and 2022 were included. ICD-10 and unstructured data were pulled from their electronic health records (EHRs) over the preceding 12 months to the CXR. The unstructured data were processed using named entity recognition to extract symptoms, which were mapped to SNOMED-CT codes. Subsumption of features up the SNOMED-CT hierarchy was used to mitigate against sparse features and a frequency-based criteria, combined with univariate logarithmic probabilities, was applied to select candidate features to take forward to the model development phase. A genetic algorithm was employed to identify the most discriminating features to form the diagnostic criteria.Results75002 patients were included, with 1012 lung cancer diagnoses made within 12 months of the CXR. The best-performing model achieved an AUROC of 0.72. Results showed that an existing ‘disorder of the lung’, such as pneumonia, and a ‘cough’ increased the probability of a lung cancer diagnosis. ‘Anomalies of great vessel’, ‘disorder of the retroperitoneal compartment’ and ‘context-dependent findings’, such as pain, statistically reduced the risk of lung cancer, making other diagnoses more likely. The performance of the developed model was compared to the existing cancer risk scores, demonstrating superior performance.ConclusionsThe proposed methods demonstrated success in leveraging unstructured secondary-care data to derive diagnostic criteria for lung cancer, outperforming existing risk tools. These advancements show potential for enhancing patient care and results. However, it is essential to tackle specific limitations by integrating primary care data to ensure a more thorough and unbiased development of diagnostic criteria. Moreover, the study highlights the importance of contextualising SNOMED-CT concepts into meaningful terminology that resonates with clinicians, facilitating a clearer and more tangible understanding of the criteria applied.

Obstructive jaundice of unusual cause.

The most prevalent tumor in women worldwide is breast cancer. Although liver metastases are relatively frequent, pancreatic involvement is unusual. In the case of jaundice in patients with a history of neoplasia, the initial diagnosis is focused on ruling out hepatic infiltration. However, it is essential to consider other, less common but related etiologies of biliary obstruction. The most frequent pancreatic metastatic involvement is usually as nodular lesions; nevertheless, diffuse parenchymal infiltration is also possible, as illustrated in the following case.

Epidemiological Insights and Diagnostic Strategies of Extrarespiratory Tuberculosis: A Five-Year Retrospective Study in Clinic of Pneumology, Târgu Mureș

Background: Tuberculosis remains one of the biggest global public health problems today. The objective of this study was to evaluate the diagnostic methods, clinical outcomes, patient compliance, and mortality rates in patients diagnosed with extrarespiratory tuberculosis. Methods: 105 cases of extrarespiratory tuberculosis were analyzed over a five-year period (2018–2023). Data from medical records were reviewed and processed. Diagnostic methods included Ziehl–Nielsen staining, Löwenstein–Jensen cultures, GeneXpert, and histopathological analysis. Diagnosis was supplemented by a specialist organ examination and, in cases with concurrent pulmonary involvement, by a chest X-ray and sputum examination. For negative cases, a probabilistic diagnosis was made. Results: Most patients presented pleural TB (38%), osteo-articular TB (26.67%), and ganglionary TB (19%). Patients were mostly men (56.19%), in the 18–40 years-old category (40%), and lived in rural areas (61%). In total, 94.29% were newly diagnosed and most observed comorbidites were chronic smoking (11.37%), chronic lung diseases (10.20%), and malnutrition (9.02%). Moreover, 68% had a negative microscopic examination, while 55% had negative cultures on Löwenstein–Jensen. Conclusions: This study highlights the importance of a multi-modal approach to diagnosing extrarespiratory tuberculosis, especially in negative bacteriological and histopathological results. Imaging, combined with clinical and epidemiological data, is critical for a probabilistic diagnosis. GeneXpert proved useful in difficult cases. This study emphasizes the need for a comprehensive diagnostic strategy to effectively manage extrarespiratory tuberculosis.

Diagnostic ecologies: Medical standards, tinkering, and worker health in Turkey

AbstractIn Turkey's occupational health system, doctors must use the International Labor Organization's (ILO) standards to classify the chest radiographs of workers at risk of lung diseases caused by dust exposure. Yet these standards do not provide a uniformity of care within the tripartite structure of the occupational health system, which divides disease surveillance, disease diagnosis, and worker compensation into distinct silos. This division often produces ambiguity and unpredictable outcomes for occupational disease claims. The traffic of diagnostic decisions among workplaces and medico‐legal institutions—what I refer to as diagnostic ecologies—shapes medical knowledge. The tripartite organization of the occupational health system in Turkey makes the evaluation of chest radiographs a space where professional expertise and professional ethics are constantly negotiated. A focus on diagnostic ecologies illustrates how disease ontology is distributed across the occupational health system's components.

Use of ultrasonography in the diagnosis of pneumonia in intensive care patients

Aims: A significant portion of respiratory system infections seen in intensive care units is ventilator-associated pneumonia, which has a high mortality rate and diagnosis may be delayed. Bedside lung ultrasonography offers the advantages of standard diagnostic methods as chest radiography or thorax tomography. We aim to evaluate the bedside lung ultrasonography correlation with the chest radiography or thorax tomography Methods: It was conducted prospectively on 60 patients between the ages of 18-85 who were admitted to intensive care with respiratory failure within an 8-month period. Anterioposterior chest radiographs were taken on the first day of mechanical ventilation for the patients included in the study. Ultrasonographic (USG) examination was performed separately for both hemithoraxes and recorded digitally. Simultaneously with the ultrasonographic examination, PEEP, FiO2, blood gas examination results and the highest body temperatures in the last 24 hours were recorded. The quality and quantity of tracheal secretions were evaluated, and sampling was performed for complete blood examination and tracheal aspirate culture-antibiogram. Lung injury score (LIS) and pulmonary infection score (CPIS) were calculated from the data obtained. In this process, independent of the research, the same day examination results of patients who required thorax tomography (CT) for diagnosis and treatment planning were evaluated together with USG and chest radiography. Tomographic examinations were evaluated by a radiologist. Results: In the examination of 120 hemithoraxes of 60 patients we included in the study, we were able to detect 74.17% of the pathological images obtained with chest radiography and ultrasonographic examination with bedside ultrasonography and 70.84% with chest radiography. Of the 20 patients who underwent tomographic evaluation, pathology was observed in 40 hemithoraxes in 92.5% by tomography, in 85% by ultrasonography, and in 75% by chest radiography. While isolated consolidation was detected equally on USG and CT imaging, there was a high false-positive rate of 48% on chest radiography. 58.8% of the patients with consolidation detected by CT, we observed that there was growth in the tracheal aspirate of 56.2% of the patients whose ultrasonographic examination revealed consolidation. Conclusion: Bedside lung ultrasonography is a fast, non-invasive, repeatable and reliable diagnostic method in patients followed in intensive care, and is compatible with traditionally used laboratory and clinical parameters. This reveals that USG, which is known to have other advantages such as cost, applicability, and not using radiopaque, will become an indispensable examination for ICU.

Emerging multifaceted application of artificial intelligence in chest radiography: a narrative review

Emerging multifaceted application of artificial intelligence in chest radiography: a narrative review

A hybrid classification approach for automatically recognizing COVID-19 using deep transfer learning using chest radiographs

Coronavirus 2019 causes COVID-19, a worldwide epidemic. It endangers millions globally. Early illness detection improves recovery and control. X-ray image processing is used to categorise and identify COVID-19 in the present study. Preprocessing, feature extraction using local binary pattern (LBP) and edge orient histogram (EOH), and classification utilising K-nearest neighbour (KNN), Navie Bayes, support vector machine (SVM), and transfer learning convolution neural networks (CNNs) are some of the stages that are implemented in the process. Other phases in the process include preprocessing, feature extraction, and preprocessing. LBP+KNN, EOH+KNN, LBP+SVM, EOH +SVM, CNN+LBP, and CNN+EOH are the outputs derived from the combinations of feature extraction operators and classifiers. Other possible outcomes are CNN+EOH and CNN+LBP. A total of 4,000 pictures were used as the basis for conducting an analysis of the performance of six different models. In order to train the models, 10-fold cross-validation was used, and their accuracy was measured accordingly. The evaluation results indicate a high level of accuracy in diagnosis, ranging from 90.2% to 97.56%. The CNN+LBP and CNN+EOH models have demonstrated superior performance compared to other models, achieving average accuracies ranging from 96.66% and 98.54%.

UniMiSS+: Universal Medical Self-Supervised Learning From Cross-Dimensional Unpaired Data.

Self-supervised learning (SSL) opens up huge opportunities for medical image analysis that is well known for its lack of annotations. However, aggregating massive (unlabeled) 3D medical images like computerized tomography (CT) remains challenging due to its high imaging cost and privacy restrictions. In our pilot study, we advocated bringing a wealth of 2D images like X-rays as compensation for the lack of 3D data, aiming to build a universal medical self-supervised representation learning framework, called UniMiSS. Especially, we designed a pyramid U-like medical Transformer (MiT) as the backbone to make UniMiSS possible to perform SSL with both 2D and 3D images. UniMiSS surpasses current 3D-specific SSL in effectiveness and versatility, excelling in various downstream tasks and overcoming the limitations of dimensionality. However, the initial version did not fully explore the anatomical correlations between 2D and 3D images due to the absence of paired multi-modal patient data. In this extension, we introduce UniMiSS+, which leverages digitally reconstructed radiographs (DRR) technology to simulate X-rays from CT volumes, providing access to paired data. Benefiting from the paired group, we introduce an extra pair-wise constraint to boost the cross modality correlation learning, which also can be adopted as a cross dimension regularization to further improve the representations. We conduct expensive experiments on multiple 3D/2D medical image analysis tasks, including segmentation and classification. The results show that our UniMiSS+ achieves promising performance on various downstream tasks, not only outperforming ImageNet pre-training and other advanced SSL counterparts but also improving the predecessor UniMiSS pre-training.

Deep learning model for detection acute cardiogenic pulmonary edema in cases of preeclampsia

<span lang="EN-US">The physiological changes during the pregnancy period increase the risk of developing pulmonary edema and acute respiratory failure. This condition falls under critical medical emergencies associated with maternal mortality. This study utilized a convolutional neural networks (CNN) architectural model employing chest Xray dataset images. CNN utilizes the convolution process by moving a convolutional kernel of a certain size across an image, allowing the computer to derive new representative information from the multiplication of portions of the image with the utilized filter.</span><span lang="EN-US">To simplify, the vanishing gradient issue occurs when information dissipates before reaching its destination due to the lengthy path between input and output layers. This study was developed model for detection acute cardiogenic pulmonary Edema in pre-eclampsia cases using chest Xray images, implemented using PyTorch, Keras, and MxNet. The validated model achieved its optimum with accuracy 90.65% and binary cross-entropy loss (BCELoss) value of 0.4538. It exhibited an improved sensitivity value of 83.514% using a 5% dataset and a specificity value of 57.273%. This indicates an increase in sensitivity value by 83.514% using a 5% data set and a specificity value of 57.273%. The research results demonstrate an improvement in accuracy compared to several similar studies that also utilized CNN models.</span>

Pneumonia stage analyzes through image processing

A physical examination and diagnostic imaging techniques including lung biopsies, ultrasounds, and chest X-rays are typically used to make the diagnosis of pneumonia infection, an infectious disease that has the potential to be life-threatening. The objective of this research is to categorize the stages of pneumonia through image processing methods. Before that, an ensemble model for diagnosing pneumonia infections is created utilizing the transfer learning algorithms ResNet50V2 and DenseNet201. The 5,857 images were taken from the PAUL MOONEY dataset for this research. The proposed ensemble averaging model recognizes lung infection appropriately and accurately. By applying a contour detection approach, the left and right chests are separated and the affected pixels from there to analyze the stage of pneumonia. It is very crucial to identify the stage for treatment purposes.

TGPO-WRHNN: Two-stage Grad-CAM-guided PMRS Optimization and weighted-residual hypergraph neural network for pneumonia detection

Recent studies based on chest X-ray images have shown that pneumonia can be effectively detected using deep convolutional neural network methods. However, these methods tend to introduce additional noise and extract only local feature information, making it difficult to express the relationship between data objects. This study proposes a Two-stage Grad-CAM-guided pre-trained model and removal scheme (PMRS) Optimization and weighted-residual hypergraph neural network model (TGPO-WRHNN). First, our model extracts high-dimensional features using the TGPO module to capture both global and local information from an image. Second, we propose a new distance-based hypergraph construction method (DBHC) to amplify the difference between distances and better distinguish the relation between nearby and distant neighbors. Finally, we introduce a weighted-residual hypergraph convolution module (WRHC) to ensure the model maintains excellent performance, even at deeper levels. Our model was tested on a dataset of chest X-ray images of pediatric patients aged 1 to 5 years at the Guangzhou Women and Children’s Medical Centre by 10-fold cross-validation. The results showed that the method achieved a maximum accuracy of 98.97%, precision of 98.86%, recall of 98.43%, F1 score of 98.64%, and AUC of 99.78%. Compared to other existing models, our model demonstrated improvements of 0.87%, 0.86%, 0.16%, and 0.38% in terms of accuracy, precision, F1 score, and AUC, respectively.

Pneumonia detection on x-ray image using improved depthwise separable convolutional neural networks

A single neural network model cannot capture intricate and diverse features due to its ability to learn only a finite set of patterns from the data. Additionally, training and utilising a single model can be computationally demanding. Experts propose incorporating multiple neural network models to address these constraints to extract complementary attributes. Previous research has highlighted challenges network models face, including difficulties in effectively capturing highly detailed spatial features, redundancy in network structure parameters, and restricted generalisation capabilities. This study introduces an innovative neural network architecture that combines the Xception module with the inverse residue structure to tackle these issues. Considering this, the paper presents a model for detecting pneumonia in X-ray images employing an improved depthwise separable convolutional network. This network architecture integrates the inverse residual structure from the MobileNetV2 model, using the rectified linear unit (ReLU) non-linear activation function throughout the entire network. The experimental results show an impressive recognition rate with a test accuracy of 97.24% on the chest x-ray dataset. This method can extract more profound and abstract image features while mitigating overfitting issues and enhancing the network's generalisation capacity.

A case of spontaneous pneumomediastinum in a triathlete.

Spontaneous pneumomediastinum is an infrequent condition typically secondary to smoking, illicit drug use, or asthma. The condition often follows barotrauma or bronchial hyperactivity, causing alveolar destruction and air trapping within the mediastinum. Rarely, it may present following strenuous exercise, particularly in tall, thin males, resembling the presentation of pneumothorax. In this case, a 23-year-old male with no prior medical history presented to the emergency department with chest pain and dyspnea following intense training for a triathlon. Following a normal chest x-ray, a high-resolution computed tomography imaging revealed the presence of spontaneous pneumomediastinum. The patient was admitted for observation and managed conservatively with close monitoring for potential complications such as pneumothorax or pneumopericardium. Emergency physicians should maintain a high index of suspicion for spontaneous pneumomediastinum in patients presenting with acute chest pain and dyspnea, especially in the absence of significant comorbidities. This condition can mimic other cardiopulmonary emergencies, necessitating its inclusion in the differential diagnosis to ensure accurate and timely management.

Utilization of Deep Learning Models for the Early Diagnosis of COVID-19 through Chest Radiography

This study aims to evaluate the earlier detection of COVID-19 through deep-learning chest radiography models. The discussion starts with the impact of SARS-CoV-2 globally and the demand for early indication of the risk of handling infection. It outlines pathogenesis and clinical features of COVID-19, puts forth shortcomings of conventional diagnostics, and elaborates on its increasing role as a choice of preferred diagnostic technique in the form of chest radiography. In this study, a deep residual learning-based convolutional neural network architecture of 49 layers is proposed and its performance is compared with several advanced transfer learning models, like ResNet-50, VGG-16, VGG-19, and Inception-v3. The dataset used the chest radiographs of the patients of the COVID-19,for whom diverse enhancement techniques such as data augmentation, resolution optimization, and region of interest (ROI) selection were applied to improve the model's diagnostic performance. The methodology section describes preparation and preprocessing of the dataset followed by the proposed CNN model configuration that aims to evaluate the models concerning the performance metrics of accuracy, sensitivity, specificity, and F1-score. Comparative results show that the 49-layer CNN obtained an accuracy at the value of 97.0%, sensitivity at 98.41%, specificity at 88.45%, and an F1-score of 92.22%. This reflects that the proposed model outperformed the best-known state-of-the-art methods. The study places great emphasis on diagnostic approaches not only towards medical diagnosis but more so onto the transformative potential in redefining AI integration into healthcare systems as forces of change in addressing health matters such as the COVID-19 pandemic in global health.

Optimizing Cardiomegaly Detection: A Random Forest Approach to Processed Chest X-ray Imagery

This study explores the application of a Random Forest Classifier for the automated detection of Cardiomegaly from chest X-ray images, utilizing a dataset processed and derived from the NIH Chest X-ray Dataset. Given the crucial need for accurate and timely diagnosis of Cardiomegaly to inform appropriate treatment decisions, this research aims to determine the efficacy of machine learning models in augmenting diagnostic processes. Employing image pre-processing techniques such as Sobel filtering for edge detection and Hu Moments for feature extraction, the study enhances the input features for the model. The performance of the classifier was evaluated using a 5-fold cross-validation approach, yielding results with average accuracy, precision, recall, and F1-scores ranging approximately between 52% and 54%. These findings suggest a moderate level of reliability and consistency, indicating the potential utility of ensemble machine learning methods in medical imaging analysis. However, the variability in performance across different data subsets highlights the challenges and necessitates further optimization. This research contributes to the ongoing discourse on integrating machine learning into clinical settings, demonstrating the potential benefits and current limitations. Future research is recommended to expand the dataset variety, integrate advanced deep learning methodologies, and rigorously test these models in clinical environments. The findings hold significant implications for the development of automated diagnostic tools in healthcare, potentially leading to enhanced diagnostic accuracy and efficiency.

Navigating laboratory investigations for an accurate assessment of community-acquired pneumonia: Case report

According to recent findings, demographic characteristics, seasonal fluctuations, and geographic regions are factors for the community-acquired pneumonia. Community acquired pneumonia is a non-hospital acquired lung parenchymal infection caused by gram-negative bacteria “Pseudomonas aeruginosa” which is transmitted through inhaling infected droplets. Here, we are reporting a case of geriatric patient with chief complaints of cough in the past 20 days, shortness of breath, tachycardia, tachypnoea, fever, and chest pain from 10 days. physician was suggested go for further investigations and lab reports like complete blood picture count, ESR test, sputum culture test and radiographic findings like Chest X-ray, chest computed tomography. Standard treatment includes antibiotics like Levofloxacin, Azithromycin and antihypertensive like Telmisartan, and mucolytics like Ambroxol syrup and other medications like N-Acetyl Cysteine, levocetirizine. If early diagnosis and early treatment were initiated, then the progression of diseases would have been stopped and then the Patient was discharged with stable condition, but she must come for the follow-up sessions like OP sessions. If the patient follows the life-style modifications and precautions like practice good hygiene, take enough rest, consume healthy diet, the quality of life will be improved.

SMALL BOWEL OBSTRUCTION DUE TO MECKELS DIVERTICULUM IN ADULTS: CASE REPORT

Meckels diverticulum is the partial persistence of the omphalomesenteric duct during the seventh week of gestation [1]. It is the most common congenital anomaly of the gastrointestinal tract with a slight male predominance [1]. It is rare and is encountered in 2 to 4% of the population [2]. Meckels diverticulum is usually, but it can be revealed by complications such as: intestinal obstruction, perforation, fistula and tumor degeneration [3].We report in this work the clinical case and management of small bowel volvulus on Meckels diverticulum, observed in theUniversity Hospital center of Marrakech in a 19-year-old adult in March 2023, this is a patient without medical history admitted to the emergency with acute abdomen made up of abdominal pain, vomiting and fever. The physical examination aimed abdominal bloating and generalized defense. Biology shows an inflammatory syndrome.Abdominal Computed tomography scan in the emergency shows a distension of the small bowel measuring 36mm, with hydroaeric levels, no disparity in caliber, associated with moderate peritoneal effusion.The patient was operated by median laparotomy. Surgical exploration revealed distension of the bowel upstream of a flange taking up an inflamed Meckels diverticulum, 6cm long and 2cm in diameter, situated on the anti-mesenteric edge, 2.30 meters from the Treitz angle and 70cm from the ileo-caecal junction, adhering to the root of the mesentery. It was around this diverticulum that the small intestine had volvulated but was viable. The appendix was normal size. The surgical procedure consisted of a losangicdiverticulectomy preserving the supporting loop of bowel and transverse suture of the loop of bowel using separate stitches.Postoperative recovery was straightforward. Discharge was authorized on the 6th day.Histo-pathological examination showed fibrous tissue with a dense, diffuse inflammatory infiltrate, compatible with a lesion of non-specific gastric diverticulitis.It is important to be aware of the complications of Meckels diverticulum in the presence of acute abdominal pain, to guide surgical management as effectively as possible.

Lung abscess caused by Streptococcus constellatus: Case report

This case report presents a detailed case study of Lung abscess caused by Streptococcus constellatus. This case underscores the critical role of accurate microbiological diagnosis in the effective management of lung abscesses, highlighting the necessity for precise identification and targeted treatment strategies. A 47-year-old male who exhibited persistent fever and mucopurulent cough, leading to a visit to the Emergency Department of a local hospital in Riobamba, Ecuador. Initially, the patient was diagnosed with pneumonia and treated with moxifloxacin and itraconazole. However, as his condition deteriorated, he was transferred to a specialty hospital in Quito, Ecuador. Chest X-rays identified a cavitary lesion, which was further confirmed by CT chest imaging to be a lung abscess. Additional diagnostic work through CT-guided biopsy and culture confirmed the presence of Streptococcus constellatus. The patient's treatment regimen included targeted antibiotic therapy with piperacillin-tazobactam, resulting in a six-week hospitalization. The patient's condition significantly improved, and he was subsequently discharged.

Classification of Pneumonia, Tuberculosis and Covid-19 from Chest X-Ray Images Using Convolution Neural Network Model

Accurate and timely diagnosis of respiratory ailments like pneumonia, tuberculosis (TB), and COVID-19 is pivotal for effective patient care and public health interventions. Deep learning algorithms have emerged as potent tools in medical image classification, offering promise for automated diagnosis and screening. This study presents a deep learning-based approach for categorizing chest X-ray images into three classes: pneumonia, tuberculosis, and COVID-19. Utilizing convolutional neural networks (CNNs) as the primary architecture, owing to their ability to automatically extract relevant features from raw image data. The proposed model is trained on a sizable dataset of chest X-ray images annotated with ground truth labels for pneumonia, TB, and COVID-19. Extensive experiments are conducted to evaluate the model's performance in terms of classification accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Furthermore, we compare the performance of our deep learning model with traditional machine learning approaches and assess its generalization ability on an independent test set. Our findings demonstrate that the proposed deep learning model achieves high accuracy in classifying chest X-ray images of pneumonia, TB, and COVID-19, outperforming traditional methods and showing potential for clinical deployment as a screening tool, especially in resource-limited settings.

Lightweight convolutional neural network for chest X-ray images classification

In this study, we developed a lightweight and rapid convolutional neural network (CNN) architecture for chest X-ray images; it primarily consists of a redesigned feature extraction (FE) module and multiscale feature (MF) module and validated using publicly available COVID-19 datasets. Experiments were conducted on multiple updated versions of the COVID-19 Radiography Database, a publicly accessible dataset on Kaggle. The database contained images categorized into three classes: COVID-19 coronavirus, viral or bacterial pneumonia, and normal. The results revealed that the proposed method achieved a training accuracy of 99.85% and a validation accuracy of 96.28% when detecting the three classes. In the test set, the optimal results were 96.03% accuracy for COVID-19, 97.10% accuracy for viral or bacterial pneumonia, and 97.86% accuracy for normal individuals. By reducing the computational requirements and improving the speed of the model, the proposed method can achieve real-time, low-error performance to help medical professionals with rapid diagnosis of COVID-19.