Chest Radiographic Images Research Articles

Optimization of convolutional neural network and visual geometry group-16 using genetic algorithms for pneumonia detection.

Pneumonia is still a major global health issue, so effective diagnostic methods are needed. This research proposes a new methodology for improving convolutional neural networks (CNNs) and the Visual Geometry Group-16 (VGG16) model by incorporating genetic algorithms (GAs) to detect pneumonia. The work uses a dataset of 5,856 frontal chest radiography images critical in training and testing machine learning algorithms. The issue relates to challenges of medical image classification, the complexity of which can be significantly addressed by properly optimizing CNN. Moreover, our proposed methodology used GAs to determine the hyperparameters for CNNs and VGG16 and fine-tune the architecture to improve the existing performance measures. The evaluation of the optimized models showed some good performances with purely convolutional neural network archetyping, averaging 97% in terms of training accuracy and 94% based on the testing process. At the same time, it has a low error rate of 0.072. Although adding this layer affected the training and testing time, it created a new impression on the test accuracy and training accuracy of the VGG16 model, with 90.90% training accuracy, 90.90%, and a loss of 0.11. Future work will involve contributing more examples so that a richer database of radiographic images is attained, optimizing the GA parameters even more, and pursuing the use of ensemble applications so that the diagnosis capability is heightened. Apart from emphasizing the contribution of GAs in improving the CNN architecture, this study also seeks to contribute to the early detection of pneumonia to minimize the complications faced by patients, especially children.

Leveraging Deep Learning of Chest Radiograph Images to Identify Individuals at High Risk for Chronic Obstructive Pulmonary Disease.

This study assessed whether deep learning applied to routine outpatient chest X-rays (CXRs) can identify individuals at high risk for incident chronic obstructive pulmonary disease (COPD). Using cancer screening trial data, we previously developed a convolutional neural network (CXR-Lung-Risk) to predict lung-related mortality from a CXR image. In this study, we externally validated CXR-Lung-Risk to predict incident COPD from routine CXRs. We identified outpatients without lung cancer, COPD, or emphysema who had a CXR taken from 2013-2014 at a Mass General Brigham site in Boston, Massachusetts. The primary outcome was 6-year incident COPD. Discrimination was assessed using AUC compared to the TargetCOPD clinical risk score. All analyses were stratified by smoking status. A secondary analysis was conducted in the Project Baseline Health Study (PBHS) to test associations between CXR-Lung-Risk with pulmonary function and protein abundance. The primary analysis consisted of 12,550 ever-smokers (mean age 62·4±6·8 years, 48.9% male, 12.4% rate of 6-year COPD) and 15,298 never-smokers (mean age 63·0±8·1 years, 42.8% male, 3.8% rate of 6-year COPD). CXR-Lung-Risk had additive predictive value beyond the TargetCOPD score for 6-year incident COPD in both ever-smokers (CXR-Lung-Risk + TargetCOPD AUC: 0·73 [95% CI: 0·72-0·74] vs. TargetCOPD alone AUC: 0·66 [0·65-0·68], p<0·01) and never-smokers (CXR-Lung-Risk + TargetCOPD AUC: 0·70 [0·67-0·72] vs. TargetCOPD AUC: 0·60 [0·57-0·62], p<0·01). In secondary analyses of 2,097 individuals in the PBHS, CXR-Lung-Risk was associated with worse pulmonary function and with abundance of SCGB3A2 (secretoglobin family 3A member 2) and LYZ (lysozyme), proteins involved in pulmonary physiology. In external validation, a deep learning model applied to a routine CXR image identified individuals at high risk for incident COPD, beyond known risk factors. The Project Baseline Health Study and this analysis were funded by Verily Life Sciences, San Francisco, California. NCT03154346.

Abstract 4138647: Opportunistic Screening for Cardiovascular Risk Using Chest X-Rays and Deep Learning: Associations with Coronary Artery Disease in the Project Baseline Health Study and Mass General Brigham Biobank

Introduction/Background: We previously demonstrated that an open-source deep learning model (CXR-CVD Risk) can predict 10-year major adverse cardiovascular events (myocardial infarction&amp;stroke), based on a chest radiograph image (CXR). As deep learning models are black boxes, establishing the biological processes the model captures to predict risk may help build understanding and trust in the model. Research Questions/Hypothesis: To test associations between deep-learning derived CXR-CVD Risk and markers of cardiovascular disease including coronary artery calcium (CAC) and stenosis ≥50% on CT, systolic blood pressure (SBP), ankle brachial index (ABI), and prevalent myocardial infarction and stroke. Methods/Approach: We conducted external validation of CXR-CVD-Risk in two cohorts: 1) 2,097 volunteers in the Project Baseline Health Study (PBHS) and 2) 1,644 Mass General Brigham Biobank (MGBB) patients. The CXR-CVD-Risk model estimated 10-year cardiovascular event risk (probability between 0 and 1) from a CXR image. We calculated linear associations with SBP, ABI, and the logarithm of coronary artery calcium and odds ratios for prevalent hypertension, myocardial infarction, stroke, and, in the MGBB, coronary artery stenosis ≥50%. Analyses were adjusted for age, BMI, sex, smoking status, and enrolling site. Results/Data: CXR-CVD-Risk was associated with CAC in both populations (PBHS: 1.11-fold increase, 95% CI: [1.07-1.16]; MGBB: 1.03-fold increase [1.01-1.05] in CAC per 1% increase in CXR-CV-Risk). CXR-CVD-Risk was also associated with SBP (0.59 mmHg increase [0.24-0.93] in SBP per 1% increase in CXR-CV-Risk), history of hypertension, history of myocardial infarction, and stroke. There was an inverse association with ABI (0.010 decrease [0.005-0.014] in ABI) in the PBHS. In the MGBB, CXR-CVD-Risk was associated with coronary artery stenosis ≥50% (OR = 1.004 [1.002-1.007]). All estimates are after covariate adjustment. Conclusion: This deep learning CXR risk score was associated with coronary artery disease (calcium score and stenosis ≥50%), CVD risk factors, and prevalent CVD. Opportunistic screening using CXRs in the electronic record can identify patients at high risk of CVD who may benefit from prevention.

A Novel Image Feature Extraction Based Machine Learning approach for Disease Detection from Chest X-Ray Images

The limitation of feature selection is the biggest challenge for machine learning classifiers in disease classification. This research proposes a novel feature extraction method to extract representative features from medical images, combining extracted features with original image pixel features. Additionally, we propose a new method that uses data values from Andrews's curve function to transform chest x-ray images into spectrograms. The spectrogram images are believed to aid in distinguishing near-similar medical images, such as COVID and pneumonia. The study aims to build an efficient machine learning system that applies the proposed feature extraction method and utilizes spectrogram images for distinguishing near-similar medical images. For experimental analysis, we have used the award winning Kaggle Chest Radiography image dataset. The test results show that among all machine learning classifiers, the logistic regression classifier could correctly distinguish COVID and pneumonia images with a 97.18% test accuracy, a 98.34% detection rate, a 97.8% precision rate, and an AUC value of 0.99 on the test dataset. The machine learning model has learned to distinguish between medical images that appear similar using features found through the proposed feature extraction and spectrogram images. The results also proved that the proposed approach using XGBoost has outperformed state-of-the-art models in recent research studies when (i) binary classification is performed using COVID-19 and Normal Chest x-ray images and (ii) multiclass classification is performed using Normal, COVID and Pneumonia Chest x-ray images.

Automated estimation of thoracic rotation in chest X-ray radiographs: a deep learning approach for enhanced technical assessment.

This study aims to develop an automated approach for estimating the vertical rotation of the thorax, which can be used to assess the technical adequacy of chest X-ray radiographs (CXRs). Total 800 chest radiographs were used to train and establish segmentation networks for outlining the lungs and spine regions in chest X-ray images. By measuring the widths of the left and right lungs between the central line of segmented spine and the lateral sides of the segmented lungs, the quantification of thoracic vertical rotation was achieved. Additionally, a life-size, full body anthropomorphic phantom was employed to collect chest radiographic images under various specified rotation angles for assessing the accuracy of the proposed approach. The deep learning networks effectively segmented the anatomical structures of the lungs and spine. The proposed approach demonstrated a mean estimation error of less than 2° for thoracic rotation, surpassing existing techniques and indicating its superiority. The proposed approach offers a robust assessment of thoracic rotation and presents new possibilities for automated image quality control in chest X-ray examinations. This study presents a novel deep-learning-based approach for the automated estimation of vertical thoracic rotation in chest X-ray radiographs. The proposed method enables a quantitative assessment of the technical adequacy of CXR examinations and opens up new possibilities for automated screening and quality control of radiographs.

Contrastive learning with hard negative samples for chest X-ray multi-label classification

Contrastive learning has gained significant popularity and achieved remarkable success in learning meaningful representations in various domains. This study addresses the significant problem of dependency on labeled data in chest radiography (CXR) images, which are crucial for diagnosing respiratory diseases such as pneumonia but are both time-consuming and expensive to annotate. Despite extensive research, existing studies on CXR largely depend on labeled data. To overcome this challenge, we propose a framework named SURE (similarity, uncertainty, and representativeness) for multi-label classification with hard negatives in contrastive learning. The proposed framework incorporates these aspects when handling hard negatives and effectively combines contrastive learning and downstream tasks for robust representation learning and multi-label classification. Experimental validation using three distinct CXR datasets demonstrates that our approach significantly reduces the dependency on labeled data while achieving notable performance improvements over existing methods, highlighting its potential effectiveness and efficiency in the CXR domain.

A light-weight and generalizable deep learning model for the prediction of COVID-19 from chest X-ray images

The detection of coronavirus disease (COVID-19) using standard laboratory tests, such as reverse transcription polymerase chain reaction (RT-PCR), is time-consuming. Complex medical imaging problems are currently being solved using machine learning and deep learning techniques. Our proposed solution utilizes chest radiography imaging techniques, which have shown to be a faster alternative for detecting COVID-19. We present an efficient and lightweight deep learning architecture for identifying COVID-19 using chest X-ray images which achieve 99.81% accuracy in intra-database testing and 100% accuracy in cross-validation testing on a separate data set. The results demonstrate the potential of our proposed model as a reliable tool for COVID-19 diagnosis using chest X-ray images, which can have a significant impact on improving the efficiency of COVID-19 diagnosis and treatment.

Open Access Data and Deep Learning for Cardiac Device Identification on Standard DICOM and Smartphone-based Chest Radiographs.

Purpose To develop and evaluate a publicly available deep learning model for segmenting and classifying cardiac implantable electronic devices (CIEDs) on Digital Imaging and Communications in Medicine (DICOM) and smartphone-based chest radiographs. Materials and Methods This institutional review board-approved retrospective study included patients with implantable pacemakers, cardioverter defibrillators, cardiac resynchronization therapy devices, and cardiac monitors who underwent chest radiography between January 2012 and January 2022. A U-Net model with a ResNet-50 backbone was created to classify CIEDs on DICOM and smartphone images. Using 2321 chest radiographs in 897 patients (median age, 76 years [range, 18-96 years]; 625 male, 272 female), CIEDs were categorized into four manufacturers, 27 models, and one "other" category. Five smartphones were used to acquire 11 072 images. Performance was reported using the Dice coefficient on the validation set for segmentation or balanced accuracy on the test set for manufacturer and model classification, respectively. Results The segmentation tool achieved a mean Dice coefficient of 0.936 (IQR: 0.890-0.958). The model had an accuracy of 94.36% (95% CI: 90.93%, 96.84%; 251 of 266) for CIED manufacturer classification and 84.21% (95% CI: 79.31%, 88.30%; 224 of 266) for CIED model classification. Conclusion The proposed deep learning model, trained on both traditional DICOM and smartphone images, showed high accuracy for segmentation and classification of CIEDs on chest radiographs. Keywords: Conventional Radiography, Segmentation Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Júdice de Mattos Farina and Celi in this issue.

Evaluation of effectiveness of pre-training method in chest X-ray imaging using vision transformer

ABSTRACT The limited availability of medical images is a major limitation when using deep learning, which requires large amounts of data to improve performance. To address this problem, transfer learning has become the de facto standard, using convolutional neural networks (CNNs) previously trained on natural images, and fine-tuned on medical images. Recently, vision transformers (ViT), which require large annotated medical images, have been studied from various perspectives. In this study, we investigated an effective pre-training method for binary classification of COVID-19 using chest radiography (CXR) images. Our results showed that pre-training on natural images outperformed CXR images using the fine-tuning method. Pre-training on natural images was also able to capture more global features. Furthermore, this trend increased as the number of pre-trained on natural images increased. In summary, these results suggest that the fine-tuning method with a large number of natural images as pre-training had the best discrimination performance.

A Deep Ensemble Dynamic Learning Network for Corona Virus Disease 2019 Diagnosis.

Corona virus disease 2019 is an extremely fatal pandemic around the world. Intelligently recognizing X-ray chest radiography images for automatically identifying corona virus disease 2019 from other types of pneumonia and normal cases provides clinicians with tremendous conveniences in diagnosis process. In this article, a deep ensemble dynamic learning network is proposed. After a chain of image preprocessing steps and the division of image dataset, convolution blocks and the final average pooling layer are pretrained as a feature extractor. For classifying the extracted feature samples, two-stage bagging dynamic learning network is trained based on neural dynamic learning and bagging algorithms, which diagnoses the presence and types of pneumonia successively. Experimental results manifest that using the proposed deep ensemble dynamic learning network obtains 98.7179% diagnosis accuracy, which indicates more excellent diagnosis effect than existing state-of-the-art models on the open image dataset. Such accurate diagnosis effects provide convincing evidences for further detections and treatments.

Automated Detection of Pediatric Foreign Body Aspiration from Chest X-rays Using Machine Learning.

Standard chest radiographs are a poor diagnostic tool for pediatric foreign body aspiration. Machine learning may improve upon the diagnostic capabilities of chest radiographs. The objective is to develop a machine learning algorithm that improves the diagnostic capabilities of chest radiographs in pediatric foreign body aspiration. This retrospective, diagnostic study included a retrospective chart review of patients with a potential diagnosis of FBA from 2010 to 2020. Frontal view chest radiographs were extracted, processed, and uploaded to Google AutoML Vision. The developed algorithm was then evaluated against a pediatric radiologist. The study selected 566 patients who were presented with a suspected diagnosis of foreign body aspiration. One thousand six hundred and eighty eight chest radiograph images were collected. The sensitivity and specificity of the radiologist interpretation were 50.6% (43.1-58.0) and 88.7% (85.3-91.5), respectively. The sensitivity and specificity of the algorithm were 66.7% (43.0-85.4) and 95.3% (90.6-98.1), respectively. The precision and recall of the algorithm were both 91.8% with an AuPRC of 98.3%. Chest radiograph analysis augmented with machine learning can diagnose foreign body aspiration in pediatric patients at a level similar to a read performed by a pediatric radiologist despite only using single-view, fixed images. Overall, this study highlights the potential and capabilities of machine learning in diagnosing conditions with a wide range of clinical presentations. 3 Laryngoscope, 134:3807-3814, 2024.

Deep Ensemble Learning Model for Diagnosis of Lung Diseases from Chest X -Ray Images

Objectives: This study aims to develop a robust medical recognition system using deep learning for the identification of various lung diseases, including COVID-19, pneumonia, lung opacity, and normal states, from chest X-ray images. The focus is on implementing ensemble fixed features learning methods to enhance diagnostic capabilities, contributing to the development of a cost-effective and reliable diagnostic tool for combating the global epidemic of lung disorders. Methods: The study utilizes a Kaggle dataset containing COVID-19 chest radiography images. Raw X-ray images undergo preprocessing for contrast enhancement and noise removal while addressing dataset imbalance through near-miss resampling. Ensemble learning techniques, including two and three-level methods, are employed to harness the strengths of individual base learners—VGG16, InceptionV3, and MobileNetV2. The model's performance is evaluated using metrics such as accuracy, recall, precision, and F1-score. For remote access, a user interface and a shared web link are developed using Python Gradio. Findings: In two-level ensembles, features from base learners are concatenated and classified using a support vector machine. Three-level ensembles use concatenated features classified by three machine learning classifiers, employing a majority voting system for the final prediction. The two-level method achieved 93% accuracy, precision, recall, and F1 score. The three-level ensemble model demonstrates superior performance, achieving 94% accuracy in detecting four lung diseases, namely COVID-19, pneumonia, lung opacity, and normal states. Novelty: This research contributes to the field by showcasing the efficacy of deep learning technology, particularly ensemble learning, in enhancing the detection of lung diseases from raw chest X-ray images. The model employs three modified and efficient pretrained networks for automatic feature extraction, eliminating the need for manual feature engineering. The developed model stands as a promising decision-support tool for healthcare professionals, particularly in low-resource environments. Keywords: Convolutional Neural Network (CNN), Deep Learning (DL), Transfer Learning (TL), Ensemble learning (EL), Fixed feature extraction, Chest X­rays (CXR), Lung diseases

ChestCovidNet: An Effective DL-based Approach for COVID-19, Lung Opacity, and Pneumonia Detection Using Chest Radiographs Images.

Currently used lung disease screening tools are expensive in terms of money and time. Therefore, chest radiograph images (CRIs) are employed for prompt and accurate COVID-19 identification. Recently, many researchers have applied Deep learning (DL) based models to detect COVID-19 automatically. However, their model could have been more computationally expensive and less robust, i.e., its performance degrades when evaluated on other datasets. This study proposes a trustworthy, robust, and lightweight network (ChestCovidNet) that can detect COVID-19 by examining various CRIs datasets. The ChestCovidNet model has only 11 learned layers, eight convolutional (Conv) layers, and three fully connected (FC) layers. The framework employs both the Conv and group Conv layers, Leaky Relu activation function, shufflenet unit, Conv kernels of 3×3 and 1×1 to extract features at different scales, and two normalization procedures that are cross-channel normalization and batch normalization. We used 9013 CRIs for training whereas 3863 CRIs for testing the proposed ChestCovidNet approach. Furthermore, we compared the classification results of the proposed framework with hybrid methods in which we employed DL frameworks for feature extraction and support vector machines (SVM) for classification. The study's findings demonstrated that the embedded low-power ChestCovidNet model worked well and achieved a classification accuracy of 98.12% and recall, F1-score, and precision of 95.75%.

Multimodal approach for early prediction of COVID-19 disease using convolutional neural network

&lt;p&gt;&lt;span&gt;The latest human coronavirus is COVID-19. Chest radiography imaging is essential for screening, early detection, and monitoring COVID-19 infections since the virus resides in the lungs. Classical real time reverse transcriptase polymerase chain reaction (RT-PCR) data and chest X-ray pictures will become more important for COVID-19 identification as the pandemic spreads due to their affordability, wide availability, and infection control benefits, which reduce cross-contamination. This work presents multi-modal hybrid automated approaches to classify COVID-19 illness into three clinical categories: normal, pathogenic, and COVID-19 utilising RT-PCR test data and online chest X-ray datasets. The RT-PCR and chest X-ray image datasets were processed using supervised machine learning and convolutional neural networks (CNN). Together, these measures help us separate COVID-19 patients, those with similar symptoms, and healthy persons. The author improved detection times and classification accuracy with extra tree classifier’s feature selection and openCV’s image sharpening. The proposed approaches were tested using a research dataset. The proposed methods allowed reliable COVID-19 disease categorization for clinical decision-making, with random forest (RF) classifier global precision values of 91.58% on the RT-PCR dataset and CNN model accuracy of 95.46% on improved sharpened images.&lt;/span&gt;&lt;/p&gt;

Domain adaptation via Wasserstein distance and discrepancy metric for chest X-ray image classification

Deep learning technology can effectively assist physicians in diagnosing chest radiographs. Conventional domain adaptation methods suffer from inaccurate lesion region localization, large errors in feature extraction, and a large number of model parameters. To address these problems, we propose a novel domain-adaptive method WDDM to achieve abnormal identification of chest radiographic images by combining Wasserstein distance and difference measures. Specifically, our method uses BiFormer as a multi-scale feature extractor to extract deep feature representations of data samples, which focuses more on discriminant features than convolutional neural networks and Swin Transformer. In addition, based on the loss minimization of Wasserstein distance and contrast domain differences, the source domain samples closest to the target domain are selected to achieve similarity and dissimilarity across domains. Experimental results show that compared with the non-transfer method that directly uses the network trained in the source domain to classify the target domain, our method has an average AUC increase of 14.8% and above. In short, our method achieves higher classification accuracy and better generalization performance.

Imaging of Acute Complications of Community-Acquired Pneumonia in the Paediatric Population-From Chest Radiography to MRI.

The most common acute infection and leading cause of death in children worldwide is pneumonia. Clinical and laboratory tests essentially diagnose community-acquired pneumonia (CAP). CAP can be caused by bacteria, viruses, or atypical microorganisms. Imaging is usually reserved for children who do not respond to treatment, need hospitalisation, or have hospital-acquired pneumonia. This review discusses the imaging findings for acute CAP complications and the diagnostic role of each imaging modality. Pleural effusion, empyema, necrotizing pneumonia, abscess, pneumatocele, pleural fistulas, and paediatric acute respiratory distress syndrome (PARDS) are acute CAP complications. When evaluating complicated CAP patients, chest radiography, lung ultrasonography, computed tomography (CT), and magnetic resonance imaging (MRI) can be used, with each having their own pros and cons. Imaging is usually not needed for CAP diagnosis, but it is essential for complicated cases and follow-ups. Lung ultrasound can supplement chest radiography (CR), which starts the diagnostic algorithm. Contrast-enhanced computed tomography (CECT) is used for complex cases. Advances in MRI protocols make it a viable alternative for diagnosing CAP and its complications.

Multi-label neural architecture search for chest radiography image classification

Multi-label neural architecture search for chest radiography image classification

Detection of fibrosing interstitial lung disease-suspected chest radiographs using a deep learning-based computer-aided detection system: a retrospective, observational study

ObjectivesTo investigate the effectiveness of BMAX, a deep learning-based computer-aided detection system for detecting fibrosing interstitial lung disease (ILD) on chest radiographs among non-expert and expert physicians in the real-world...

CXNet - A Novel approach for COVID-19 detection and Classification using Chest X-Ray image

Preliminary screenings are essential to limit the community-propagating nature of COVID-19. COVID-19 patients’ lung health status can be assessed by chest radiographic imaging, such as computed tomography scanning or X-ray images. Therefore, it is preferable to use machine learning approaches to help identify COVID-19 by using chest radiographs. This research presents an image-based diagnosis of COVID-19 disease using deep learning. The presented work uses chest X-ray images because the X-ray imaging facility is widely available in almost all healthcare facilities. It is less costly and has a more negligible radiation effect than computed tomography (CT) scan images. This study employed a custom convolutional neural network (CNN) model and pre- trained deep neural architectures such as resnet50, DenseNet121, VGG16, and VGG19 to classify COVID-19 chest X-ray images. The proposed model has been evaluated on real-life data, and an accuracy of 98% has been achieved. The proposed model can be recommended to health care professionals as a trustworthy diagnostic decision-making system for COVID-19 detection.

Efficacy of a topical formulation containing eprinomectin, esafoxolaner and praziquantel (NexGard® Combo) in the treatment of natural respiratory capillariosis of cats.

Feline pulmonary capillariosis is a significant disorder due to its distribution and clinical impact. This study evaluated the safety and efficacy of two administrations 28 days apart of a topical solution containing esafoxolaner, eprinomectin and praziquantel (NexGard® Combo) in treating Eucoleus aerophilus (syn. Capillaria aerophila) infection in naturally infected cats. Cats were allocated to two groups: G1 cats (n=23) received two treatments at study days (SDs) 0 and 28 (±2) and were evaluated for 6 weeks, and G2 cats (n=17) served as a negative control for 6 weeks and were then treated twice on SDs 42 (±2) and 70 (±2), allowing for an additional 6-week assessment of efficacy. Each cat was subjected to McMaster coproscopy at SDs -7/0, 28 (±2) and 42 (±2) for both groups, 70 (±2) and 84 (±2) only for G2. Clinical examination and chest radiographic images were performed at SDs 0, 28 (±2) and 42 (±2) for G1 and G2, 70 (±2) and 84 (±2) only for G2. The comparison of EPG (eggs per gram of feces), clinical (CS), and radiographic scores (RS) at each time-point was used as a criterion. The efficacy based on the EPG reduction was 99.5% (G1) and 100% (G2) after two administrations of NexGard® Combo 2 weeks apart. At SD 0, no significant differences for CS and RS were recorded between G1 and G2, while a significant reduction (p<0.05) was observed post-treatment for CS, RS, oculo-nasal discharge, auscultation noises, and cough. Two doses of NexGard® Combo 28 days apart stopped egg shedding and significantly improved clinical alterations in cats infected by E. aerophilus.