Could automated analysis of chest X-rays detect early bronchiectasis in children?
Ontology highlight
ABSTRACT:
SUBMITTER: Clark AR
PROVIDER: S-EPMC8080192 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAirspace disease as seen on chest X-rays is an important point in triage for patients initially presenting to the emergency department with suspected COVID-19 infection. The purpose of this study is to evaluate a previously trained interpretable deep learning algorithm for the diagnosis and prognosis of COVID-19 pneumonia from chest X-rays obtained in the ED.MethodsThis retrospective study included 2456 (50% RT-PCR positive for COVID-19) adult patients who received both a chest X-ray and SARS-CoV-2 RT-PCR test from January 2020 to March of 2021 in the emergency department at a single U.S.InstitutionA total of 2000 patients were included as an additional training cohort and 456 patients in the randomized internal holdout testing cohort for a previously trained Siemens AI-Radiology Companion deep learning convolutional neural network algorithm. Three cardiothoracic fellowship-trained radiologists systematically evaluated each chest X-ray and generated an airspace disease area-based severity score which was compared against the same score produced by artificial intelligence. The interobserver agreement, diagnostic accuracy, and predictive capability for inpatient outcomes were assessed. Principal statistical tests used in this study include both univariate and multivariate logistic regression.ResultsOverall ICC was 0.820 (95% CI 0.790-0.840). The diagnostic AUC for SARS-CoV-2 RT-PCR positivity was 0.890 (95% CI 0.861-0.920) for the neural network and 0.936 (95% CI 0.918-0.960) for radiologists. Airspace opacities score by AI alone predicted ICU admission (AUC = 0.870) and mortality (0.829) in all patients. Addition of age and BMI into a multivariate log model improved mortality prediction (AUC = 0.906).ConclusionThe deep learning algorithm provides an accurate and interpretable assessment of the disease burden in COVID-19 pneumonia on chest radiographs. The reported severity scores correlate with expert assessment and accurately predicts important clinical outcomes. The algorithm contributes additional prognostic information not currently incorporated into patient management.
| S-EPMC9301895 | biostudies-literature
Project description:Acute respiratory distress syndrome (ARDS) is a life-threatening lung injury with global prevalence and high mortality. Chest x-rays (CXR) are critical in the early diagnosis and treatment of ARDS. However, imaging findings may not result in proper identification of ARDS due to a number of reasons, including nonspecific appearance of radiological features, ambiguity in a patient's case due to the pathological stage of the disease, and poor inter-rater reliability from interpretations of CXRs by multiple clinical experts. This study demonstrates the potential capability of methodologies in artificial intelligence, machine learning, and image processing to overcome these challenges and quantitatively assess CXRs for presence of ARDS. We propose and describe Directionality Measure, a novel feature engineering technique used to capture the "cloud-like" appearance of diffuse alveolar damage as a mathematical concept. This study also examines the effectiveness of using an off-the-shelf, pretrained deep learning model as a feature extractor in addition to standard features extracted from the histogram and gray-level co-occurrence matrix (GLCM). Data was collected from hospitalized patients at Michigan Medicine's intensive care unit and the cohort's inclusion criteria was specifically designed to be representative of patients at risk of developing ARDS. Multiple machine learning models were used to evaluate these features with 5-fold cross-validation and the final performance was reported on a hold-out, temporally distinct test set. With AdaBoost, Directionality Measure achieved an accuracy of 78% and AUC of 74% - outperforming classification results using features from the histogram (75% accuracy and 73% AUC), GLCM (76% accuracy and 73% AUC), and ResNet-50 (77% accuracy and 73% AUC). Further experimental results demonstrated that using all feature sets in combination achieved the best overall performance, yielding an accuracy of 83% and AUC of 79% with AdaBoost. These results demonstrate the potential capability of using the proposed methodologies to complement current clinical analysis for detection of ARDS from CXRs.
| S-EPMC9169678 | biostudies-literature
Project description:BackgroundPneumothorax can precipitate a life-threatening emergency due to lung collapse and respiratory or circulatory distress. Pneumothorax is typically detected on chest X-ray; however, treatment is reliant on timely review of radiographs. Since current imaging volumes may result in long worklists of radiographs awaiting review, an automated method of prioritizing X-rays with pneumothorax may reduce time to treatment. Our objective was to create a large human-annotated dataset of chest X-rays containing pneumothorax and to train deep convolutional networks to screen for potentially emergent moderate or large pneumothorax at the time of image acquisition.Methods and findingsIn all, 13,292 frontal chest X-rays (3,107 with pneumothorax) were visually annotated by radiologists. This dataset was used to train and evaluate multiple network architectures. Images showing large- or moderate-sized pneumothorax were considered positive, and those with trace or no pneumothorax were considered negative. Images showing small pneumothorax were excluded from training. Using an internal validation set (n = 1,993), we selected the 2 top-performing models; these models were then evaluated on a held-out internal test set based on area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV). The final internal test was performed initially on a subset with small pneumothorax excluded (as in training; n = 1,701), then on the full test set (n = 1,990), with small pneumothorax included as positive. External evaluation was performed using the National Institutes of Health (NIH) ChestX-ray14 set, a public dataset labeled for chest pathology based on text reports. All images labeled with pneumothorax were considered positive, because the NIH set does not classify pneumothorax by size. In internal testing, our "high sensitivity model" produced a sensitivity of 0.84 (95% CI 0.78-0.90), specificity of 0.90 (95% CI 0.89-0.92), and AUC of 0.94 for the test subset with small pneumothorax excluded. Our "high specificity model" showed sensitivity of 0.80 (95% CI 0.72-0.86), specificity of 0.97 (95% CI 0.96-0.98), and AUC of 0.96 for this set. PPVs were 0.45 (95% CI 0.39-0.51) and 0.71 (95% CI 0.63-0.77), respectively. Internal testing on the full set showed expected decreased performance (sensitivity 0.55, specificity 0.90, and AUC 0.82 for high sensitivity model and sensitivity 0.45, specificity 0.97, and AUC 0.86 for high specificity model). External testing using the NIH dataset showed some further performance decline (sensitivity 0.28-0.49, specificity 0.85-0.97, and AUC 0.75 for both). Due to labeling differences between internal and external datasets, these findings represent a preliminary step towards external validation.ConclusionsWe trained automated classifiers to detect moderate and large pneumothorax in frontal chest X-rays at high levels of performance on held-out test data. These models may provide a high specificity screening solution to detect moderate or large pneumothorax on images collected when human review might be delayed, such as overnight. They are not intended for unsupervised diagnosis of all pneumothoraces, as many small pneumothoraces (and some larger ones) are not detected by the algorithm. Implementation studies are warranted to develop appropriate, effective clinician alerts for the potentially critical finding of pneumothorax, and to assess their impact on reducing time to treatment.
| S-EPMC6245672 | biostudies-literature
Project description:IntroductionChest x-rays (CXRs) are the most frequent radiological tests performed in the intensive care unit (ICU). However, the utility of performing daily routine CXRs is unclear.MethodsWe searched Medline and Embase (1948 to March 2011) for randomized and quasi-randomized controlled trials (RCTs) and before-after observational studies comparing a strategy of routine CXRs to a more restrictive approach with CXRs performed to investigate clinical changes among critically ill adults or children. In duplicate, we extracted data on the CXR strategy, study quality and clinical outcomes (ICU and hospital mortality; duration of mechanical ventilation and ICU and hospital stay).ResultsNine studies (39,358 CXRs; 9,611 patients) were included in the meta-analysis. Three trials (N = 870) of moderate to good quality provided information on the safety of a restrictive routine CXR strategy; only one trial systematically assessed for missed findings. Pooled data from trials showed no evidence of effect of a restrictive approach on ICU mortality (risk ratio [RR] 1.04, 95% confidence interval [CI] 0.84 to 1.28, P = 0.72; two trials, N = 776), hospital mortality (RR 0.98, 95% CI 0.68 to 1.41, P = 0.91; two trials, N = 259), ICU length of stay (weighted mean difference [WMD] -0.86 days, 95% CI -2.38 to 0.66 days, P = 0.27; three trials, N = 870), hospital length of stay (WMD -2.50 days, 95% CI -6.62 to 1.61 days, P = 0.23; two trials, N = 259), or duration of mechanical ventilation (WMD -0.30 days, 95% CI -1.48 to 0.89 days, P = 0.62; three trials, N = 705). Adding data from six observational studies, one of which systematically screened for missed findings, gave similar results.ConclusionsThis meta-analysis did not detect any harm associated with a restrictive chest radiograph strategy. However, confidence intervals were wide and harm was not rigorously assessed. Therefore, the safety of abandoning routine CXRs in patients admitted to the ICU remains uncertain.
| S-EPMC3681397 | biostudies-literature
Project description:A pandemic of respiratory illnesses from a novel coronavirus known as Sars-CoV-2 has swept across the globe since December of 2019. This is calling upon the research community including medical imaging to provide effective tools for use in combating this virus. Research in biomedical imaging of viral patients is already very active with machine learning models being created for diagnosing Sars-CoV-2 infections in patients using CT scans and chest x-rays. We aim to build upon this research. Here we used a transfer-learning approach to develop models capable of diagnosing COVID19 from chest x-ray. For this work we compiled a dataset of 112120 negative images from the Chest X-Ray 14 and 2725 positive images from public repositories. We tested multiple models, including logistic regression and random forest and XGBoost with and without principal components analysis, using five-fold cross-validation to evaluate recall, precision, and f1-score. These models were compared to a pre-trained deep-learning model for evaluating chest x-rays called COVID-Net. Our best model was XGBoost with principal components with a recall, precision, and f1-score of 0.692, 0.960, 0.804 respectively. This model greatly outperformed COVID-Net which scored 0.987, 0.025, 0.048. This model, with its high precision and reasonable sensitivity, would be most useful as "rule-in" test for COVID19. Though it outperforms some chemical assays in sensitivity, this model should be studied in patients who would not ordinarily receive a chest x-ray before being used for screening.Ccs conceptsLife and Medical Sciences • Machine Learning • Artificial Intelligence.Reference formatJonathan Stubblefield, Jason Causey, Dakota Dale, Jake Qualls, Emily Bellis, Jennifer Fowler, Karl Walker and Xiuzhen Huang. 2022. COVID19 Diagnosis Using Chest X-Rays and Transfer Learning.
| S-EPMC9580378 | biostudies-literature
Project description:Chest Radiograph or Chest X-ray (CXR) is a common, fast, non-invasive, relatively cheap radiological examination method in medical sciences. CXRs can aid in diagnosing many lung ailments such as Pneumonia, Tuberculosis, Pneumoconiosis, COVID-19, and lung cancer. Apart from other radiological examinations, every year, 2 billion CXRs are performed worldwide. However, the availability of the workforce to handle this amount of workload in hospitals is cumbersome, particularly in developing and low-income nations. Recent advances in AI, particularly in computer vision, have drawn attention to solving challenging medical image analysis problems. Healthcare is one of the areas where AI/ML-based assistive screening/diagnostic aid can play a crucial part in social welfare. However, it faces multiple challenges, such as small sample space, data privacy, poor quality samples, adversarial attacks and most importantly, the model interpretability for reliability on machine intelligence. This paper provides a structured review of the CXR-based analysis for different tasks, lung diseases and, in particular, the challenges faced by AI/ML-based systems for diagnosis. Further, we provide an overview of existing datasets, evaluation metrics for different[][15mm][0mm]Q5 tasks and patents issued. We also present key challenges and open problems in this research domain.
| S-EPMC10116151 | biostudies-literature
Project description:ObjectiveBronchiectasis is an important component of cystic fibrosis (CF) lung disease but little is known about its development. We aimed to study the development of bronchiectasis and identify determinants for rapid progression of bronchiectasis on chest CT.MethodsForty-three patients with CF with at least four consecutive biennial volumetric CTs were included. Areas with bronchiectasis on the most recent CT were marked as regions of interest (ROIs). These ROIs were generated on all preceding CTs using deformable image registration. Observers indicated whether: bronchiectasis, mucus plugging, airway wall thickening, atelectasis/consolidation or normal airways were present in the ROIs.ResultsWe identified 362 ROIs on the most recent CT. In 187 (51.7 %) ROIs bronchiectasis was present on all preceding CTs, while 175 ROIs showed development of bronchiectasis. In 139/175 (79.4 %) no pre-stages of bronchiectasis were identified. In 36/175 (20.6 %) bronchiectatic airways the following pre-stages were identified: mucus plugging (17.7 %), airway wall thickening (1.7 %) or atelectasis/consolidation (1.1 %). Pancreatic insufficiency was more prevalent in the rapid progressors compared to the slow progressors (p?=?0.05).ConclusionMost bronchiectatic airways developed within 2 years without visible pre-stages, underlining the treacherous nature of CF lung disease. Mucus plugging was the most frequent pre-stage.Key points• Development of bronchiectasis in cystic fibrosis lung disease on CT. • Most bronchiectatic airways developed within 2 years without pre-stages. • The most frequently identified pre-stage was mucus plugging. • This study underlines the treacherous nature of CF lung disease.
| S-EPMC5101271 | biostudies-literature
Project description:Airway wall thickening and mucus plugging are important characteristics of cystic fibrosis (CF) lung disease in the first 5 years of life.The aim of this study is to investigate the association of lung disease in preschool children (age, 2-6) with bronchiectasis and other clinical outcome measures in the school age (age >7). Deidentified computed tomography-scans were annotated using Perth-Rotterdam annotated grid morphometric analysis for CF. Preschool %disease (a composite score of %airway wall thickening, %mucus plugging, and %bronchiectasis) and %MUPAT (a composite score of %airway wall thickening and %mucus plugging) were used as predictors for %bronchiectasis and several other school-age clinical outcomes. For statistical analysis, we used regression analysis, linear mixed-effects models and two-way mixed models. Sixty-one patients were included. %Disease increased significantly with age (P??<??.01). Preschool %disease and %MUPAT were significantly associated with school-age %bronchiectasis (P??<??.01 and P??<??.01, respectively). No significant association was found between preschool %disease and %MUPAT and school-age forced expiratory volume 1 (FEV1%) predicted and quality of life (P??>??.05). Cross-sectional, %disease in school-age was associated with a low FEV1% predicted and low quality of life (P??=??.01 and P??=??.007, respectively). %Disease can be considered an early marker of diffuse airways disease and is a risk factor for school-age bronchiectasis.
| S-EPMC6972540 | biostudies-literature
Project description:As a major infectious disease, tuberculosis (TB) still poses a threat to people's health in China. As a triage test for TB, reading chest radiography with traditional approach ends up with high inter-radiologist and intra-radiologist variability, moderate specificity and a waste of time and medical resources. Thus, this study established a deep convolutional neural network (DCNN) based artificial intelligence (AI) algorithm, aiming at diagnosing TB on posteroanterior chest X-ray photographs in an effective and accurate way. Altogether, 5,000 patients with TB and 4,628 patients without TB were included in the study, totaling to 9,628 chest X-ray photographs analyzed. Splitting the radiographs into a training set (80.4%) and a testing set (19.6%), three different DCNN algorithms, including ResNet, VGG, and AlexNet, were trained to classify the chest radiographs as images of pulmonary TB or without TB. Both the diagnostic accuracy and the area under the receiver operating characteristic curve were used to evaluate the performance of the three AI diagnosis models. Reaching an accuracy of 96.73% and marking the precise TB regions on the radiographs, ResNet algorithm-based AI outperformed the rest models and showed excellent diagnostic ability in different clinical subgroups in the stratification analysis. In summary, the ResNet algorithm-based AI diagnosis system provided accurate TB diagnosis, which could have broad prospects in clinical application for TB diagnosis, especially in poor regions with high TB incidence.
| S-EPMC9023793 | biostudies-literature
Project description:(1) Background: The number of chest X-rays that are performed in the perioperative window of thoracic surgery varies. Many clinics X-ray patients daily, while others only perform X-rays if there are clinical concerns. The purpose of this study was to assess the evidence of perioperative X-rays following thoracic surgery and estimate the clinical value with regard to changes in patient care. (2) Methods: A systematic literature research was conducted up until November 2021. Studies reporting X-ray outcomes in adult patients undergoing general thoracic surgery were included. (3) Results: In total, 11 studies (3841 patients/4784 X-rays) were included. The X-ray resulted in changes in patient care in 488 cases (10.74%). In patients undergoing mediastinoscopic lymphadenectomy or thoracoscopic sympathectomy, postoperative X-ray never led to changes in patient care. (4) Conclusions: There are no data to recommend an X-ray before surgery or to recommend daily X-rays. X-rays immediately after surgery seem to rarely have any consequences. It is probably reasonable to keep requesting X-rays after drain removal since they serve multiple purposes and alter patient care in 7.30% of the cases.
| S-EPMC9496662 | biostudies-literature