Dataset Information

PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children.

ABSTRACT: Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the advent of high-performance supervised learning algorithms. However, the development of diagnostic models for detecting and diagnosing pediatric diseases in CXR scans is undertaken due to the lack of high-quality physician-annotated datasets. To overcome this challenge, we introduce and release PediCXR, a new pediatric CXR dataset of 9,125 studies retrospectively collected from a major pediatric hospital in Vietnam between 2020 and 2021. Each scan was manually annotated by a pediatric radiologist with more than ten years of experience. The dataset was labeled for the presence of 36 critical findings and 15 diseases. In particular, each abnormal finding was identified via a rectangle bounding box on the image. To the best of our knowledge, this is the first and largest pediatric CXR dataset containing lesion-level annotations and image-level labels for the detection of multiple findings and diseases. For algorithm development, the dataset was divided into a training set of 7,728 and a test set of 1,397. To encourage new advances in pediatric CXR interpretation using data-driven approaches, we provide a detailed description of the PediCXR data sample and make the dataset publicly available on https://physionet.org/content/vindr-pcxr/1.0.0/ .

SUBMITTER: Pham HH

PROVIDER: S-EPMC10133237 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children.

Pham Hieu H HH Nguyen Ngoc H NH Tran Thanh T TT Nguyen Tuan N M TNM Nguyen Ha Q HQ

Scientific data 20230427 1

Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the advent of high-performance supervised learning algorithms. However, the development of diagnostic models for detecting and diagnosing pediatric diseases in CXR scans is undertaken due to the lack of high-quality physician-annotated datasets. To overcome this challenge, we introduce and release PediCXR, a new pediatric CXR dat ...[more]

PMID: 37100784

Similar Datasets

Project description:Chest radiography is a frequently used imaging modality in children. However, only fair to moderate inter-observer agreement has been reported between chest radiograph interpreters. Most studies were not performed in real-world clinical settings. Our aims were to examine the agreement between emergency department pediatricians and board-certified radiologists in a pediatric real-life setting and to identify clinical risk factors for the discrepancies. Included were children aged 3 months to 18 years who underwent chest radiography in the emergency department not during the regular hours of radiologist interpretation. Every case was reviewed by an expert panel. Inter-observer agreement between emergency department pediatricians and board-certified radiologists was assessed by Cohen's kappa; risk factors for disagreement were analyzed. Among 1373 cases, the level of agreement between emergency department pediatricians and board-certified radiologists was "moderate" (k = 0.505). For radiographs performed after midnight, agreement was only "fair" (k = 0.391). The expert panel identified clinically relevant disagreements in 260 (18.9%) of the radiographs. Over-treatment of antibiotics was identified in 121 (8.9%) of the cases and under-treatment in 79 (5.8%). In a multivariable logistic regression, the following parameters were found to be significantly associated with disagreements: neurological background (p = 0.046), fever (p = 0.001), dyspnea (p = 0.014), and radiographs performed after midnight (p = 0.007).ConclusionsModerate agreement was found between emergency department pediatricians and board-certified radiologists in interpreting chest radiographs. Neurological background, fever, dyspnea, and radiographs performed after midnight were identified as risk factors for disagreement. Implementing these findings could facilitate the use of radiologist expertise, save time and resources, and potentially improve patient care.What is known• Only fair to moderate inter-observer agreement has been reported between chest radiograph interpreters. • Most studies were not performed in real-world clinical settings. Clinical risk factors for disagreements have not been reported.What is new• In this study, which included 1373 cases at the emergency department, the level of agreement between interpreters was only "moderate." • The major clinical parameters associated with interpretation discrepancies were neurological background, fever, dyspnea, and interpretations conducted during the night shift.

Project description:ImportanceMultimodal generative artificial intelligence (AI) methodologies have the potential to optimize emergency department care by producing draft radiology reports from input images.ObjectiveTo evaluate the accuracy and quality of AI-generated chest radiograph interpretations in the emergency department setting.Design, setting, and participantsThis was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale.Main outcomes and measuresThe primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded.ResultsA total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3 (21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22 [0.34]; P < .001) and radiologist (mean [SE] score, 3.34 [0.34]; P < .001) reports compared with teleradiology (mean [SE] score, 2.74 [0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types.Conclusions and relevanceIn a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.

Project description:ImportanceThe efficient and accurate interpretation of radiologic images is paramount.ObjectiveTo evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities.Design, setting, and participantsThis multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH).Main outcomes and measuresThe ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding.ResultsA total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001).Conclusions and relevanceThese findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.

Project description:BackgroundChest X-ray radiography (CXR) has been widely considered as an accessible, feasible, and convenient method to evaluate suspected patients' lung involvement during the COVID-19 pandemic. However, with the escalating number of suspected cases, traditional diagnosis via CXR fails to deliver results within a short period of time. Therefore, it is crucial to employ artificial intelligence (AI) to enhance CXRs for obtaining quick and accurate diagnoses. Previous studies have reported the feasibility of utilizing deep learning methods to screen for COVID-19 using CXR and CT results. However, these models only use a single deep learning network for chest radiograph detection; the accuracy of this approach required further improvement.MethodsIn this study, we propose a three-step hybrid ensemble model, including a feature extractor, a feature selector, and a classifier. First, a pre-trained AlexNet with an improved structure extracts the original image features. Then, the ReliefF algorithm is adopted to sort the extracted features, and a trial-and-error approach is used to select the n most important features to reduce the feature dimension. Finally, an SVM classifier provides classification results based on the n selected features.ResultsCompared to five existing models (InceptionV3: 97.916 ± 0.408%; SqueezeNet: 97.189 ± 0.526%; VGG19: 96.520 ± 1.220%; ResNet50: 97.476 ± 0.513%; ResNet101: 98.241 ± 0.209%), the proposed model demonstrated the best performance in terms of overall accuracy rate (98.642 ± 0.398%). Additionally, compared to the existing models, the proposed model demonstrates a considerable improvement in classification time efficiency (SqueezeNet: 6.602 ± 0.001s; InceptionV3: 12.376 ± 0.002s; ResNet50: 10.952 ± 0.001s; ResNet101: 18.040 ± 0.002s; VGG19: 16.632 ± 0.002s; proposed model: 5.917 ± 0.001s).ConclusionThe model proposed in this article is practical and effective, and can provide high-precision COVID-19 CXR detection. We demonstrated its suitability to aid medical professionals in distinguishing normal CXRs, viral pneumonia CXRs and COVID-19 CXRs efficiently on small sample sizes.

Dataset Information

PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children.

Publications

PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets