Due to recent advances in artificial intelligence, there is renewed interest in automating interpretation of imaging tests. Chest radiographs are particularly interesting due to many factors: ...relatively inexpensive equipment, importance to public health, commonly performed throughout the world, and deceptively complex taking years to master. This article presents a brief introduction to artificial intelligence, reviews the progress to date in chest radiograph interpretation, and provides a snapshot of the available datasets and algorithms available to chest radiograph researchers. Finally, the limitations of artificial intelligence with respect to interpretation of imaging studies are discussed.
•Chest x-ray had a 89 % sensitivity detecting COVID-19 pneumonia during pandemic peak.•Experienced radiologists had higher specificity than less-experienced ones.•Overall and per-group sensitivity in ...detecting COVID-19 pneumonia increased over time.•Overall and per-group accuracy in detecting COVID-19 pneumonia increased over time.
To report real-world diagnostic performance of chest x-ray (CXR) readings during the COVID-19 pandemic.
In this retrospective observational study we enrolled all patients presenting to the emergency department of a Milan-based university hospital from February 24th to April 8th 2020 who underwent nasopharyngeal swab for reverse transcriptase-polymerase chain reaction (RT-PCR) and anteroposterior bedside CXR within 12 h. A composite reference standard combining RT-PCR results with phone-call-based anamnesis was obtained. Radiologists were grouped by CXR reading experience (Group-1, >10 years; Group-2, <10 years), diagnostic performance indexes were calculated for each radiologist and for the two groups.
Group-1 read 435 CXRs (77.0 % disease prevalence): sensitivity was 89.0 %, specificity 66.0 %, accuracy 83.7 %. Group-2 read 100 CXRs (73.0 % prevalence): sensitivity was 89.0 %, specificity 40.7 %, accuracy 76.0 %. During the first half of the outbreak (195 CXRs, 66.7 % disease prevalence), overall sensitivity was 80.8 %, specificity 67.7 %, accuracy 76.4 %, Group-1 sensitivity being similar to Group-2 (80.6 % versus 81.5 %, respectively) but higher specificity (74.0 % versus 46.7 %) and accuracy (78.4 % versus 69.0 %). During the second half (340 CXRs, 81.8 % prevalence), overall sensitivity increased to 92.8 %, specificity dropped to 53.2 %, accuracy increased to 85.6 %, this pattern mirrored in both groups, with decreased specificity (Group-1, 58.0 %; Group-2, 33.3 %) but increased sensitivity (92.7 % and 93.5 %) and accuracy (86.5 % and 81.0 %, respectively).
Real-world CXR diagnostic performance during the COVID-19 pandemic showed overall high sensitivity with higher specificity for more experienced radiologists. The increase in accuracy over time strengthens CXR role as a first line examination in suspected COVID-19 patients.
Disorders of the lungs such as chronic obstructive pulmonary disease (COPD) are a major cause of chronic morbidity and mortality and the third leading cause of death in the world. The absence of ...sensitive diagnostic tests for early disease stages of COPD results in under-diagnosis of this treatable disease in an estimated 60-85% of the patients. In recent years a grating-based approach to X-ray dark-field contrast imaging has shown to be very sensitive for the detection and quantification of pulmonary emphysema in small animal models. However, translation of this technique to imaging systems suitable for humans remains challenging and has not yet been reported. In this manuscript, we present the first X-ray dark-field images of in-situ human lungs in a deceased body, demonstrating the feasibility of X-ray dark-field chest radiography on a human scale. Results were correlated with findings of computed tomography imaging and autopsy. The performance of the experimental radiography setup allows acquisition of multi-contrast chest X-ray images within clinical boundary conditions, including radiation dose. Upcoming clinical studies will have to demonstrate that this technology has the potential to improve early diagnosis of COPD and pulmonary diseases in general.
The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is ...effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors' knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors' knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.
Purpose To investigate whether photon-counting detector (PCD) technology can improve dose-reduced chest computed tomography (CT) image quality compared with that attained with conventional ...energy-integrating detector (EID) technology in vivo. Materials and Methods This was a HIPAA-compliant institutional review board-approved study, with informed consent from patients. Dose-reduced spiral unenhanced lung EID and PCD CT examinations were performed in 30 asymptomatic volunteers in accordance with manufacturer-recommended guidelines for CT lung cancer screening (120-kVp tube voltage, 20-mAs reference tube current-time product for both detectors). Quantitative analysis of images included measurement of mean attenuation, noise power spectrum (NPS), and lung nodule contrast-to-noise ratio (CNR). Images were qualitatively analyzed by three radiologists blinded to detector type. Reproducibility was assessed with the intraclass correlation coefficient (ICC). McNemar, paired t, and Wilcoxon signed-rank tests were used to compare image quality. Results Thirty study subjects were evaluated (mean age, 55.0 years ± 8.7 standard deviation; 14 men). Of these patients, 10 had a normal body mass index (BMI) (BMI range, 18.5-24.9 kg/m
; group 1), 10 were overweight (BMI range, 25.0-29.9 kg/m
; group 2), and 10 were obese (BMI ≥30.0 kg/m
, group 3). PCD diagnostic quality was higher than EID diagnostic quality (P = .016, P = .016, and P = .013 for readers 1, 2, and 3, respectively), with significantly better NPS and image quality scores for lung, soft tissue, and bone and with fewer beam-hardening artifacts (all P < .001). Image noise was significantly lower for PCD images in all BMI groups (P < .001 for groups 1 and 3, P < .01 for group 2), with higher CNR for lung nodule detection (12.1 ± 1.7 vs 10.0 ± 1.8, P < .001). Inter- and intrareader reproducibility were good (all ICC > 0.800). Conclusion Initial human experience with dose-reduced PCD chest CT demonstrated lower image noise compared with conventional EID CT, with better diagnostic quality and lung nodule CNR.
RSNA, 2017 Online supplemental material is available for this article.
ObjectivesTo establish the level of observer variation for the current ATS/ERS/JRS/ALAT criteria for a diagnosis of usual interstitial pneumonia (UIP) on CT among a large group of thoracic ...radiologists of varying levels of experience.Materials and methods112 observers (96 of whom were thoracic radiologists) categorised CTs of 150 consecutive patients with fibrotic lung disease using the ATS/ERS/JRS/ALAT CT criteria for a UIP pattern (3 categories—UIP, possibly UIP and inconsistent with UIP). The presence of honeycombing, traction bronchiectasis and emphysema was also scored using a 3-point scale (definitely present, possibly present, absent). Observer agreement for the UIP categorisation and for the 3 CT patterns in the entire observer group and in subgroups stratified by observer experience, were evaluated.ResultsInterobserver agreement across the diagnosis category scores among the 112 observers was moderate, ranging from 0.48 (IQR 0.18) for general radiologists to 0.52 (IQR 0.20) for thoracic radiologists of 10–20 years’ experience. A binary score for UIP versus possible or inconsistent with UIP was examined. Observer agreement for this binary score was only moderate. No significant differences in agreement levels were identified when the CTs were stratified according to multidisciplinary team (MDT) diagnosis or patient age or when observers were categorised according to experience. Observer agreement for each of honeycombing, traction bronchiectasis and emphysema were 0.59±0.12, 0.42±0.15 and 0.43±0.18, respectively.ConclusionsInterobserver agreement for the current ATS/ERS/JRS/ALAT CT criteria for UIP is only moderate among thoracic radiologists, irrespective of their experience, and did not vary with patient age or the MDT diagnosis.
Purpose To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs. Materials and Methods Four deidentified HIPAA-compliant datasets ...were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent board-certified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves. Results The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were .03 and .02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%. Conclusion Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy.
RSNA, 2017.