Pneumothorax 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.
In 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.
We 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.
Many interesting dynamic properties of biological molecules cannot be simulated directly using molecular dynamics because of nanosecond time scale limitations. These systems are trapped in potential ...energy minima with high free energy barriers for large numbers of computational steps. The dynamic evolution of many molecular systems occurs through a series of rare events as the system moves from one potential energy basin to another. Therefore, we have proposed a robust bias potential function that can be used in an efficient accelerated molecular dynamics approach to simulate the transition of high energy barriers without any advance knowledge of the location of either the potential energy wells or saddle points. In this method, the potential energy landscape is altered by adding a bias potential to the true potential such that the escape rates from potential wells are enhanced, which accelerates and extends the time scale in molecular dynamics simulations. Our definition of the bias potential echoes the underlying shape of the potential energy landscape on the modified surface, thus allowing for the potential energy minima to be well defined, and hence properly sampled during the simulation. We have shown that our approach, which can be extended to biomolecules, samples the conformational space more efficiently than normal molecular dynamics simulations, and converges to the correct canonical distribution.
The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One ...thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73–100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.
The coronavirus disease 2019 (COVID-19) pandemic is a global health care emergency. Although reverse-transcription polymerase chain reaction testing is the reference standard method to identify ...patients with COVID-19 infection, chest radiography and CT play a vital role in the detection and management of these patients. Prediction models for COVID-19 imaging are rapidly being developed to support medical decision making. However, inadequate availability of a diverse annotated data set has limited the performance and generalizability of existing models. To address this unmet need, the RSNA and Society of Thoracic Radiology collaborated to develop the RSNA International COVID-19 Open Radiology Database (RICORD). This database is the first multi-institutional, multinational, expert-annotated COVID-19 imaging data set. It is made freely available to the machine learning community as a research and educational resource for COVID-19 chest imaging. Pixel-level volumetric segmentation with clinical annotations was performed by thoracic radiology subspecialists for all COVID-19-positive thoracic CT scans. The labeling schema was coordinated with other international consensus panels and COVID-19 data annotation efforts, the European Society of Medical Imaging Informatics, the American College of Radiology, and the American Association of Physicists in Medicine. Study-level COVID-19 classification labels for chest radiographs were annotated by three radiologists, with majority vote adjudication by board-certified radiologists. RICORD consists of 240 thoracic CT scans and 1000 chest radiographs contributed from four international sites. It is anticipated that RICORD will ideally lead to prediction models that can demonstrate sustained performance across populations and health care systems.
This dataset is composed of annotations of the five hemorrhage subtypes (subarachnoid, intraventricular, subdural, epidural, and intraparenchymal hemorrhage) typically encountered at brain CT.
Technological innovation has enabled the development of machine learning (ML) tools that aim to improve the practice of radiologists. In the last decade, ML applications to neuro-oncology have ...expanded significantly, with the pre-operative prediction of glioma grade using medical imaging as a specific area of interest. We introduce the subject of ML models for glioma grade prediction by remarking upon the models reported in the literature as well as by describing their characteristic developmental workflow and widely used classifier algorithms. The challenges facing these models-including data sources, external validation, and glioma grade classification methods -are highlighted. We also discuss the quality of how these models are reported, explore the present and future of reporting guidelines and risk of bias tools, and provide suggestions for the reporting of prospective works. Finally, this review offers insights into next steps that the field of ML glioma grade prediction can take to facilitate clinical implementation.
To compare the diagnostic performance of dual-energy (DE) computed tomography (CT) with two simultaneously administered contrast agents (hereafter, dual contrast) with that of conventional CT in the ...evaluation of the presence and source of extravasation in penetrating abdominopelvic trauma.
Institutional animal care and use committee approval was obtained, and the study was performed in accordance with National Institutes of Health guidelines for the care and use of laboratory animals. Five rabbits with bowel trauma, vascular penetrating trauma, or both were imaged with simultaneous iodinated intravenous and bismuth subsalicylate enteric contrast material at DE CT. Four attending radiologists and six radiology residents without prior DE CT experience each evaluated 10 extraluminal collections to identify the vascular and/or enteric origin of extravasation and assess their level of diagnostic confidence, first with virtual monochromatic images simulating conventional CT and then with DE CT material decomposition attenuation maps.
Overall accuracy of identification of source of extravasation increased from 78% with conventional CT to 92% with DE CT (157 of 200 diagnoses vs 184 of 200 diagnoses, respectively; P < .001). Nine radiologists were more accurate with DE CT; one had no change. Mean confidence increased from 67% to 81% with DE CT (P < .001).
In a rabbit abdominopelvic trauma model, dual-contrast DE CT significantly increased accuracy and confidence in the diagnosis of vascular versus enteric extravasated contrast material.
Coronary artery disease (CAD), the most common manifestation of cardiovascular disease, remains the most common cause of mortality in the United States. Risk assessment is key for primary prevention ...of coronary events and coronary artery calcium (CAC) scoring using computed tomography (CT) is one such non-invasive tool. Despite the proven clinical value of CAC, the current clinical practice implementation for CAC has limitations such as the lack of insurance coverage for the test, need for capital-intensive CT machines, specialized imaging protocols, and accredited 3D imaging labs for analysis (including personnel and software). Perhaps the greatest gap is the millions of patients who undergo routine chest CT exams and demonstrate coronary artery calcification, but their presence is not often reported or quantitation is not feasible. We present two deep learning models that automate CAC scoring demonstrating advantages in automated scoring for both dedicated gated coronary CT exams and routine non-gated chest CTs performed for other reasons to allow opportunistic screening. First, we trained a gated coronary CT model for CAC scoring that showed near perfect agreement (mean difference in scores = -2.86; Cohen's Kappa = 0.89, P < 0.0001) with current conventional manual scoring on a retrospective dataset of 79 patients and was found to perform the task faster (average time for automated CAC scoring using a graphics processing unit (GPU) was 3.5 ± 2.1 s vs. 261 s for manual scoring) in a prospective trial of 55 patients with little difference in scores compared to three technologists (mean difference in scores = 3.24, 5.12, and 5.48, respectively). Then using CAC scores from paired gated coronary CT as a reference standard, we trained a deep learning model on our internal data and a cohort from the Multi-Ethnic Study of Atherosclerosis (MESA) study (total training n = 341, Stanford test n = 42, MESA test n = 46) to perform CAC scoring on routine non-gated chest CT exams with validation on external datasets (total n = 303) obtained from four geographically disparate health systems. On identifying patients with any CAC (i.e., CAC ≥ 1), sensitivity and PPV was high across all datasets (ranges: 80-100% and 87-100%, respectively). For CAC ≥ 100 on routine non-gated chest CTs, which is the latest recommended threshold to initiate statin therapy, our model showed sensitivities of 71-94% and positive predictive values in the range of 88-100% across all the sites. Adoption of this model could allow more patients to be screened with CAC scoring, potentially allowing opportunistic early preventive interventions.