ObjectivesCardiac computed tomography (CCT) is a common pre-operative imaging modality to evaluate pulmonary vein anatomy and left atrial appendage thrombus in patients undergoing catheter ablation (CA) for atrial fibrillation (AF). These images also allow for full volumetric left atrium (LA) measurement for recurrence risk stratification, as larger LA volume (LAV) is associated with higher recurrence rates. Our objective is to apply deep learning (DL) techniques to fully automate the computation of LAV and assess the quality of the computed LAV values.MethodsUsing a dataset of 85,477 CCT images from 337 patients, we proposed a framework that consists of several processes that perform a combination of tasks including the selection of images with LA from all other images using a ResNet50 classification model, the segmentation of images with LA using a UNet image segmentation model, the assessment of the quality of the image segmentation task, the estimation of LAV, and quality control (QC) assessment.ResultsOverall, the proposed LAV estimation framework achieved accuracies of 98% (precision, recall, and F1 score metrics) in the image classification task, 88.5% (mean dice score) in the image segmentation task, 82% (mean dice score) in the segmentation quality prediction task, and R2 (the coefficient of determination) value of 0.968 in the volume estimation task. It correctly identified 9 out of 10 poor LAV estimations from a total of 337 patients as poor-quality estimates.ConclusionsWe proposed a generalizable framework that consists of DL models and computational methods for LAV estimation. The framework provides an efficient and robust strategy for QC assessment of the accuracy for DL-based image segmentation and volume estimation tasks, allowing high-throughput extraction of reproducible LAV measurements to be possible.

This study aimed to prospectively evaluate the early effects of radiation on cardiac structure and function following neoadjuvant chemoradiation for distal esophageal cancer. Conclusions: Our study is the first to our knowledge to prospectively demonstrate radiation associated structural and functional heart damage as early as 3 months following neoadjuvant chemoradiation for distal esophageal cancer. Given the early onset of this subclinical heart damage, strategies should be developed to identify patients at risk for future clinically significant heart toxicity.

This article reviews current and evolving concepts in the diagnosis of penetrating diaphragmatic injury with multidetector CT (MDCT). As criteria for nonoperative management in the setting of penetrating trauma become more inclusive, confident exclusion of penetrating diaphragmatic injury (PDI) has become imperative. Diagnostic performance of MDCT for PDI has improved substantially with the use of thin sections and multiplanar reformats. Evaluation of injury trajectory in nonstandard planes using 3D post-processing software can aid in the diagnosis. Contiguous injury and transdiaphragmatic trajectory are the best predictors of PDI. Careful appraisal of the diaphragm for defects should be undertaken in all patients with thoracoabdominal penetrating trauma.

No abstract

We describe the curation, annotation methodology and characteristics of the dataset used in an artificial intelligence challenge for detection and localization of COVID-19 on chest radiographs. The chest radiographs were annotated by an international group of radiologists into four mutually exclusive categories, including “typical”, “indeterminate”, and “atypical appearance” for COVID-19, or “negative for pneumonia”, adapted from previously published guidelines, and bounding boxes were placed on airspace opacities. This dataset and respective annotations are freely available to all researchers for academic and noncommercial use.