Purpose To develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs (CXRs), for longitudinal disease tracking and outcome prediction. Materials and Methods A convolutional Siamese neural network-based algorithm was trained to output a measure of pulmonary disease severity on CXRs (pulmonary x-ray severity (PXS) score), using weakly-supervised pretraining on ∼160,000 anterior-posterior images from CheXpert and transfer learning on 314 frontal CXRs from COVID-19 patients. The algorithm was evaluated on internal and external test sets from different hospitals (154 and 113 CXRs respectively). PXS scores were correlated with radiographic severity scores independently assigned by two thoracic radiologists and one in-training radiologist (Pearson r). For 92 internal test set patients with follow-up CXRs, PXS score change was compared to radiologist assessments of change (Spearman ρ). The association between PXS score and subsequent intubation or death was assessed. Bootstrap 95% confidence intervals (CI) were calculated. Results PXS scores correlated with radiographic pulmonary disease severity scores assigned to CXRs in the internal and external test sets (r=0.86 (95%CI 0.80-0.90) and r=0.86 (95%CI 0.79-0.90) respectively). The direction of change in PXS score in follow-up CXRs agreed with radiologist assessment (ρ=0.74 (95%CI 0.63-0.81)). In patients not intubated on the admission CXR, the PXS score predicted subsequent intubation or death within three days of hospital admission (area under the receiver operating characteristic curve=0.80 (95%CI 0.75-0.85)). Conclusion A Siamese neural network-based severity score automatically measures radiographic COVID-19 pulmonary disease severity, which can be used to track disease change and predict subsequent intubation or death.

CT texture analysis and CT features are predictive of PNET aggressiveness and can be used to identify patients at risk of early disease progression after surgical resection.

• Current dual-energy CT platforms provide accurate, reliable quantitative information. • Dual-energy CT cross-platform evaluation revealed noticeable performance differences between different systems. • Dual-layer CT offers constant noise levels over the complete energy range.

Multienergy CT involves acquisition of two or more CT measurements with distinct energy spectra. Using the differential attenuation of tissues and materials at different x-ray energies, multienergy CT allows distinction of tissues and materials beyond that possible with conventional CT. Multienergy CT technologies can operate at the source or detector level. Dual-source, rapid tube-voltage switching, and dual-layer detector CT are the most commonly used multienergy CT technologies. Most of the currently available technologies typically use two energy levels, commonly referred to as dual-energy CT. With use of two or more energy bins, photoncounting detector CT can perform multienergy CT beyond current dual-energy CT technologies. Multienergy CT postprocessing can be performed in the projection or image domain using two-material or multimaterial decomposition. The most commonly used multienergy CT images are virtual monoenergetic images (VMIs), iodine maps, virtual noncontrast (VNC) images, and uric acid images. Low-energy VMIs are used to boost contrast signal and enhance lesion conspicuity. High-energy VMIs are used to decrease some artifacts. Iodine maps are used to evaluate perfusion, characterize lesions, and evaluate response to therapy. VNC images are used to characterize lesions and save radiation dose by eliminating true noncontrast images from multiphasic acquisitions. Uric acid images are used for characterization of renal calculi and gout.