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.
Central or neurogenic diabetes insipidus (CDI) is due to deficient synthesis or secretion of antidiuretic hormone (ADH), also known as arginine vasopressin peptide (AVP). It is clinically characterised by polydipsia and polyuria (urine output > 30 mL/kg/day) of dilute urine (< 250 mOsm/L). It is the result of a defect in one of more sites involving the hypothalamic osmoreceptors, supraoptic or paraventricular nuclei of the hypothalamus, median eminence of the hypothalamus, infundibulum or the posterior pituitary gland. A focused MRI pituitary gland or sella protocol is essential. There are several neuroimaging correlates and causes of CDI, illustrated in this review. The most common causes are benign or malignant neoplasms of the hypothalamic-pituitary axis (25%), surgery (20%), head trauma (16%) or familial causes (10%). No cause is identified in up to 30% of cases. Knowledge of the anatomy and physiology of the hypothalamo-neurohypophyseal axis is crucial when evaluating a patient with CDI. Establishing the aetiology of CDI with MRI in combination with clinical and biochemical assessment facilitates appropriate targeted treatment. The aim of the pictorial review is to illustrate the wide variety of causes of CDI on neuroimaging, highlight the optimal MRI protocol and to revise the detailed neuroanatomy and neurophysiology required to interpret these studies.
Purpose
To develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs (CXRs), for longitudinal disease evaluation and clinical risk stratification.
Materials and Methods
A convolutional Siamese neural network-based algorithm was trained to output a measure of pulmonary disease severity on anterior-posterior CXRs (pulmonary x-ray severity (PXS) score), using weakly-supervised pretraining on ~160,000 images from CheXpert and transfer learning on 314 CXRs from patients with COVID-19. The algorithm was evaluated on internal and external test sets from different hospitals, containing 154 and 113 CXRs respectively. The PXS score was correlated with a radiographic severity score independently assigned by two thoracic radiologists and one in-training radiologist. For 92 internal test set patients with follow-up CXRs, the change in PXS score was compared to radiologist assessments of change. The association between PXS score and subsequent intubation or death was assessed.
Results
The PXS score correlated with the radiographic pulmonary disease severity score assigned to CXRs in the COVID-19 internal and external test sets (ρ=0.84 and ρ=0.78 respectively). The direction of change in PXS score in follow-up CXRs agreed with radiologist assessment (ρ=0.74). 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 operator characteristic curve=0.80 (95%CI 0.75-0.85)).
Conclusion
A Siamese neural network-based severity score automatically measures COVID-19 pulmonary disease severity in chest radiographs, which can be scaled and rapidly deployed for clinical triage and workflow optimization.
We aimed to further characterize pancreatic involvement in tuberous sclerosis complex (TSC), with a focus on management of TSC-associated nonfunctional pancreatic neuroendocrine tumors (PNETs). This was a retrospective chart review of a large cohort of TSC patients. A total of 637 patients with a confirmed diagnosis of TSC were seen at the Herscot Center for Tuberous Sclerosis Complex at Massachusetts General Hospital. Of the 637 total patients with a confirmed diagnosis of TSC, 28 patients were found to have varying pancreatic findings ranging from simpleappearing cysts to well-differentiated PNETs. Thirteen of the 28 patients had PNET confirmed on pathology; 10 of these tumors were resected at Massachusetts General Hospital. None of the patients had serious perioperative or postoperative complications; only one of the patients had a recurrence following resection. As roughly 4.4% of our TSC patient population had pancreatic involvement, surveillance abdominal imaging should include evaluation of the pancreas instead of limiting to a renal protocol. Additionally, given the low risk of complications and recurrence combined with documented risk of metastasis in TSC-associated PNET, TSC patients with pancreatic lesions suspicious for PNETs should be considered as surgical candidates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.