Skeletal maturity progresses through discrete phases, a fact that is used routinely in pediatrics where bone age assessments (BAAs) are compared to chronological age in the evaluation of endocrine and metabolic disorders. While central to many disease evaluations, little has changed to improve the tedious process since its introduction in 1950. In this study, we propose a fully automated deep learning pipeline to segment a region of interest, standardize and preprocess input radiographs, and perform BAA. Our models use an ImageNet pretrained, fine-tuned convolutional neural network (CNN) to achieve 57.32 and 61.40% accuracies for the female and male cohorts on our held-out test images. Female test radiographs were assigned a BAA within 1 year 90.39% and within 2 years 98.11% of the time. Male test radiographs were assigned 94.18% within 1 year and 99.00% within 2 years. Using the input occlusion method, attention maps were created which reveal what features the trained model uses to perform BAA. These correspond to what human experts look at when manually performing BAA. Finally, the fully automated BAA system was deployed in the clinical environment as a decision supporting system for more accurate and efficient BAAs at much faster interpretation time (<2 s) than the conventional method.
After restrictive guidelines regarding GBCA administration were instituted, no new cases of NSF were identified among 52,954 contrast-enhanced MR examinations, including those performed in patients with an eGFR lower than 60 mL/min/m(2).
We have designed an approach for modeling olfactory pathways by which one can explore how the properties of individual receptors affect the information coding capacity of an entire system. The effect of receptor tuning breadth on system performance was explored explicitly. We presented model sensory arrays with sets of stimuli randomly and uniformly distributed in an "olfactory space". Arrays of uniformly sized model receptors responding to 25-35% of the stimuli gave the best performance as measured by the ability to capture the most information about the stimulus set. Arrays of variably sized model receptors that were both more broadly and more narrowly tuned than this optimum could, however, perform better than uniform arrays. This method and the results obtained using it suggest a framework for considering the growing body of evidence on the functional properties of individual olfactory receptor and relay neurons from a systems coding perspective.
A 59-year-old male was admitted to Massachusetts General Hospital, Boston, Mass, with a 2-month history of exertional dyspnea (New York Heart Association class II to III). The patient denied dyspnea at rest, chest pain, palpitations, or syncope. There was no history of fevers or recent weight loss.An outpatient echocardiogram (Figure 1), performed as part of the workup of the patient's dyspnea, demonstrated normal left ventricular size and function. The right ventricle (RV) was normal in size but diffusely hypokinetic. There was evidence of segmental RV dysfunction, with 2 discrete aneurysmal areas in the RV free wall at the base and apex, which measured 1.5 and 3.0 cm in width. Both areas appeared thinned and dyskinetic. The echocardiographic appearance was suggestive of arrhythmogenic RV dysplasia/cardiomyopathy (ARVD/C). 1 A CT scan ruled out the presence of pulmonary embolism but was notable for marked mediastinal lymphadenopathy ( Figure 2).One week later, the patient developed intermittent Mobitz type II second-degree atrioventricular block that prompted his admission to the hospital for monitoring and further workup. An admission ECG (Figure 3) showed normal sinus rhythm with a heart rate of 45 bpm and Mobitz type II second-degree atrioventricular block with 2:1 conduction. Chest radiograph findings (Figure 4) were unremarkable. All laboratory tests were normal, including troponin and ACE levels.Cardiac magnetic resonance imaging (Figures 5 and 6) confirmed the presence of the RV aneurysms and segmental hypokinesis. Delayed hyperenhancement of the basal portion of the RV free wall, the RV border of the midventricular septum, and the subepicardial portion of the basal and apical inferolateral walls of the left ventricle was noted. These findings placed into doubt the diagnosis of ARVD/C and suggested the possibility of cardiac sarcoidosis.An endomyocardial biopsy ( Figure 7) was performed that targeted the locations of delayed hyperenhancement, observed by MRI, within the RV. It revealed extensive fibrosis with giant cells, compact noncaseating granulomas, and an accompanying lymphocytic infiltrate consistent with cardiac sarcoidosis. 2-[18 F]fluoro-2-deoxy-D-glucose positron emission tomography scanning was conducted (Figure 8) to evaluate the extent of disease, which demonstrated intense uptake in the RV and patchy uptake in the left ventricle. Prominent uptake in multiple thoracic lymph node groups The online-only Data Supplement, which contains movies, is available with this article at http://circ.ahajournals.org/cgi/content/full/ 118/7/e113/DC1.
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.