On Primary Adrenal Insufficiency with Normal Concentrations of Cortisol - Early Manifestation of Addison's Disease.

Primary adrenal insufficiency (AI) is an endocrine disorder in which hormones of the adrenal cortex are produced to an insufficient extent. Since receptors for adrenal steroids have a wide distribution, initial symptoms may be nonspecific. In particular, the lack of glucocorticoids can quickly lead to a life-threatening adrenal crisis. Therefore, current guidelines suggest applying a low threshold for testing and to rule out AI not before serum cortisol concentrations are higher than 500 nmol/l (18 µg/dl). To ease the diagnostic, determination of morning cortisol concentrations is increasingly used for making a diagnosis whereby values of>350 nmol/l are considered to safely rule out Addison's disease. Also, elevated corticotropin concentrations (>300 pg/ml) are indicative of primary AI when cortisol levels are below 140 nmol/l (5 µg/dl). However, approximately 10 percent of our patients with the final diagnosis of primary adrenal insufficiency would clearly have been missed for they presented with normal cortisol concentrations. Here, we present five such cases to support the view that normal to high basal concentrations of cortisol in the presence of clearly elevated corticotropin are indicative of primary adrenal insufficiency when the case history is suggestive of Addison's disease. In all cases, treatment with hydrocortisone had been started, after which the symptoms improved. Moreover, autoantibodies to the adrenal cortex had been present and all patients underwent a structured national education program to ensure that self-monitored dose adjustments could be made as needed.

Application of a Deep Learning Approach to Analyze Large-Scale MRI Data of the Spine.

With its standardized MRI datasets of the entire spine, the German National Cohort (GNC) has the potential to deliver standardized biometric reference values for intervertebral discs (VD), vertebral bodies (VB) and spinal canal (SC). To handle such large-scale big data, artificial intelligence (AI) tools are needed. In this manuscript, we will present an AI software tool to analyze spine MRI and generate normative standard values. 330 representative GNC MRI datasets were randomly selected in equal distribution regarding parameters of age, sex and height. By using a 3D U-Net, an AI algorithm was trained, validated and tested. Finally, the machine learning algorithm explored the full dataset (n = 10,215). VB, VD and SC were successfully segmented and analyzed by using an AI-based algorithm. A software tool was developed to analyze spine-MRI and provide age, sex, and height-matched comparative biometric data. Using an AI algorithm, the reliable segmentation of MRI datasets of the entire spine from the GNC was possible and achieved an excellent agreement with manually segmented datasets. With the analysis of the total GNC MRI dataset with almost 30,000 subjects, it will be possible to generate real normative standard values in the future.