Deep-Learning Based Automated Segmentation and Quantitative Volumetric Analysis of Orbital Muscle and Fat for Diagnosis of Thyroid Eye Disease.

Purpose: Thyroid eye disease (TED) is characterized by proliferation of orbital tissues and complicated by compressive optic neuropathy (CON). This study aims to utilize a deep-learning (DL)-based automated segmentation model to segment orbital muscle and fat volumes on computed tomography (CT) images and provide quantitative volumetric data and a machine learning (ML)-based classifier to distinguish between TED and TED with CON. Methods: Subjects with TED who underwent clinical evaluation and orbital CT imaging were included. Patients with clinical features of CON were classified as having severe TED, and those without were classified as having mild TED. Normal subjects were used for controls. A U-Net DL-model was used for automatic segmentation of orbital muscle and fat volumes from orbital CTs, and ensemble of Random Forest Classifiers were used for volumetric analysis of muscle and fat. Results: Two hundred eighty-one subjects were included in this study. Automatic segmentation of orbital tissues was performed. Dice coefficient was recorded to be 0.902 and 0.921 for muscle and fat volumes, respectively. Muscle volumes among normal, mild, and severe TED were found to be statistically different. A classification model utilizing volume data and limited patient data had an accuracy of 0.838 and an area under the curve (AUC) of 0.929 in predicting normal, mild TED, and severe TED. Conclusions: DL-based automated segmentation of orbital images for patients with TED was found to be accurate and efficient. An ML-based classification model using volumetrics and metadata led to high diagnostic accuracy in distinguishing TED and TED with CON. By enabling rapid and precise volumetric assessment, this may be a useful tool in future clinical studies.

The Role of Serum Anti-Mullerian Hormone Measurement in the Diagnosis of Polycystic Ovary Syndrome.

Polycystic ovary syndrome (PCOS) is a common endocrinological disorder in women with significant reproductive, metabolic, and psychological health implications. The lack of a specific diagnostic test poses challenges in making the diagnosis of PCOS, resulting in underdiagnosis and undertreatment. Anti-Mullerian hormone (AMH) synthesized by the pre-antral and small antral ovarian follicles appears to play an important role in the pathophysiology of PCOS, and serum AMH levels are often elevated in women with PCOS. The aim of this review is to inform the possibility of utilizing anti-Mullerian hormone either as a diagnostic test for PCOS or as an alternative diagnostic criterion in place of polycystic ovarian morphology, hyperandrogenism, and oligo-anovulation. Increased levels of serum AMH correlate highly with PCOS, polycystic ovarian morphology, hyperandrogenism, and oligo/amenorrhea. Additionally, serum AMH has high diagnostic accuracy as an isolated marker for PCOS or as a replacement for polycystic ovarian morphology.

The Sky's the LEMit: New insights into nuclear structure regulation of transcription factor activity.

The nucleoskeleton has been associated with partitioning the genome into active and inactive compartments that dictate local transcription factor (TF) activity. However, recent data indicate that the nucleoskeleton and TFs reciprocally influence each other in dynamic TF trafficking pathways through the functions of LEM proteins. While the conserved peripheral recruitment of TFs by LEM proteins has been viewed as a mechanism of repressing transcription, a diversity of release mechanisms from the lamina suggest this compartment serves as a refuge for nuclear TF accumulation for rapid mobilization and signal stability. Detailed mechanisms suggest that TFs toggle between nuclear lamina refuge and nuclear matrix lamin-LEM protein complexes at sites of active transcription. In this review we will highlight emerging LEM functions acting at the interface of chromatin and nucleoskeleton to create TF trafficking networks.

The COVID-19 Pandemic as an Opportunity for Operational Innovation at 2 Student-Run Free Clinics.

The onset of the COVID-19 pandemic and subsequent county shelter-in-place order forced the Cardinal Free Clinics (CFCs), Stanford University's 2 student-run free clinics, to close in March 2020. As student-run free clinics adhering to university-guided COVID policies, we have not been able to see patients in person since March of 2020. However, the closure of our in-person operations provided our student management team with an opportunity to innovate. In consultation with Stanford's Telehealth team and educators, we rapidly developed a telehealth clinic model for our patients. We adapted available telehealth guidelines to meet our patient care needs and educational objectives, which manifested in 3 key innovations: reconfigured clinic operations, an evidence-based social needs screen to more effectively assess and address social needs alongside medical needs, and a new telehealth training module for student volunteers. After 6 months of piloting our telehealth services, we believe that these changes have made our services and operations more robust and provided benefit to both our patients and volunteers. Despite an uncertain and evolving public health landscape, we are confident that these developments will strengthen the future operations of the CFCs.