Cooled Radiofrequency Ablation for Chronic Joint Pain Secondary to Hip and Shoulder Osteoarthritis.

Osteoarthritis (OA) of the shoulder and hip is a leading cause of physical disability and mental distress. Traditional nonsurgical management alone is often unable to completely address the associated chronic joint pain. Moreover, a large number of patients are not eligible for joint replacement surgery owing to comorbidities or cost. Radiofrequency ablation (RFA) of articular sensory nerve fibers can disrupt the transmission of nociceptive signals by neurolysis, thereby providing long-term pain relief. A subtype of RFA, cooled RFA (CRFA), utilizes internally cooled electrodes to generate larger ablative zones compared with standard RFA techniques. Given the complex variable innervation of large joints such as the glenohumeral and hip joints, a larger ablative treatment zone, such as that provided by CRFA, is desired to capture a greater number of afferent nociceptive fibers. The suprascapular, axillary, and lateral pectoral nerve articular sensory branches are targeted during CRFA of the glenohumeral joint. The obturator and femoral nerve articular sensory branches are targeted during CRFA of the hip. CRFA is a promising tool in the interventionalist's arsenal for management of OA-related pain and symptoms, particularly in patients who cannot undergo, have long wait times until, or have persistent pain following joint replacement surgery. An invited commentary by Tomasian is available online. ©RSNA, 2022.

A Fusion NLP Model for the Inference of Standardized Thyroid Nodule Malignancy Scores from Radiology Report Text.

Radiology reports are a rich resource for advancing deep learning applications for medical images, facilitating the generation of large-scale annotated image databases. Although the ambiguity and subtlety of natural language poses a significant challenge to information extraction from radiology reports. Thyroid Imaging Reporting and Data Systems (TI-RADS) has been proposed as a system to standardize ultrasound imaging reports for thyroid cancer screening and diagnosis, through the implementation of structured templates and a standardized thyroid nodule malignancy risk scoring system; however there remains significant variation in radiologist practice when it comes to diagnostic thyroid ultrasound interpretation and reporting. In this work, we propose a computerized approach using a contextual embedding and fusion strategy for the large-scale inference of TI-RADS final assessment categories from narrative ultrasound (US) reports. The proposed model has achieved high accuracy on an internal data set, and high performance scores on an external validation dataset.