This study aimed to verify whether a commercial deep learning-based automatic segmentation (DLS) method can maintain contour geometric accuracy post-update and to propose a streamlined validation method that minimizes the burden on clinical workflows. This study included 109 participants. Radiation oncologists used computed tomography (CT) imaging to identify 28 organs located in the head and neck, chest, abdomen, and pelvic regions. Contours were delineated on CT images using AI-Rad Companion Organs RT (AIRC; Siemens Healthineers, Erlangen, Germany) versions VA30, VA50, and VA50. The Dice similarity coefficient, maximum Hausdorff distance, and mean distance to agreement were calculated to identify contours with significant differences among versions. To evaluate the identified contours, the ground truth was defined as the contour delineated by radiation oncologists, and the geometric indices for VA30, VA50, and VA60 were recalculated. Statistical analysis was performed on the geometric indices to verify differences between each version. Among the 28 contours evaluated, nine organs did not satisfy the established criteria. Statistical analysis revealed that the brain, rectum, and bladder contours differed substantially across AIRC versions. In particular, the pre-update rectum contour had a mean (range) Hausdorff distance of 0.76 (0.40-1.16), whereas the post-update rectum contour exhibited lower quality, with a Hausdorff distance of 1.13 (0.24-5.68). Therefore, commercial DLS methods that undergo regular updates must be reassessed for quality in each region of interest. The proposed method can help reduce the burden on clinical workflows while appropriately evaluating post-update DLS performance.

Neuropsychiatric systemic lupus erythematosus (NPSLE) refers to the neurological and psychiatric manifestations of systemic lupus erythematosus (SLE), which remain poorly understood yet often have a profound effect on the lives of afflicted patients. The aim of this study is to synthesize the available information on the pathogenesis, diagnostics, management, and prognosis of this disease. Our hope is to increase awareness and call for further investigations that may optimize NPSLE patient outcomes and quality of life. We performed a literature review following the Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines, resulting in 11 studies of inclusion. Within each study, we extracted data on epidemiologic factors, diagnostics, therapeutic modalities, and prognosis for each neuropsychiatric condition. The most widely discussed neuropsychiatric manifestations of SLE based on the American College of Rheumatology (ACR) classifications included status epilepticus (SE) and seizures, transverse myelitis (TM), and cognitive dysfunction. SE and TM had a prevalence of 1-2%, while cognitive dysfunction was nearly 38%. Diagnostics varied depending on symptom presentation but often included brain magnetic resonance imaging (MRI) and antibody testing. Treatment for NPSLE is still widely understudied, but concurrent treatment with immunosuppressants and anti-inflammatories for symptom control and more targeted immunotherapies based on the specific condition is often effective. Prognosis is highly symptom dependent, ranging from a 12.5% one-year mortality in SE and seizure patients to near resolution of symptoms in certain presentations including idiopathic intracranial hypertension and cerebellar ataxia. Further studies are needed to better understand the pathophysiology, diagnostics, and effective therapeutic measures for NPSLE. The severity of these manifestations and generally poor prognosis highlight the need for more research to accurately diagnose and treat this disease. While there is still little data available, this literature review serves to provide updated context on this condition.