To characterize the imaging features of patients with pathologically confirmed intraosseous schwannoma (IOS), institutional pathology and imaging databases were searched for IOS cases over a period of 17 years. A musculoskeletal radiologist evaluated all imaging studies. Additionally, a literature search was performed to identify IOS cases that had imaging findings of at least two modalities. Six patients (one female, five males, mean age of 50 ± 14 years) with IOS were identified, with all lesions localized to the lumbosacral region. Radiographic imaging was available in four patients, while all patients underwent CT and MR imaging. Radiographs depicted lytic lesions, and CT depicted heterogeneous expansile lesions with centrally hypodense areas and peripheral sclerosis. All cases involved extra-osseous extension, producing a mass effect on adjacent soft tissues and nerve roots. On MRI, the neoplasms displayed iso- to- slightly- low signal intensity on T1-weighted images and hyperintense signal intensity on T2-weighted images with heterogeneous enhancement. The literature review resulted in 102 IOS cases, which to the best of our knowledge, is the largest review on IOS, and the imaging findings of the previously published cases were the same as our cases. IOSs are rare benign neoplasms that should be considered in the differential diagnosis of well-defined expansile lytic lesions with sclerotic borders. This is particularly important in middle-aged adults with mandibular, sacral, or vertebral body mass.

Artificial intelligence (AI) has attracted increasing attention as a tool for the detection and management of several medical conditions. Multiple myeloma (MM), a malignancy characterized by uncontrolled proliferation of plasma cells, is one of the most common hematologic malignancies, which relies on imaging for diagnosis and management. We aimed to review the current literature and trends in AI research of MM imaging. This study was performed according to the PRISMA guidelines. Three main concepts were used in the search algorithm, including “artificial intelligence” in “radiologic examinations” of patients with “multiple myeloma”. The algorithm was used to search the PubMed, Embase, and Web of Science databases. Articles were screened based on the inclusion and exclusion criteria. In the end, we used the checklist for Artificial Intelligence in Medical Imaging (CLAIM) criteria to evaluate the manuscripts. We provided the percentage of studies that were compliant with each criterion as a measure of the quality of AI research on MM. The initial search yielded 977 results. After reviewing them, 14 final studies were selected. The studies used a wide array of imaging modalities. Radiomics analysis and segmentation tasks were the most popular studies (10/14 studies). The common purposes of radiomics studies included the differentiation of MM bone lesions from other lesions and the prediction of relapse. The goal of the segmentation studies was to develop algorithms for the automatic segmentation of important structures in MM. Dice score was the most common assessment tool in segmentation studies, which ranged from 0.80 to 0.97. These studies show that imaging is a valuable data source for medical AI models and plays an even greater role in the management of MM.

Musculoskeletal (MSK) disorders are among the top five contributors to disability-adjusted life years (DALYs) worldwide