Spinal–pelvic parameters are utilized in orthopedics for assessing patients’ curvature and body alignment in diagnosing, treating, and planning surgeries for spinal and pelvic disorders. Segmenting and autodetecting the whole spine from lateral radiographs is challenging. Recent efforts have employed deep learning techniques to automate the segmentation and analysis of whole-spine lateral radiographs. This study aims to develop an artificial intelligence (AI)-based deep learning approach for the automated segmentation, alignment, and measurement of spinal–pelvic parameters through whole-spine lateral radiographs. We conducted the study on 932 annotated images from various spinal pathologies. Using a deep learning (DL) model, anatomical landmarks of the cervical, thoracic, lumbar vertebrae, sacrum, and femoral head were automatically distinguished. The algorithm was designed to measure 13 radiographic alignment and spinal–pelvic parameters from the whole-spine lateral radiographs. Training data comprised 748 digital radiographic (DR) X-ray images, while 90 X-ray images were used for validation. Another set of 90 X-ray images served as the test set. Inter-rater reliability between orthopedic spine specialists, orthopedic residents, and the DL model was evaluated using the intraclass correlation coefficient (ICC). The segmentation accuracy for anatomical landmarks was within an acceptable range (median error: 1.7–4.1 mm). The inter-rater reliability between the proposed DL model and individual experts was fair to good for measurements of spinal curvature characteristics (all ICC values > 0.62). The developed DL model in this study demonstrated good levels of inter-rater reliability for predicting anatomical landmark positions and measuring radiographic alignment and spinal–pelvic parameters. Automated segmentation and analysis of whole-spine lateral radiographs using deep learning offers a promising tool to enhance accuracy and efficiency in orthopedic diagnostics and treatments.

A glomus tumor is a rare, benign tumor with atypical clinical symptoms. Because of its small size, it is difficult to diagnose and treat early; therefore, it leads to poor quality of life. Glomus tumors are known to commonly affect the hand and rarely manifest in other areas. Because they simulate neuromas, hemangiomas, and neurofibromatosis, the differential diagnosis is difficult. We performed marginal resection of a solitary forearm mass previously suspected to be a hemangioma or glomus tumor on the basis of ultrasound findings and histologically diagnosed to be a glomus tumor afterward. We report this case to demonstrate the good prognosis of the procedure we used, and we review the relevant literature. A 68-year-old Asian man without a particular medical history visited our hospital with a mass with focal tenderness in his left distal forearm that had developed 8 years earlier. The tumor was observed with suspicion of being a hemangioma or glomus tumor based on the location, clinical symptoms, and ultrasound findings taken into consideration together. The biopsy results led us to conclude that the lesion was a glomus tumor. A glomus tumor located in the forearm is very rare. It is often clinically overlooked and is likely to be misdiagnosed as another disease. The patient’s quality of life deteriorates, and, though the disease is rare, it has serious sequelae. Therefore, a quick diagnosis and appropriate treatment must be conducted early. If a mass occurs with serious pain in subcutaneous soft tissue of not the hands but the limbs, it is important to conduct examinations with suspicion of a glomus tumor. Ultrasonography performed quickly may be useful for making the differential diagnosis.

Fibrous dysplasia is one of many well-known disorders in which there is a defect in the remodeling process of immature bone to mature into lamellar bone, and it often exists in metaphyseal and diaphyseal parts of the long bone. In this report, we describe a rare case where fibrous dysplasia was found only in the proximal part of the epiphysis of the tibia without other bony lesions.

Introduction: Langerhans` Cell Histiocytosis (LCH) is a rare disease involving proliferation of Langerhans-type cells, which shares immunophenotypic and ultrastructural similarities. In this article, we report a case of Langerhans cell histiocytosis in solitary involvement of clavicle of adult male. Presentation of case: A 21-year-old male visited outpatient department on account of solitary palpable tumorous lesion in right clavicle. The lesion was found 2 weeks before the visit, and it triggered pain but no tenderness. Findings on X-ray, and CT were suggestive of homogeneous osteolytic lesion of the clavicle, and hot uptake was found in right clavicle on bone scan which is commensurate with site of the lesion. Based on findings on MRI, Ewing's sarcoma, osteomyelitis and malignant hematologic malignancies were initially suspected for differential diagnosis. For the purpose of excision and histologic analysis, excisional biopsy was performed. Biopsy concluded with diagnosis of LCH. Discussion: LCH is widely renowned for its frequent occurrence in pediatric ages, and it occurs usually between ages of one and four. It occasionally occurs in adults. LCH in skeletal system usually involves cranium, vertebrae, rib and so forth. It is very rare for LCH to occur exclusively in clavicle when it involves skeletal system. For diagnosis of LCH, sole imaging studies are inadequate, and histologic, immunochemical analyses are confirmative modalities. Treatment of LCH is not currently standardized. Conclusions: Most of the solitary tumorous lesions in clavicle in adults call for various differential diagnoses. LCH should be considered in the diagnosis of a adult patient with a clavicle mass. Highlights: