Background: We sought to evaluate the performance of a computed tomography (CT)-based radiomics nomogram we devised in distinguishing benign from malignant bone tumours.Methods: Two hundred and six patients with bone tumours were spilt into two groups: a training set (n = 155) and a validation set (n = 51). A feature extraction process based on 3D Slicer software was used to extract the radiomics features from unenhanced CT images, and least absolute shrinkage and selection operator logistic regression was used to calculate the radiomic score to generate a radiomics signature. A clinical model comprised demographics and CT features. A radiomics nomogram combined with the clinical model and the radiomics signature was constructed. The performance of the three models was comprehensively evaluated from three aspects: identification ability, accuracy, and clinical value, allowing for generation of an optimal prediction model.Results: The radiomics nomogram comprised clinical and radiomics signature features. The nomogram model displayed good performance in training and validation sets with areas under the curve of 0.917 and 0.823, respectively. The areas under the curve, decision curve analysis, and net reclassification improvement showed that the radiomics nomogram model could obtain better diagnostic performance than the clinical model and achieve greater clinical net benefits than the clinical and radiomics signature models alone.Conclusions: We constructed a combined nomogram comprising a clinical model and radiomics signature as a noninvasive preoperative prediction method to distinguish between benign and malignant bone tumours and assist treatment planning.

Hepatic PEComas are very rare. Few systematic reports are available characterizing the imaging and pathological features of hepatic PEComa. The aim of this study was to investigate the imaging findings of primary hepatic perivascular epithelioid cell tumors (PEComa) and its correlation with histopathological features. The CT, MRI and ultrasound images and pathological findings of 22 patients with primary hepatic PEComa were retrospectively reviewed. More females (14/22) were affected with the mean age of 47.1 years. Most patients (17/22) were asymptomatic and the routine laboratory tests were normal. More tumors occurred in the right lobe (13/22) with a mean diameter of 76.7 mm. Surgery was performed in 21 patients, and biopsy was performed in 1 patient. Immunohistochemical studies showed the expression rate of HMB-45 and Melan A was 100% (22/22) and 86.4% (19/22) within the tumor cells. The pathology diagnoses were angiomyolipoma (n = 18), lymphangioleiomyoma (n = 2), clear-cell myomelanocytic tumor of falciform ligament/ligamentum teres (n = 1), and not otherwise specified (n = 1). Fifteen cases were classified as uncertain malignant potential (n = 13) or malignant (n = 2). CT, MRI and ultrasound features included well-defined margins (19/22), internal heterogeneity (20/22), arterial enhancement (20/22), dysmorphic vessels (17/22), fat (9/22), hemorrhage (3/22), necrosis (8/22), and calcification (2/22). The diagnostic accuracy was only 27.3% (6/22). No local recurrence or metastasis was found in the follow-up patients (12/22). On CT, MRI and ultrasound images, most hepatic PEComas are well-defined, heterogeneous, arterial enhanced masses with dysmorphic vessels, with or without fat, especially in middle-aged females. With the potential to be malignant, timely surgical resection and long-term follow-up may be helpful for improving the prognosis.