Preoperative contrast-enhanced CT-based radiomics nomogram for differentiating benign and malignant primary retroperitoneal tumors.

OBJECTIVES: This study evaluated the ability of a preoperative contrast-enhanced CT (CECT)-based radiomics nomogram to differentiate benign and malignant primary retroperitoneal tumors (PRT). METHODS: Images and data from 340 patients with pathologically confirmed PRT were randomly placed into training (n = 239) and validation sets (n = 101). Two radiologists independently analyzed all CT images and made measurements. Key characteristics were identified through least absolute shrinkage selection combined with four machine-learning classifiers (support vector machine, generalized linear model, random forest, and artificial neural network back propagation) to create a radiomics signature. Demographic data and CECT characteristics were analyzed to formulate a clinico-radiological model. Independent clinical variables were merged with the best-performing radiomics signature to develop a radiomics nomogram. The discrimination capacity and clinical value of three models were quantified by the area under the receiver operating characteristics (AUC), accuracy, and decision curve analysis. RESULTS: The radiomics nomogram was able to consistently differentiate between benign and malignant PRT in the training and validation datasets, with AUCs of 0.923 and 0.907, respectively. Decision curve analysis manifested that the nomogram achieved higher clinical net benefits than did separate use of the radiomics signature and clinico-radiological model. CONCLUSIONS: The preoperative nomogram is valuable for differentiating between benign and malignant PRT; it can also aid in treatment planning. KEY POINTS: • A noninvasive and accurate preoperative determination of benign and malignant PRT is crucial to identifying suitable treatments and predicting disease prognosis. • Associating the radiomics signature with clinical factors facilitates differentiation of malignant from benign PRT with improved diagnostic efficacy (AUC) and accuracy from 0.772 to 0.907 and from 0.723 to 0.842, respectively, compared with the clinico-radiological model alone. • For some PRT with anatomically special locations and when biopsy is extremely difficult and risky, a radiomics nomogram may provide a promising preoperative alternative for distinguishing benignity and malignancy.

Giant cell tumors of the mobile spine with invasion of adjacent vertebrae: an unusual imaging finding.

BACKGROUND: Giant cell tumors of the mobile spine invasion of the adjacent vertebrae are an ignored imaging finding. METHODS: Nine patients with giant cell tumors of the mobile spine with invasion of the adjacent vertebrae confirmed by pathology were enrolled. Eight patients had pure giant cell tumors (GCTs), while one patient also had an aneurysmal bone cyst. All patients underwent conventional computed tomography, three-dimensional reconstruction, and conventional magnetic resonance imaging, while seven patients also underwent post-contrast magnetic resonance imaging. RESULTS: All patients showed GCTs of the mobile spine that arose from the vertebral body and extended to the vertebral arch. The tumors showed soft-tissue attenuation with no evidence of a mineralized matrix. Pathological fracture was seen in five patients. The margin of the original tumor showed partial sclerosis in four patients and involved an adjacent vertebral body with a sclerotic rim in two patients. The tumors showed a homogeneous and similar signal intensity to the normal spinal cord on T1WI (T1-weighted image) in five patients. The cystic area of the tumors was hyperintense on T2WI in the remaining four patients, while one patient showed hemorrhage that was hyperintense on T1WI. The solid components of the GCTs show marked enhancement in all cases, while the cystic area of the tumors was observed without enhancement on contrast-enhanced images in four patients. Bone destruction of the adjacent vertebral body showed a homogeneous signal on T1WI and T2WI and marked enhancement on contrast-enhanced images. CONCLUSIONS: Giant cell tumors of the mobile spine with invasion into adjacent vertebrae are an unusual imaging finding. Radiologists should be familiar with this imaging characteristic.

Distribution patterns of microcalcifications in suspected thyroid carcinoma: a classification method helpful for diagnosis.

PURPOSE: The aim of this study was to compare the distribution patterns of microcalcifications in thyroid cancers with benign cases. METHODS: In total, 358 patients having microcalcifications on ultrasonography were analysed. Microcalcifications were categorised according to the distribution patterns: (I) microcalcifications inside one (a) or more (b) suspected nodules, (II) microcalcifications not only inside but also surrounding a suspected single (a) or multiple (b) nodules, and (III) focal (a) or diffuse (b) microcalcifications in the absence of any suspected nodule. Differences in distribution patterns of microcalcifications in benign and malignant thyroid lesions were compared. RESULTS: We found that the distribution patterns of microcalcifications differed between malignant (n = 325) and benign lesions (n = 117) (X 2 = 9.926, p < 0.01). Benign lesions were classified as type Ia (66.7%), type Ib (29.1%) or type IIIa (4.3%). The specificity of type II and type IIIb in diagnosing malignant cases was 100%. Among malignant lesions, 172 locations were classified as type Ia, 106 as type Ib, 12 as type IIa, 7 as IIb, 7 as type IIIa and 19 as type IIIb. Accompanying Hashimoto thyroiditis was most frequent in type III (51.6%). CONCLUSIONS: Types II and IIIb are highly specific for cancer detection. Microcalcifications outside a nodule and those detected in the absence of any nodule should therefore be reviewed carefully in clinical practice. KEY POINTS: • A method to classify distribution patterns of thyroid microcalcifications is presented. • Distribution features of microcalcifications are useful for diagnosing thyroid cancers. • Microcalcifications outside a suspicious nodule are highly specific for thyroid cancers. • Microcalcifications without suspicious nodules should also alert the physician to thyroid cancers.