Computed tomography (CT) and magnetic resonance imaging (MRI) scans of 11 patients with histologically proven cervical chordoma were retrospectively evaluated. Imaging features assessed included location, morphology, association with adjacent structures, vertebral destruction, status of cortical bone, periosteal reaction, attenuation and calcification by CT, and signal intensity and enhancement pattern by MRI. Of 7 cases with CT, 6 exhibited lytic-sclerotic bone destruction. A total of 5 cases exhibited pressure erosion of outer cortex, 3 of which had spiculated periosteal reaction. Calcification was observed in 3 cases. All cases were heterogeneous and hypodense. MRI T2-weighted images (n=10) revealed heterogeneous hyperintense (n=5), intermediate (n=2) and intermediate-hyperintense signal intensity (n=3). Hypointense septa between lobules (n=5) and stripes (n=3) were observed on T2-weighted images. Post-contrast magnetic resonance images (n=6) demonstrated marked heterogeneous (n=3) and ring-like (n=3) enhancement. CT scanning is valuable in revealing the lytic-sclerotic bone destruction, pressure erosion of outer cortex and calcification. MRI is useful in demonstrating the results of soft tissue mass. The two examinations are necessary for differential diagnosis of patients with suspected cervical chordoma.
Pigmented villonodular synovitis (PVNS) of the ankle is a rare benign proliferative growth of the synovium. Studies of the radiologic characteristics of ankle PVNS are sparse.To characterize the radiologic features of ankle PVNS, five patients with histologically proven ankle PVNS were retrospectively studied. The features of their radiographs, computed tomographic scans, and magnetic resonance images were reviewed, with emphasis on the morphological features, extension, margin, bone involvement, signal intensity, and degree of magnetic resonance enhancement.All five lesions were diffuse, affecting the ankle and distal tibiofibular joint; three lesions also involved the subtalar joint. Radiography demonstrated extrinsic bone erosions with marginal sclerosis of the involved joints in all of the patients, but computed tomography identified this much better than did radiography. Magnetic resonance imaging revealed multiple lobulated soft-tissue masses in all of the cases. These soft-tissue masses surrounded the flexor hallux longus tendon and were hypointense on T1-weighted images, with a heterogeneous signal in two cases and homogenous hypointensity in three cases on fat-suppressed T2-weighted images. In one patient who underwent gadolinium-enhanced imaging, the masses showed intense enhancement.Magnetic resonance imaging is the best way to reveal ankle PVNS. Magnetic resonance imaging findings of predominant hypointensity on all pulse sequences and standard radiography findings of bone erosion with marginal sclerosis are characteristic.
Background Preoperative prediction of the grade of soft tissue sarcomas (STSs) is important because of its effect on treatment planning. Purpose To assess the value of radiomics features in distinguishing histological grades of STSs. Study Type Retrospective. Population In all, 113 patients with pathology‐confirmed low‐grade (grade I), intermediate‐grade (grade II), or high‐grade (grade III) soft tissue sarcoma were collected. Field Strength/Sequence The 3.0T axial T 1 ‐weighted imaging (T 1 WI) with 550 msec repetition time (TR); 18 msec echo time (TE), 312 × 312 matrix, fat‐suppressed fast spin‐echo T 2 WI with 4291 msec TR, 85 msec TE, 312 × 312 matrix. Assessment Multiple machine‐learning methods were trained to establish classification models for predicting STS grades. Eighty STS patients (18 low‐grade [grade I]; 62 high‐grade [grades II–III]) were enrolled in the primary set and we tested the model with a validation set with 33 patients (7 low‐grade, 26 high‐grade). Statistical Tests 1) Student's t ‐tests were applied for continuous variables and the χ 2 test were applied for categorical variables between low‐grade STS and high‐grade STS groups. 2) For feature subset selection, either no subset selection or recursive feature elimination was performed. This technology was combined with random forest and support vector machine‐learning methods. Finally, to overcome the disparity in the frequencies of the STS grades, each machine‐learning model was trained i) without subsampling, ii) with the synthetic minority oversampling technique, and iii) with random oversampling examples, for a total of 12 combinations of machine‐learning algorithms that were assessed, trained, and tested in the validation cohort. Results The best classification model for the prediction of STS grade was a combination of features selected by recursive feature elimination and random forest classification algorithms with a synthetic minority oversampling technique, which had an area under the curve of 0.9615 (95% confidence interval 0.8944–1.0) in the validation set. Data Conclusion Radiomics feature‐based machine‐learning methods are useful for distinguishing STS grades. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:791–797.
OBJECTIVE. The purpose of this study was to assess the value of radiomics features for differentiating soft tissue sarcomas (STSs) of different histopathologic grades. MATERIALS AND METHODS. The T1-weighted and fat-suppressed T2-weighted MR images of 70 STSs of varying grades (35 low-grade [grades 1 and 2], 35 high-grade [grade 3]) formed the primary dataset used to train multiple machine learning algorithms for the construction of models for assigning STS grade. The models were tested with a separate validation dataset. RESULTS. Different machine learning algorithms had different strengths and weaknesses. The best classification algorithm for the prediction of STS grade had a combination of the least absolute shrinkage and selection operator feature selection method and the random forest classification algorithm (AUC, 0.9216; 95% CI, 0.8437-0.9995) in the validation set. The accuracy of the combined methods applied to the validation set was 91.43%; sensitivity, 88.24%; and specificity, 94.44%. CONCLUSION. Because of tumor heterogeneity, initial biopsy grade may be an underestimate of the final grade identified in extensive histopathologic analysis of surgical specimens. This creates an urgent need to construct an accurate preoperative approach to grading STS. This radiomics study revealed the optimal machine learning approaches for differentiating STS grades. This capability can enhance the precision of preoperative diagnosis.
Objective To explore the radiological diagnosis of primary malignant fibrous histiocytoma (MFH) of bone. Methods Sixteen patients with biopsy-or surgery-confirmed MFH received both plain X-ray and CT examinations, among whom six patients simultaneously received MRI. The imaging features were analyzed and the differential diagnoses were assessed. Results (1) Plain X-ray findings: All these lesions showed irregularly osteolytic, accompanied by cortical destruction. Five patients had varied degrees of cortical expansion, 12 had large soft tissue masses adjacent to the lesions, and only 2 had periosteal reaction. (2) CT findings: All lesions were osteolytic areas but had no evidences that its internal architecture had been replaced by soft tissue mass, and the cortical adjacent to the lesions were permeative osteolysis. Four patients had internal or marginal crest within the lesions and marginal inconsecutive osteosclerosis. Twelve had large soft tissue masses but without any calcification and residual architecture adjacent to the lesions, among which 3 patients had solitary or multiple cystic attenuation areas within the masses. No clear periosteal reaction was observed on CT. (3) MRI findings: All of lesions in 6 patients who received MRI showed inhomogeneous long T1 and long T2 abnormal signal intensity with soft tissue masses adjacent to the osteo-destructions. Conclusions The imaging manifestations of MFH were specific to some extent. Combined utilization of plain X-ray, CT, and MRI is helpful for the diagnosis and differential diagnosis of MFH.
To characterize and evaluate CT and MRI features of extremity soft tissue adult fibrosarcoma.CT and MRI images from 10 adult patients with pathologically proven fibrosarcomas were retrospectively analyzed with regard to tumor location, size, number, shape, margins, attenuation, signal intensity, and enhancement patterns on MR images. Additionally, the relationships between lesions, deep fascia, and change in adjacent bones were also assessed.Nineteen tumor lesions in 10 patients were selected for this study. Eighteen lesions were lobulated and one was oval in shape. Most cases were located under the deep fascia, including seven cases that had a nodular lump adjacent to the deep fascia and one case that had broken lesion through the deep fascia. On CT, the adult fibrosarcomas mostly showed iso-attenuated soft tissue masses (n = 6). On MRI, all the cases (n = 9) displayed low signal on T1-weighted imaging (T1WI) and heterogeneous low and high intensity signals on T2-weighted imaging (T2WI), with band-like areas of low signal on both T1WI and T2WI. On contrast-enhanced MRI images, three cases showed heterogeneous peripheral enhancement and one case demonstrated a spoke-wheel-like enhancement. Eight cases showed muscle edema signals in the peritumoral muscle and one case involved adjacent bone.CT and MR imaging have respective advantages in diagnosing adult fibrosarcoma. Combined application of CT and MR is recommended for patients with suspected adult fibrosarcoma.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)