No abstract

To investigate the value of the radiomic models for differentiating parasellar cavernous hemangiomas from meningiomas and to compare the classification performance with different MR sequences and classifiers. A total of 96 patients with parasellar tumors (40 cavernous hemangiomas and 56 meningiomas) were enrolled in this retrospective multiple-center study. Univariate and multivariate analyses were performed to identify the clinical factors and semantic features of MRI scans. Radiomics features were extracted from five MRI sequences using radiomics software. Three feature selection methods and six classifiers were evaluated in the training cohort to construct favorable radiomic machine-learning classifiers. The performance of different classifiers was evaluated using the AUC and compared to neuroradiologists. The detection rates of T1WI, T2WI, and CE-T1WI for parasellar cavernous hemangiomas and meningiomas were approximately 100%. In contrast, the ADC maps had the detection rate of 18/22 and 19/25, respectively, (AUC, 0.881) with 2.25 cm as the critical value diameter. Radiomics models with the SVM and KNN classifiers based on T2WI and ADC maps had favorable predictive performances (AUC > 0.90 and F-score value > 0.80). These models outperformed MRI model (AUC 0.805) and neuroradiologists (AUC, 0.756 and 0.545, respectively). Radiomic models based on T2WI and ADC and combined with SVM and KNN classifiers have the potential to be a viable method for differentiating parasellar hemangiomas from meningiomas. T2WI is more universally applicable than ADC values due to its higher detection rate for parasellar tumors.

No abstract

Spiral computed tomography (SCT) with its advantage of multi-dimensional reconstruction function can not only give the cross-sectional images of the lesion but also show the lesion images in three dimensions, and this advantage greatly broadens its usefulness in diagnosing the diseases in various parts of the body. For the diagnosis of the urinary tract diseases, SCT also plays a very important role. In this research, we collected 16 cases with primary ureteral carcinoma between May 2001 and April 2006. We reviewed their SCT manifestations and compared them with the histopathological reports and staging in an attempt to explore the characteristics of the primary ureteral carcinoma (PUC) and discuss the value of spiral CT in the diagnosis of PUC. Materials and methodsOf the 16 patients, 8 were males and 8 were females aged from 45-87 years old with mean age of 67 years. 11 patients presented with intermittent gross painless hematuria, among them 5 with flank pain; 2 patients with colic flank pain; 2 with dull flank pain; 1 patient was discovered with hydronephrosis on routine physical examination. 12 patients underwent nephroureterectomy and their diseases were confirmed pathologically; 2 patients underwent exploratory operation but the tumors were proved to be unresectable and the diseases were confirmed through lymph node biopsy; In 2 cases the diagnosis were made by ureteral endoscopy and biopsy. All tumors were single-sided with 8 on the left side and 8 on the right-side respectively. Tumor occurred in the pelvo-ureteral junction in 3 patients, in the upper segment of the ureter in 2, in the middle segment in 1, in the middle lower segment in 2, in the lower segment in 6, and involved the upper, middle and a part of lower segment of the ureter in 2 patients. Transitional cell carcinomas were found in 15 patients with pathological grade of borderline between I-II in 4 cases, II in 6, borderline between II-III in 1 case, and III in 4. Squamous cell carcinoma was found in 1 patient. 1 case was pathological stage zero (pT0), 2 cases were pT1, 3 cases were pT2, 6 cases were pT3, 2 cases were pT4. 2 patients didn't undergo operation, so the pathological stages of their diseases were unclear (their pathological grades were borderline I-II and III respectively).We used the pathological staging method which is widely accepted in our country: stage T0: the tumor is localized in the mucous membrane; stage T1: invades the lamina propria; stage T2: invades the muscularis; stage Abstract Objective: To explore the characteristics of the primary ureteral carcinoma (PUC) and discuss the value of spiral CT (SCT) in the diagnosis of PUC. Methods: The SCT findings of the primary ureteral carcinoma in 16 cases were analyzed and compared with the histopathological diagnosis and staging. Results: The transverse diameters of the lesions were 1.0-2.1 cm, and the longitudinal lengths were 1.5-15.2 cm. There were no statistically significant differences (P>0.1) in diameters and lengths among the low staging group (pT0-T2) and the high s...

To investigate the value of the radiomic models for differentiating parasellar cavernous hemangiomas from meningiomas and to compare the classification performance with different MR sequences and classifiers. A total of 96 patients with parasellar tumors (40 cavernous hemangiomas and 56 meningiomas) were enrolled in this retrospective multiple-center study. Radiomics features were extracted from five MRI sequences using radiomics software. Three feature selection methods and six classifiers were evaluated in the training cohort to construct favorable radiomic machine-learning classifiers. The performance of different classifiers was evaluated using the AUC and compared to neuroradiologists. The detection rates of T1WI, T2WI, and CE-T1WI for parasellar cavernous hemangiomas and meningiomas were approximately 100%. In contrast, the ADC maps had the detection rate of 18/22 and 19/25, respectively, (AUC, 0.881) with 2.25 cm as the critical value diameter. Radiomics models with the SVM and KNN classifiers based on T2WI and ADC maps had favorable predictive performances (AUC > 0.90 and F-score value > 0.80). These models outperformed neuroradiologists (AUC, 0.756 and 0.545, respectively). Radiomic models based on T2WI and ADC and combined with SVM and KNN classifiers have the potential to be a viable method for differentiating parasellar hemangiomas from meningiomas. T2WI is more universally applicable than ADC values due to its higher detection rate for parasellar tumors.