RESUMO
Since the Bosniak cysts classification is highly reader-dependent, automated tools based on radiomics could help in the diagnosis of the lesion. This study is an initial step in the search for radiomic features that may be good classifiers of benign-malignant Bosniak cysts in machine learning models. A CCR phantom was used through five CT scanners. Registration was performed with ARIA software, while Quibim Precision was used for feature extraction. R software was used for the statistical analysis. Robust radiomic features based on repeatability and reproducibility criteria were chosen. Excellent correlation criteria between different radiologists during lesion segmentation were imposed. With the selected features, their classification ability in benignity-malignity terms was assessed. From the phantom study, 25.3% of the features were robust. For the study of inter-observer correlation (ICC) in the segmentation of cystic masses, 82 subjects were prospectively selected, finding 48.4% of the features as excellent regarding concordance. Comparing both datasets, 12 features were established as repeatable, reproducible, and useful for the classification of Bosniak cysts and could serve as initial candidates for the elaboration of a classification model. With those features, the Linear Discriminant Analysis model classified the Bosniak cysts in terms of benignity or malignancy with 88.2% accuracy.
RESUMO
PURPOSE: To evaluate the accuracy of unenhanced magnetic resonance angiography (U-MRA) using balanced steady-state free precession (SSFP) sequences with inversion recovery (IR) pulses for the evaluation of renal artery stenosis. MATERIALS AND METHODS: U-MRA was performed in 24 patients with suspected main renal artery stenosis. Two radiologists evaluated the quality of the imaging studies and the ability of U-MRA to identify hemodynamically significant main renal artery stenosis (RAS) defined as a stenosis ≥50% when compared to gold standard tests: contrast-enhanced magnetic resonance angiography (CE-MRA) (18 patients) or digital subtraction arteriography (DSA) (6 patients). RESULTS: A total of 44 main renal arteries were evaluated. Of them, 32 renal arteries could be assessed with U-MRA. When CE-MRA or DSA was used as the reference standard, nine renal arteries had hemodynamically significant RAS. U-MRA correctly identified eight out of nine arteries as having ≥50% RAS, and correctly identified 22 out of 23 arteries as not having significant RAS, with a sensitivity of 88.8%, a specificity of 95.65%, positive and negative predictive value of 88.8% and 95.65%, respectively, and an accuracy of 93.75%. Renal artery fibromuscular dysplasia (FMD) was observed in the two misclassified arteries. CONCLUSION: U-MRA is a reliable diagnostic method to depict normal and stenotic main renal arteries. U-MRA can be used as an alternative to contrast-enhanced magnetic resonance angiography or computer tomography angiography in patients with renal insufficiency unless FMD is suspected.