Radiomics and artificial intelligence have the potential to become a valuable tool in clinical applications. Frequently, radiomic analyses through machine learning methods present issues caused by high dimensionality and multicollinearity, and redundant radiomic features are usually removed based on correlation analysis. We assessed the effect of preprocessing—in terms of voxel size resampling, discretization, and filtering—on correlation-based dimensionality reduction in radiomic features from cardiac T1 and T2 maps of patients with hypertrophic cardiomyopathy. For different combinations of preprocessing parameters, we performed a dimensionality reduction of radiomic features based on either Pearson’s or Spearman’s correlation coefficient, followed by the computation of the stability index. With varying resampling voxel size and discretization bin width, for both T1 and T2 maps, Pearson’s and Spearman’s dimensionality reduction produced a slightly different percentage of remaining radiomic features, with a relatively high stability index. For different filters, the remaining features’ stability was instead relatively low. Overall, the percentage of eliminated radiomic features through correlation-based dimensionality reduction was more dependent on resampling voxel size and discretization bin width for textural features than for shape or first-order features. Notably, correlation-based dimensionality reduction was less sensitive to preprocessing when considering radiomic features from T2 compared with T1 maps.

Background: A fair amount of microcalcifications sent for biopsy are false positives. The study investigates whether quantitative radiomic features extracted from digital breast tomosynthesis (DBT) can be an additional and useful tool to discriminate between benign and malignant BI-RADS category 4 microcalcification. Methods: This retrospective study included 252 female patients with BI-RADS category 4 microcalcifications. The patients were divided into two groups according to micro-histopathology: 126 patients with benign lesions and 126 patients with certain or possible malignancies. A total of 91 radiomic features were extracted for each patient, and the 12 most representative features were selected by using the agglomerative hierarchical clustering method. The binary classification task of the two groups was carried out by using four different machine-learning algorithms (i.e., linear support vector machine (SVM), radial basis function (RBF) SVM, logistic regression (LR), and random forest (RF)). Accuracy, sensitivity, sensibility, and the area under the curve (AUC) were calculated for each of them. Results: The best performance was achieved using the RF classifier (AUC = 0.59, 95% confidence interval 0.57–0.60; sensitivity = 0.56, 95% CI 0.54–0.58; specificity = 0.61, 95% CI 0.59–0.63; accuracy = 0.58, 95% CI 0.57–0.59). Conclusions: DBT-based radiomic analysis seems to have only limited potential in discriminating benign from malignant microcalcifications.

Given the inherent characteristics of nonlinearity and nonstationarity of iterative reconstruction algorithms in computed tomography (CT) imaging, this study aimed to perform, for the first time, a voxel-based characterization of noise properties in CT imaging with the ASiR-V and ASiR algorithms as compared with conventional filtered back projection (FBP). Multiple repeated scans of the Catphan-504 phantom were carried out. CT images were reconstructed using FBP and ASiR/ASiR-V with different blending levels of reconstruction (20%, 40%, 60%, 80%, 100%). Noise maps and their nonuniformity index (NUI) were obtained according to the approach proposed by the report of AAPM TG-233. For the homogeneous CTP486 module, ASiR-V/ASiR allowed a noise reduction of up to 63.7%/52.9% relative to FBP. While the noise reduction values of ASiR-V-/ASiR-reconstructed images ranged up to 33.8%/39.9% and 31.2%/35.5% for air and Teflon contrast objects, respectively, these values were approximately 60%/50% for other contrast objects (PMP, LDPE, polystyrene, acrylic, Delrin). Moreover, for all contrast objects but air and Teflon, ASiR-V showed a greater noise reduction potential than ASiR when the blending level was ≥40%. While noise maps of the homogenous CTP486 module showed only a slight spatial variation of noise (NUI < 5.2%) for all reconstruction algorithms, the NUI values of iterative-reconstructed images of the nonhomogeneous CTP404 module increased nonlinearly with blending level and were 19%/15% and 6.7% for pure ASiR-V/ASiR and FBP, respectively. Overall, these results confirm the potential of ASiR-V and ASiR in reducing noise as compared with conventional FBP, suggesting, however, that the use of pure ASiR-V or ASiR might be suboptimal for specific clinical applications.