ABSTRACT
(1) Background: Open-source software tools are available to estimate proton density fat fraction (PDFF). (2) Methods: We compared four algorithms: complex-based with graph cut (GC), magnitude-based (MAG), magnitude-only estimation with Rician noise modeling (MAG-R), and multi-scale quadratic pseudo-Boolean optimization with graph cut (QPBO). The accuracy and reliability of the methods were evaluated in phantoms with known fat/water ratios and a patient cohort with various grades (S0-S3) of steatosis. Image acquisitions were performed at 1.5 Tesla (T). (3) Results: The PDFF estimates showed a nearly perfect correlation (Pearson r = 0.999, p < 0.001) and inter-rater agreement (ICC = from 0.995 to 0.999, p < 0.001) with true fat fractions. The absolute bias was low with all methods (0.001-1%), and an ANCOVA detected no significant difference between the algorithms in vitro. The agreement across the methods was very good in the patient cohort (ICC = 0.891, p < 0.001). However, MAG estimates (-2.30% ± 6.11%, p = 0.005) were lower than MAG-R. The field inhomogeneity artifacts were most frequent in MAG-R (70%) and GC (39%) and absent in QPBO images. (4) Conclusions: The tested algorithms all accurately estimate PDFF in vitro. Meanwhile, QPBO is the least affected by field inhomogeneity artifacts in vivo.
ABSTRACT
Introduction: This study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners. Materials and methods: Preoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson's correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The "Kidney Tumor Segmentation 2019" (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist's. Results: The training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model's performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69. Conclusion: Radiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.
