Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Abstract

IntroductionThis 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 methodsPreoperative 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.ResultsThe 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.ConclusionRadiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

Emerging Trends in AI and Radiomics for Bladder, Kidney, and Prostate Cancer: A Critical Review

“…This model utilized radiomic features derived from the CT scans of 209 patients, leading to a classification system with accuracy rivaling expert radiologists. This achievement highlights the potential of radiogenomics to enhance cancer diagnostics and influence clinical decision-making [21]. These findings have profound implications.…”

“…The application of radiogenomics is transformative in oncology, where treatments and prognoses are increasingly tailored to each patient's unique tumor characteristics. A notable study in this area involved constructing an ML model to distinguish between nonclear cell RCCs and clear cell RCCs (ccRCCs) [21]. This model utilized radiomic features derived from the CT scans of 209 patients, leading to a classification system with accuracy rivaling expert radiologists.…”

CT−based radiomics signature for differentiating pyelocaliceal upper urinary tract urothelial carcinoma from infiltrative renal cell carcinoma

“…Although radiomics analysis has already been applied for differentiating renal tumors, previously published studies mostly focused on identifying benign and malignant renal lesions or distinguishing different types of RCCs such as clear cell renal cell carcinoma, renal papillary cell carcinoma, and chromophobe cell renal cell carcinoma ( 28 ). We first used radiomics analysis to differentiate clear cell renal cell carcinoma and urothelial carcinomas with good accuracy.…”

Computed tomography texture analysis to discriminate fungal and non-fungal infected fluid collections

“…This was shown in previous studies in the oncologic field, who could employ texture analysis to reflect histopathologic features of tumors. [15][16][17] It seems plausible to translate these results to non-oncological disorders.…”

“…12 Beyond that, CT texture features can provide information regarding the microstructure of tissues, which was shown in preliminary studies. [13][14][15][16][17][18][19] This is why texture features might also help to better characterize the content and different aspects of fluid collections to identify fungal associated changes, such as hyphae.…”