RESUMEN
OBJECTIVES: Accurate preoperative prediction of the pathological grade of clear cell renal cell carcinoma (ccRCC) is crucial for optimal treatment planning and patient outcomes. This study aims to develop and validate a deep-learning (DL) algorithm to automatically segment renal tumours, kidneys, and perirenal adipose tissue (PRAT) from computed tomography (CT) images and extract radiomics features to predict the pathological grade of ccRCC. METHODS: In this cross-ethnic retrospective study, a total of 614 patients were divided into a training set (383 patients from the local hospital), an internal validation set (88 patients from the local hospital), and an external validation set (143 patients from the public dataset). A two-dimensional TransUNet-based DL model combined with the train-while-annotation method was trained for automatic volumetric segmentation of renal tumours, kidneys, and visceral adipose tissue (VAT) on images from two groups of datasets. PRAT was extracted using a dilation algorithm by calculating voxels of VAT surrounding the kidneys. Radiomics features were subsequently extracted from three regions of interest of CT images, adopting multiple filtering strategies. The least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and the support vector machine (SVM) for developing the pathological grading model. Ensemble learning was used for imbalanced data classification. Performance evaluation included the Dice coefficient for segmentation and metrics such as accuracy and area under curve (AUC) for classification. The WHO/International Society of Urological Pathology (ISUP) grading models were finally interpreted and visualized using the SHapley Additive exPlanations (SHAP) method. RESULTS: For automatic segmentation, the mean Dice coefficient achieved 0.836 for renal tumours and 0.967 for VAT on the internal validation dataset. For WHO/ISUP grading, a model built with features of PRAT achieved a moderate AUC of 0.711 (95% CI, 0.604-0.802) in the internal validation set, coupled with a sensitivity of 0.400 and a specificity of 0.781. While model built with combination features of the renal tumour, kidney, and PRAT showed an AUC of 0.814 (95% CI, 0.717-0.889) in the internal validation set, with a sensitivity of 0.800 and a specificity of 0.753, significantly higher than the model built with features solely from tumour lesion (0.760; 95% CI, 0.657-0.845), with a sensitivity of 0.533 and a specificity of 0.767. CONCLUSION: Automated segmentation of kidneys and visceral adipose tissue (VAT) through TransUNet combined with a conventional image morphology processing algorithm offers a standardized approach to extract PRAT with high reproducibility. The radiomics features of PRAT and tumour lesions, along with machine learning, accurately predict the pathological grade of ccRCC and reveal the incremental significance of PRAT in this prediction.
RESUMEN
OBJECTIVES: To explore the association between computed tomography (CT)-measured sex-specific abdominal adipose tissue and the pathological grade of clear cell renal cell carcinoma (ccRCC). METHODS: This retrospective study comprised 560 patients (394 males and 166 females) with pathologically proven ccRCC (467 low- and 93 high-grade). Abdominal CT images were used to assess the adipose tissue in the subcutaneous, visceral, and intermuscular regions. Subcutaneous fat index (SFI), visceral fat index (VFI), intermuscular fat index (IFI), total fat index (TFI), and relative visceral adipose tissue (rVAT) were calculated. Univariate and multivariate logistic regression analyses were performed according to sex to identify the associations between fat-related parameters and pathological grade. RESULTS: IFI was significantly higher in high-grade ccRCC patients than in low-grade patients for both men and women. For male patients with high-grade tumors, the SFI, VFI, TFI, and rVAT were significantly lower, but not for female patients. In both univariate and multivariate studies, the IFI continued to be a reliable and independent predictor of high-grade ccRCC, regardless of sex. CONCLUSIONS: Intermuscular fat index proved to be a valuable biomarker for the pathological grade of ccRCC and could be used as a reliable independent predictor of high-grade ccRCC for both males and females. CRITICAL RELEVANCE STATEMENT: Sex-specific fat adipose tissue can be used as a new biomarker to provide a new dimension for renal tumor-related research and may provide new perspectives for personalized tumor management decision-making approaches. KEY POINTS: ⢠There are sex differences in distribution of subcutaneous fat and visceral fat. ⢠The SFI, VFI, TFI, and rVAT were significantly lower in high-grade ccRCC male patients, but not for female patients. ⢠Intermuscular fat index can be used as a reliable independent predictor of high-grade ccRCC for both males and females.
