Background/Objectives: Perirenal fat (PRF) constitutes a critical yet understudied component of the tumor microenvironment in clear cell renal cell carcinoma (ccRCC). While radiomics enables non-invasive tissue characterization, whether PRF-derived features can simultaneously predict both TNM stage and histological grade, and whether optimal peritumoral distances differ between these distinct biological targets, remains unexplored in the literature. Methods: This multi-cohort retrospective study included 474 histopathologically confirmed ccRCC patients from three independent datasets (2007–2023). Automated nnU-Net segmentation delineated tumors and kidneys. Concentric PRF regions were systematically generated at 1–10 mm radial distances, yielding 18 distinct regions of interest. From each ROI, 1409 radiomic features were extracted using PyRadiomics. Sequential feature selection employed correlation filtering, SHAP-guided elimination, and LASSO regularization. Multiple machine learning classifiers underwent hyperparameter optimization with rigorous cross-cohort validation. Results: Systematic ROI screening revealed target-specific optimal distances: 4 mm PRF for TNM staging versus 10 mm PRF for histological grading. For staging, the integrated model (tumor + PRF radiomics + clinical variables) achieved AUC 0.829 (95% CI 0.781–0.877), sensitivity 80.2%, and specificity 67.8%. For grading, the combined model achieved AUC 0.780 (95% CI 0.598–0.962), sensitivity 79.7%, and specificity 63.3%, significantly outperforming all single-compartment models (DeLong p < 0.001). Conclusions: This study establishes that PRF radiomics enables accurate simultaneous non-invasive prediction of both TNM stage and histological grade in ccRCC. The novel discovery that optimal peritumoral distances differ substantially by prediction target (4 mm versus 10 mm) suggests distinct biological underpinnings for stage- and grade-related microenvironmental alterations, with important methodological implications for radiomic model development in oncology.

Objectives: 18F-FDG PET/CT is central to head and neck cancer (HNC) care, yet most radiomic models use PET or CT alone. We quantified the discrimination of fused PET/CT models and what fusion adds. Methods: Following PRISMA 2020 and a registered protocol (PROSPERO CRD420261319855), seven sources were searched, supplemented by citation and proceedings searching. Reports sharing patients were grouped into independent cohort lineages, which served as the unit of analysis, and every synthesis included one analysis per lineage. The estimand was each report’s within-study difference between its fused model and its own comparator. Two confirmatory hypotheses were specified in the statistical analysis plan, with a Bonferroni threshold of 0.025. Random-effects models used REML with Hartung-Knapp; risk of bias used PROBAST+AI, reporting completeness METRICS v1.0 and diagnostic accuracy QUADAS-3. Results: 100 studies were included, arising from 31 independent cohort lineages. Fused models exceeded PET-only models by 0.042 (95% CI 0.014 to 0.070) on the concordance index (6 lineages; p = 0.0115), meeting the confirmatory threshold, and CT-only models by 0.037 (0.002 to 0.072; p = 0.0429), which did not. Pooled absolute discrimination was 0.711 (95% CI 0.659 to 0.763). Diagnostic evidence was reported by task and not pooled. Only 25 studies could contribute to any pooled estimate, chiefly because 71 of 100 fused estimates lacked a recoverable measure of precision; all were at high risk of bias in the analysis domain. Conclusions: Fusing PET and CT radiomic information improves survival discrimination in HNC, most securely against the PET-only baseline. The advantage over CT-only models was smaller and did not meet the multiplicity-adjusted criterion, and none was established for diagnostic classification. Incremental benefit depends on the comparator, the cohort and the endpoint; it does not follow from fusion itself.

Background/Objectives: Preoperative risk stratification in renal cell carcinoma (RCC) remains challenging for tumor aggressiveness and for adherent perinephric fat (APF) relevant to surgical planning. Although intratumoral radiomics are established, the peritumoral and perirenal fat microenvironment is biologically active and may encode imaging biomarkers. This systematic review and meta-analysis evaluated CT-based peritumoral and perirenal fat radiomics for preoperative grading, staging, and APF prediction and examined whether fat-derived features add incremental value beyond intratumoral models. Methods: Following PRISMA 2020 and a registered protocol (PROSPERO CRD420251150155), databases were searched through March 2026, with documented verification searches through August 2026. Eligible studies extracted CT radiomics from peritumoral or perirenal fat in adults with RCC and reported discrimination metrics. Random-effects meta-analyses (restricted maximum likelihood with Hartung–Knapp intervals) were performed; incremental value was estimated from nested within-study AUC differences under predefined rules; and methodological quality was assessed with PROBAST, RQS, METRICS, and TRIPOD, and certainty with an adapted GRADE framework. Results: Twenty-five retrospective studies (10,761 patients) were included. Fat radiomics were most consistent for APF prediction (pooled AUC 0.848, 95% CI 0.738–0.917; I² = 0%). Pooled AUCs were 0.772 (0.599–0.884; I² = 93%; 95% prediction interval 0.298–0.964) for grade and 0.813 (0.681–0.899; I² = 72%) for stage. Combined fat-plus-tumor models were numerically higher than tumor-only models in 12 of 15 studies (exploratory p = 0.022), but the formally estimable nested increment (stage family, five studies) was small (delta-AUC +0.017; governing modified Hartung–Knapp 95% CI −0.008 to +0.042) and statistically compatible with no true difference; fat-only models showed no evidence of differing from tumor-only models. PROBAST rated 72% of studies at high risk of bias, and 88% originated from China. Certainty ranged from VERY LOW (grade prediction; grade-family fat-versus-tumor comparison) to LOW (all remaining outcomes). Conclusions: CT-based peritumoral and perirenal fat radiomics show the most consistent signal for APF prediction, while the measurable increment from adding fat features to tumor models is small and of unestablished clinical utility. Standardized fat segmentation, calibration and decision-curve reporting and prospective multicenter validation are required before clinical translation.