Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma.

AIM: To identify combined positron-emission tomography (PET)/magnetic resonance imaging (MRI)-based radiomics as a surrogate biomarker of intratumour disease risk for molecular subtype ccA and ccB in patients with primary clear cell renal cell carcinoma (ccRCC). MATERIALS AND METHODS: PET/MRI data were analysed retrospectively from eight patients. One hundred and sixty-eight radiomics features for each tumour sampling based on the regionally sampled tumours with 23 specimens were extracted. Sparse partial least squares discriminant analysis (SPLS-DA) was applied to feature screening on high-throughput radiomics features and project the selected features to low-dimensional intrinsic latent components as radiomics signatures. In addition, multilevel omics datasets were leveraged to explore the complementing information and elevate the discriminative ability. RESULTS: The correct classification rate (CCR) for molecular subtype classification by SPLS-DA using only radiomics features was 86.96% with permutation test p=7×10-4. When multi-omics datasets including mRNA, microvascular density, and clinical parameters from each specimen were combined with radiomics features to refine the model of SPLS-DA, the best CCR was 95.65% with permutation test, p<10-4; however, even in the case of generating the classification based on transcription features, which is the reference standard, there is roughly 10% classification ambiguity. Thus, this classification level (86.96-95.65%) of the proposed method represents the discriminating level that is consistent with reality. CONCLUSION: Featured with high accuracy, an integrated multi-omics model of PET/MRI-based radiomics could be the first non-invasive investigation for disease risk stratification and guidance of treatment in patients with primary ccRCC.

Does hyperglycemia affect the diagnostic value of 18F-FDG PET/CT?

BACKGROUND: Net cellular uptake of (18)F-FDG is adversely affected by elevated plasma glucose levels. The purpose of our study was to investigate the influence of hyperglycemic state at the time of (18)F-FDG injection on the diagnostic accuracy of (18)F-FDG PET/CT. METHOD: Pre-scan plasma glucose levels of all patients who were referred for PET/CT with an oncologic indication during the year 2005 were reviewed. All seventy-six patients (50 men, 26 women, mean age ± SD: 65.5 ± 9.7 years) with pre-scan glucose level higher than 140 mg/dL (mean plasma glucose level ± SD: 168.7 ± 30.8, ranging from 140 to 260 mg/dL) were enrolled into our study. The accuracy of PET/CT scans was assessed using concurrent or follow-up CT, MRI and histologic evidences as well as clinical follow-up as the reference standard. RESULTS: PET/CT was true positive in 37 patients, true-negative in 30 patients, false negative in 6 patients and false positive in 3 patients. Overall sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy of (18)F-FDG PET/CT on a patient basis were 86%, 90.9%, 92.5%, 83.3% and 88.1%, respectively. Diabetes mellitus was recorded in 50 patients. No significant diagnostic accuracy difference between diabetics and non-diabetics was noticed. CONCLUSION: Our study suggests that (18)F-FDG accumulation of malignant lesions remains sufficiently high for reliable qualitative clinical diagnosis in chronic and acute hyperglycemic states. However, regarding the discordant and inconclusive results of the available reports and the remarkable concerns with reference to the adverse effects of elevated plasma glucose levels on the diagnostic accuracy of (18)F-FDG PET/CT scans, further direct clues seems to be required and should be provided by future studies.