Does FDG PET-Based Radiomics Have an Added Value for Prediction of Overall Survival in Non-Small Cell Lung Cancer?

Objectives: Radiomics and machine learning are innovative approaches to improve the clinical management of NSCLC. However, there is less information about the additive value of FDG PET-based radiomics compared with clinical and imaging variables. Methods: This retrospective study included 320 NSCLC patients who underwent PET/CT with FDG at initial staging. VOIs were placed on primary tumors only. We included a total of 94 variables, including 87 textural features extracted from PET studies, SUVmax, MTV, TLG, TNM stage, histology, age, and gender. We used the least absolute shrinkage and selection operator (LASSO) regression to select variables with the highest predictive value. Although several radiomics variables are available, the added value of these predictors compared with clinical and imaging variables is still under evaluation. Three hundred and twenty NSCLC patients were included in this retrospective study and underwent 18F-FDG PET/CT at initial staging. In this study, we evaluated 94 variables, including 87 textural features, SUVmax, MTV, TLG, TNM stage, histology, age, and gender. Image-based predictors were extracted from a volume of interest (VOI) positioned on the primary tumor. The least absolute shrinkage and selection operator (LASSO) Cox regression was used to reduce the number of variables and select only those with the highest predictive value. The predictive model implemented with the variables selected using the LASSO analysis was compared with a reference model using only a tumor stage and SUVmax. Results: NGTDM coarseness, SUVmax, and TNM stage survived the LASSO analysis and were used for the radiomic model. The AUCs obtained from the reference and radiomic models were 80.82 (95%CI, 69.01-92.63) and 81.02 (95%CI, 69.07-92.97), respectively (p = 0.98). The median OS in the reference model was 17.0 months in high-risk patients (95%CI, 11-21) and 113 months in low-risk patients (HR 7.47, p < 0.001). In the radiomic model, the median OS was 16.5 months (95%CI, 11-20) and 113 months in high- and low-risk groups, respectively (HR 9.64, p < 0.001). Conclusions: Our results indicate that a radiomic model composed using the tumor stage, SUVmax, and a selected radiomic feature (NGTDM_Coarseness) predicts survival in NSCLC patients similarly to a reference model composed only by the tumor stage and SUVmax. Replication of these preliminary results is necessary.

Multivariable Risk Modelling and Survival Analysis with Machine Learning in SARS-CoV-2 Infection.

AIM: To evaluate the performance of a machine learning model based on demographic variables, blood tests, pre-existing comorbidities, and computed tomography(CT)-based radiomic features to predict critical outcome in patients with acute respiratory syndrome coronavirus 2 (SARS-CoV-2). METHODS: We retrospectively enrolled 694 SARS-CoV-2-positive patients. Clinical and demographic data were extracted from clinical records. Radiomic data were extracted from CT. Patients were randomized to the training (80%, n = 556) or test (20%, n = 138) dataset. The training set was used to define the association between severity of disease and comorbidities, laboratory tests, demographic, and CT-based radiomic variables, and to implement a risk-prediction model. The model was evaluated using the C statistic and Brier scores. The test set was used to assess model prediction performance. RESULTS: Patients who died (n = 157) were predominantly male (66%) over the age of 50 with median (range) C-reactive protein (CRP) = 5 [1, 37] mg/dL, lactate dehydrogenase (LDH) = 494 [141, 3631] U/I, and D-dimer = 6.006 [168, 152.015] ng/mL. Surviving patients (n = 537) had median (range) CRP = 3 [0, 27] mg/dL, LDH = 484 [78, 3.745] U/I, and D-dimer = 1.133 [96, 55.660] ng/mL. The strongest risk factors were D-dimer, age, and cardiovascular disease. The model implemented using the variables identified using the LASSO Cox regression analysis classified 90% of non-survivors as high-risk individuals in the testing dataset. In this sample, the estimated median survival in the high-risk group was 9 days (95% CI; 9-37), while the low-risk group did not reach the median survival of 50% (p < 0.001). CONCLUSIONS: A machine learning model based on combined data available on the first days of hospitalization (demographics, CT-radiomics, comorbidities, and blood biomarkers), can identify SARS-CoV-2 patients at risk of serious illness and death.

Increased myocardial 18F-FDG uptake as a marker of Doxorubicin-induced oxidative stress.

BACKGROUND: Oxidative stress and its interference on myocardial metabolism play a major role in Doxorubicin (DXR) cardiotoxic cascade. METHODS: Mice models of neuroblastoma (NB) were treated with 5 mg DXR/kg, either free (Free-DXR) or encapsulated in untargeted (SL[DXR]) or in NB-targeting Stealth Liposomes (pep-SL[DXR] and TP-pep-SL[DXR]). Control mice received saline. FDG-PET was performed at baseline (PET1) and 7 days after therapy (PET2). At PET2 Troponin-I and NT-proBNP were assessed. Explanted hearts underwent biochemical, histological, and immunohistochemical analyses. Finally, FDG uptake and glucose consumption were simultaneously measured in cultured H9c2 in the presence/absence of Free-DXR (1 µM). RESULTS: Free-DXR significantly enhanced the myocardial oxidative stress. Myocardial-SUV remained relatively stable in controls and mice treated with liposomal formulations, while it significantly increased at PET2 with respect to baseline in Free-DXR. At this timepoint, myocardial-SUV was directly correlated with both myocardial redox stress and hexose-6-phosphate-dehydrogenase (H6PD) enzymatic activity, which selectively sustain cellular anti-oxidant mechanisms. Intriguingly, in vitro, Free-DXR selectively increased FDG extraction fraction without altering the corresponding value for glucose. CONCLUSION: The direct correlation between cardiac FDG uptake and oxidative stress indexes supports the potential role of FDG-PET as an early biomarker of DXR oxidative damage.

G6Pase location in the endoplasmic reticulum: Implications on compartmental analysis of FDG uptake in cancer cells.

The favourable kinetics of 18F-fluoro-2-deoxyglucose (FDG) permits to depict cancer glucose consumption by a single evaluation of late tracer uptake. This standard procedure relies on the slow radioactivity loss, usually attributed to the limited tumour expression of G6P-phosphatase (G6Pase). However, this classical interpretation intrinsically represents an approximation since, as in all tissues, cancer G6Pase activity is remarkable and is confined to the endoplasmic reticulum (ER), whose lumen must be reached by phosphorylated FDG to explain its hydrolysis and radioactivity release. The present study tested the impact of G6Pase sequestration on the mathematical description of FDG trafficking and handling in cultured cancer cells. Our data show that accounting for tracer access to the ER configures this compartment as the preferential site of FDG accumulation. This is confirmed by the reticular localization of fluorescent FDG analogues. Remarkably enough, reticular accumulation rate of FDG is dependent upon extracellular glucose availability, thus configuring the same ER as a significant determinant of cancer glucose metabolism.

Obligatory role of endoplasmic reticulum in brain FDG uptake.

PURPOSE: The endoplasmic reticulum (ER) contains hexose-6P-dehydrogenase (H6PD). This enzyme competes with glucose-6P-phosphatase for processing a variety of phosphorylated hexoses including 2DG-6P. The present study aimed to verify whether this ER glucose-processing machinery contributes to brain FDG uptake. METHODS: Effect of the H6PD inhibitor metformin on brain 18F-FDG accumulation was studied, in vivo, by microPET imaging. These data were complemented with the in vitro estimation of the lumped constant (LC). Finally, reticular accumulation of the fluorescent 2DG analogue 2-[N-(7-nitrobenz-2-oxa-1,3-diazol-4-yl)amino]-2-deoxyglucose (2NBDG) and its response to metformin was studied by confocal microscopy in cultured neurons and astrocytes. RESULTS: Metformin halved brain 18F-FDG accumulation without altering whole body tracer clearance. Ex vivo, this same response faced the doubling of both glucose consumption and lactate release. The consequent fall in LC was not explained by any change in expression or activity of its theoretical determinants (GLUTs, hexokinases, glucose-6P-phosphatase), while it agreed with the drug-induced inhibition of H6PD function. In vitro, 2NBDG accumulation selectively involved the ER lumen and correlated with H6PD activity being higher in neurons than in astrocytes, despite a lower glucose consumption. CONCLUSIONS: The activity of the reticular enzyme H6PD profoundly contributes to brain 18F-FDG uptake. These data challenge the current dogma linking 2DG/FDG uptake to the glycolytic rate and introduce a new model to explain the link between 18-FDG uptake and neuronal activity.