ABSTRACT
PURPOSE: This retrospective study was undertaken to assess the predictive efficacy of 18F-FDG PET/CT -derived radiomic features concerning the co-mutation status of epidermal growth factor receptor (EGFR) and TP53 in LUAD. METHODS: A cohort of 150 LUAD patients underwent pretreatment 18F-FDG PET/CT scans with known mutation status of EGFR and TP53 were collected. The feature extraction based on their PET/CT images utilized the Pyradiomics package based on the 3D Slicer. The optimal radiomic features were selected through correlation analysis and the Gradient Boosting Decision Tree (GBDT) algorithm, followed by the construction of the radiomic model. The clinical model incorporated meaningful clinical variables, whereas the complex model integrated both the radiomic and clinical models. The area under the receiver operating characteristic curve (AUC) facilitated the comparison of prediction performance across the three models. The DCA gauged the clinical utility of these models. RESULTS: The patient cohort was randomly allocated into a training set (n = 105) and a validation set (n = 45) in a 7:3 ratio. Eleven PET and eleven CT optimal radiomic features were selected to construct the radiomic model. The model showed a good ability to discriminate the co-occurrence of EGFR and TP53, with AUC equal to 0.850 in the training set, and 0.748 in the validation set, compared with 0.750 and 0.626 for the clinical model. The complex model exhibited the highest AUC values, with 0.880 and 0.794 in both sets, but there were no significant differences compared to the radiomic model. The DCA revealed favorable clinical value.
ABSTRACT
PURPOSE: The objective of this investigation is to explore the capability of baseline 18F-FDG PET/CT radiomics to predict the prognosis of diffuse large B-cell lymphoma (DLBCL) with extranodal involvement (ENI). METHODS: 126 patients diagnosed with DLBCL with ENI were included in the cohort. The least absolute shrinkage and selection operator (LASSO) Cox regression was utilized to refine the optimum subset from the 1328 features. Cox regression analyses were employed to discern significant clinical variables and conventional PET parameters, which were then employed with radiomics score to develop combined model for predicting both progression-free survival (PFS) and overall survival (OS). The fitness and the predictive capability of the models were assessed via the Akaike information criterion (AIC) and concordance index (C-index). RESULTS: 62 patients experienced disease recurrence or progression and 28 patients ultimately died. The combined model exhibited a lower AIC value compared to the radiomics model and SDmax/clinical variables for both PFS (507.101 vs. 510.658 vs. 525.506) and OS (215.667 vs. 230.556 vs. 219.313), respectively. The C-indices of the combined model, radiomics model, and SDmax/clinical variables were 0.724, 0.704, and 0.615 for PFS, and 0.842, 0.744, and 0.792 for OS, respectively. Kaplan--Meier curves showed significantly higher rates of relapse and mortality among patients classified as high-risk compared to those classified as low-risk (all P < 0.05). CONCLUSIONS: The combined model of clinical variables, conventional PET parameters, and baseline PET/CT radiomics features demonstrates a higher accuracy in predicting the prognosis of DLBCL with ENI.
ABSTRACT
Previous studies in our lab found that heregulin-1β with SKP-SCs (neurons and Schwann cells differentiated from SKPs) / ANA (acellular nerve allograft) transplantation represented a powerful therapeutic approach, and facilitates the efficacy of ANA in peripheral nerve injury. In this study, our purpose is to explore the mechanism between them. Firstly we transplanted ANA + SKP-SC + heregulin-1β into rats with right sciatic nerve injury and then detected the miR-21 and SOX2 (SRY-like HMG box 2) levels. Then we transfected miR-21 inhibitor in SCs (Schwann cells) which induced in hypoxic condition before harvesting. Then we detected expression of miR-21 and SOX2 using real time-PCR and western blot assay. Results in vivo showed that the expression of miR-21 in rats was inhibited after transplantation of ANA + SKP-SC + heregulin-1β with induced SOX2 accordingly. Then we found miR-21 was increased time dependently in hypoxic SCs with decreased SOX2 accordingly. After miR-21 inhibitor transfection, miR-21 level was reduced and SOX2 was up-regulated. Meanwhile it was also showed that the miR-21 inhibitor induced the hypoxic SCs growth, decreased the apoptosis with cell cycle changing. In conclusion miR-21 and its target gene SOX2 played important role in peripheral nerve injury. Heregulin-1β may increase the synergistic effect between SKP-SC and ANA through inhibiting miR-21 in vivo.