Search

Background: Accurate, noninvasive, and reliable assessment of epidermal growth factor receptor (EGFR) mutation status and EGFR molecular subtypes is essential for treatment plan selection and individualized therapy in lung adenocarcinoma (LUAD). Radiomics models based on 18F‐FDG PET/CT have great potential in identifying EGFR mutation status and EGFR subtypes in patients with LUAD. The validation of multi‐center data, model visualization, and interpretation are significantly important for the management, application and trust of machine learning predictive models. However, few EGFR‐related research involved model visualization and interpretation, and multi‐center trial. Purpose: To develop explainable optimal predictive models based on handcrafted radiomics features (HRFs) extracted from multi‐center 18F‐FDG PET/CT to predict EGFR mutation status and molecular subtypes in LUAD. Methods: Baseline 18F‐FDG PET/CT images of 383 LUAD patients from three hospitals and one public data set were collected. Further, 1808 HRFs were extracted from the primary tumor regions using Pyradiomics. Predictive models were built based on cross‐combination of seven feature selection methods and seven machine learning algorithms. Yellowbrick and explainable artificial intelligence technology were used for model visualization and interpretation. Receiver operating characteristic curve, classification report and confusion matrix were used for model performance evaluation. Clinical applicability of the optimal models was assessed by decision curve analysis. Results: STACK feature selection method combined with light gradient boosting machine (LGBM) reached optimal performance in identifying EGFR mutation status ([area under the curve] AUC = 0.81 in the internal test cohort; AUC = 0.62 in the external test cohort). Random forest feature selection method combined with LGBM reached optimal performance in predicting EGFR mutation molecular subtypes (AUC = 0.89 in the internal test cohort; AUC = 0.61 in the external test cohort). Conclusions: Explainable machine learning models combined with radiomics features extracted from multi‐center/scanner 18F‐FDG PET/CT have certain potential to identify EGFR mutation status and subtypes in LUAD, which might be helpful to the treatment of LUAD. [ABSTRACT FROM AUTHOR]

Protein kinase B (AKT) hyperactivation and de novo lipogenesis are both common in tumor progression. Sterol regulatory element‐binding protein 1 (SREBP1) is the master regulator for tumor lipid metabolism, and protein arginine methyltransferase 5 (PRMT5) is an enzyme that can catalyze symmetric dimethyl arginine (SDMA) modification of the mature form of SREBP1 (mSREBP1) to induce its hyperactivation. Here, we report that SDMA‐modified mSREBP1 (mSREBP1‐SDMA) was overexpressed and correlated with Ser473‐phosphorylated AKT (AKT‐473P) expression and poor patient outcomes in human lung adenocarcinomas. Furthermore, patients with AKT‐473P and mSREBP1‐SDMA coexpression showed the worst prognosis. Mechanistic investigation revealed that AKT activation upregulated SREBP1 at both the transcriptional and post‐translational levels, whereas PRMT5 knockdown reversed AKT signaling‐mediated mSREBP1 ubiquitin‐proteasome pathway stabilization at the post‐translational level. Meanwhile, AKT activation promoted nuclear PRMT5 to the cytoplasm without changing total PRMT5 expression, and the transported cytoplasmic PRMT5 (cPRMT5) induced by AKT activation showed a strong mSREBP1‐binding ability. Immunohistochemical assay indicated that AKT‐473P and mSREBP1‐SDMA were positively correlated with cPRMT5 in lung adenocarcinomas, and high cPRMT5 levels in tumors were associated with poor patient outcomes. Additionally, PRMT5 knockdown reversed AKT activation‐induced lipid synthesis and growth advantage of lung adenocarcinoma cells both in vitro and in vivo. Finally, we defined an AKT/PRMT5/SREBP1 axis involved in de novo lipogenesis and the growth of lung cancer. Our data also support that cPRMT5 is a potential therapeutic target for hyperactive AKT‐driven lung adenocarcinoma. [ABSTRACT FROM AUTHOR]

ABSTRACT This study investigated the fatigue fracture mechanisms and life prediction of clinched joints made from titanium alloy TA1. The fatigue tests revealed that TA1 titanium alloy clinched joints exhibited failure characterized by fracture of the lower plate at three distinct fatigue load levels. Additionally, finite element analysis indicated that cold work hardening enhanced the fatigue performance of these joints. Observations of fracture surfaces using scanning electron microscopy identified the crack source and its propagation path, which correlated with the location of maximum principal stress from the finite element simulations. Fretting wear was also observed in this critical region. Furthermore, fatigue life predictions for TA1 titanium alloy clinched joints were made using Paris' law and the local strain approach. Both methods closely matched experimental results across different fatigue life intervals. Overall, the local strain approach exhibited superior predictive capability compared to Paris' law, taking into account various influencing factors. [ABSTRACT FROM AUTHOR]