RESUMEN
Purpose: This study was designed to determine the diagnostic performance of fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics-based machine learning (ML) in the classification of cervical adenocarcinoma (AC) and squamous cell carcinoma (SCC). Methods: Pretreatment 18F-FDG PET/CT data were retrospectively collected from patients who were diagnosed with locally advanced cervical cancer at two centers. Radiomics features were extracted and selected by the Pearson correlation coefficient and least absolute shrinkage and selection operator regression analysis. Six ML algorithms were then applied to establish models, and the best-performing classifier was selected based on accuracy, sensitivity, specificity, and area under the curve (AUC). The performance of different model was assessed and compared using the DeLong test. Results: A total of 227 patients with locally advanced cervical cancer were enrolled in this study (N=136 for the training cohort, N=59 for the internal validation cohort, and N=32 for the external validation cohort). The PET radiomics model constructed based on the lightGBM algorithm had an accuracy of 0.915 and an AUC of 0.851 (95% confidence interval [CI], 0.715-0.986) in the internal validation cohort, which were higher than those of the CT radiomics model (accuracy: 0.661; AUC: 0.513 [95% CI, 0.339-0.688]). The DeLong test revealed no significant difference in AUC between the combined radiomics model and the PET radiomics model in either the training cohort (z=0.940, P=0.347) or the internal validation cohort (z=0.285, P=0.776). In the external validation cohort, the lightGBM-based PET radiomics model achieved good discrimination between SCC and AC (AUC = 0.730). Conclusions: The lightGBM-based PET radiomics model had great potential to predict the fine histological subtypes of locally advanced cervical cancer and might serve as a promising noninvasive approach for the diagnosis and management of locally advanced cervical cancer.
RESUMEN
BACKGROUND: The expression of TES, a novel tumor suppressor gene, is found to be down-regulated in the left anterior descending aorta of patients with coronary artery disease (CAD) compared with non-CAD subjects. This study aimed to investigate the expression of TES during the development of atherosclerosis in rabbits. METHODS: Thirty-two New Zealand rabbits were randomly divided into a normal diet (ND) and high-fat diet (HFD) groups. Body weight and serum lipid levels were measured at 0, 4, and 12 weeks after diet treatment. The degree of atherosclerosis in thoracic aortas was analyzed by histological examinations. The expression of Testin in the tissue samples was inspected via immunohistochemical and immunofluorescence confocal microscopy. Real time-polymerase chain reaction and Western blot analysis were performed to evaluate the expression of TES/Testin at mRNA and protein levels in the aortic tissues. RESULTS: After 12 weeks postenrollment, rabbits in HFD group had a higher level of serum lipids and atherosclerotic plaque compared to ND group (P < 0.05). Testin expression was detected at high levels in the endothelium and a weak expression on the subendothelium area. The expression of TES mRNA was markedly reduced by 10-fold in the aortic tissues in the HFD group compared with the ND group (P = 0.015), and the protein level was also significantly decreased in the HFD group (P < 0.05). CONCLUSIONS: Reduced TES/Testin expression is associated with the development of atherosclerosis, implicating a potentially important role in the pathogenesis of atherosclerosis.