RESUMEN
Contrast-MRI scans carry risks associated with the chemical contrast agents. Accurate prediction of enhancement pattern of gliomas has potential in avoiding contrast agent administration to patients. This study aimed to develop a machine learning radiomics model that can accurately predict enhancement pattern of gliomas based on T2 fluid attenuated inversion recovery images. A total of 385 cases of pathologically-proven glioma were retrospectively collected with preoperative magnetic resonance T2 fluid attenuated inversion recovery images, which were divided into enhancing and non-enhancing groups. Predictive radiomics models based on machine learning with 6 different classifiers were established in the training cohort (nâ =â 201), and tested both in the internal validation cohort (nâ =â 85) and the external validation cohort (nâ =â 99). Receiver-operator characteristic curve was used to assess the predictive performance of these radiomics models. This study demonstrated that the radiomics model comprising of 15 features using the Gaussian process as a classifier had the highest predictive performance in both the training cohort and the internal validation cohort, with the area under the curve being 0.88 and 0.80, respectively. This model showed an area under the curve, sensitivity, specificity, positive predictive value and negative predictive value of 0.81, 0.98, 0.61, 0.82, 0.76 and 0.96, respectively, in the external validation cohort. This study suggests that the T2-FLAIR-based machine learning radiomics model can accurately predict enhancement pattern of glioma.
Asunto(s)
Neoplasias Encefálicas , Glioma , Aprendizaje Automático , Imagen por Resonancia Magnética , Humanos , Glioma/diagnóstico por imagen , Glioma/patología , Imagen por Resonancia Magnética/métodos , Femenino , Persona de Mediana Edad , Masculino , Estudios Retrospectivos , Neoplasias Encefálicas/diagnóstico por imagen , Adulto , Curva ROC , Valor Predictivo de las Pruebas , Anciano , Medios de Contraste , RadiómicaRESUMEN
BACKGROUND: Myocardial ischemia/reperfusion injury (MIRI) usually induces serious health problems. OBJECTIVES: This study attempted to explore protective effects of (-)-epigallocatechin-3-gallate (EGCG) on MIRI and the associated mechanism. MATERIAL AND METHODS: Ischemia/reperfusion of an isolated rat heart (I/R model) and the MIRI model were used in this study. Myocardial infarction was measured with staining with 2,3,5-triphenyltetrazolium chloride (TTC). Ca2+ and troponin T (TnT) concentrations in coronary perfusion fluid were evaluated using the chromatometry method. Ca2+ concentration in cardiomyocytes was determined with detecting Ca2+ fluorescence intensity. The ultrastructure of cardiomyocytes was observed using transmission electron microscopy (TEM). ß-nicotinamide adenine dinucleotide (NAD+) of cardiomyocytes was also determined. RESULTS: The EGCG (I/R+EGCG) significantly reduced myocardial infarction size of isolated rat heart compared to I/R rats (p < 0.05), remarkably increased Ca2+ and decreased TnT concentrations in coronary perfusion fluid of I/R rats compared to the I/R model (p < 0.05), as well as markedly decreased intracellular Ca2+ concentration and promoted NAD+ concentration in cardiomyocytes compared to I/R rats (p < 0.05). It also obviously maintained the mitochondrial structure in cardiomyocytes of I/R rats and improved the ultrastructure of cardiomyocytes of MIRI rats. Lonidamine (LND) treatment (I/R+EGCG+LND group) significantly blocked the effects of EGCG on I/R injury compared to the I/R+EGCG group (p < 0.05). The EGCG (MIRI+EGCG) significantly decreased myocardial infarction size compared to MIRI rats (p < 0.05) and remarkably enhanced Ca2+ and reduced TnT concentrations in the pulmonary artery compared to that of MIRI rats (p < 0.05). CONCLUSIONS: The EGCG decreased myocardial infarction size in both I/R models and MIRI models by reducing intracellular Ca2+ concentration, increasing TnT concentration, promoting NAD+ concentration, and improving the ultrastructure of cardiomyocytes.