Search

Purpose: Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20–30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Methods: We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure. Results: Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. Conclusions: Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features. [ABSTRACT FROM AUTHOR]

Objective: The objective of this study was to assess the relationship between spermine synthase (SMS) expression, tumor occurrence, and prognosis in lower-grade gliomas (LGGs). Methods: A total of 523 LGG patients and 1152 normal brain tissues were included as controls. Mann-Whitney U test was performed to evaluate SMS expression in the LGG group. Functional annotation analysis was conducted to explore the biological processes associated with high SMS expression. Immune cell infiltration analysis was performed to examine the correlation between SMS expression and immune cell types. The association between SMS expression and clinical and pathological features was assessed using Spearman correlation analysis. In vitro experiments were conducted to investigate the effects of overexpressing or downregulating SMS on cell proliferation, apoptosis, migration, invasion, and key proteins in the protein kinase B (AKT)/epithelialmesenchymal transition signaling pathway. Results: The study revealed a significant upregulation of SMS expression in LGGs compared to normal brain tissues. High SMS expression was associated with certain clinical and pathological features, including older age, astrocytoma, higher World Health Organization grade, poor disease-specific survival, disease progression, non-1p/19q codeletion, and wild-type isocitrate dehydrogenase. Cox regression analysis identified SMS as a risk factor for overall survival. Bioinformatics analysis showed enrichment of eosinophils, T cells, and macrophages in LGG samples, while proportions of dendritic (DC) cells, plasmacytoid DC (pDC) cells, and CD8+ T cells were decreased. Conclusion: High SMS expression in LGGs may promote tumor occurrence through cellular proliferation and modulation of immune cell infiltration. These findings suggest the prognostic value of SMS in predicting clinical outcomes for LGG patients. [ABSTRACT FROM AUTHOR]