Abstract
Effective prediction of molecular features is crucial for the prognostic assessment of glioma patients. This study aims to develop a nomogram model using fractal analysis and Visually AcceSAble Rembrandt Images (VASARI) features to predict the molecular characteristics of WHO Grade 3-4 diffuse gliomas. Retrospective analysis of clinical data and VASARI features of patients with WHO grade 3-4 diffuse gliomas confirmed by pathology between January 2020 and December 2023 at our institution. Preoperative T1-weighted contrast-enhanced and T2-weighted images were used to delineate the tumor and surrounding edema regions on 3D-Slicer. Fractal dimension (FD) and lacunarity of both the tumor and surrounding edema were extracted using ImageJ software. Univariate and multivariate logistic regression analyses were performed to identify independent predictive factors for the Ki_67 proliferation index (PI), p53, and telomerase reverse transcriptase promoter (TERTp) mutations. Based on these findings, a nomogram prediction model was constructed. Model performance was comprehensively assessed using the receiver operating characteristic curve (ROC), calibration curve (CRC), and decision curve analysis (DCA). Sex, Proportion Enhancing, and Pial invasion were identified as independent predictive factors for the Ki_67 PI. FD of the tumor (FD((T))) was an independent predictor for p53 expression. FD((T)), Enhancement Quality, and Definition of the enhancing margin were independent predictors for TERTp mutations. The areas under the ROC for each nomogram model were 0.791, 0.739, and 0.601, respectively. Sensitivities were 68.75%, 78.12%, and 51.43%, and specificities were 81.03%, 64.86%, and 71.00%, respectively. CRC showed a high degree of concordance between predicted probabilities and actual observed values, while DCA demonstrated favorable net benefits for all models. VASARI features and fractal analysis effectively predict the Ki_67 PI, p53, and TERTp mutations in WHO grade 3-4 diffuse gliomas. Furthermore, combining these two approaches enhances the predictive performance for TERTp mutations.