Background: Current histopathology- and molecular-based gold standards for diagnosing adult diffuse gliomas (ADGs) have inherent limitations in reproducibility and interobserver concordance, while being time-intensive and resource-demanding. Although hyperspectral imaging (HSI)-based computer-aided pathology shows potential for automated diagnosis, it often yields suboptimal accuracy due to the lack of complementary spatial and structural tumor information. This study introduces a multimodal fusion framework integrating HSI with routinely acquired preoperative magnetic resonance imaging (MRI) to enable automated, high-precision ADG diagnosis. Methods: We developed the Hyperspectral Attention Fusion Network (HAFNet), incorporating residual learning and channel attention to jointly capture HSI patterns and MRI-derived radiomic features. The dataset comprised 1931 HSI cubes (400–1000 nm, 300 spectral bands) from histopathological patches of six major World Health Organization (WHO)-defined glioma subtypes in 30 patients, together with their routinely acquired preoperative MRI sequences. Informative wavelengths were selected using mutual information. Radiomic features were extracted with the PyRadiomics package. Model performance was assessed via stratified 5-fold cross-validation, with accuracy and area under the curve (AUC) as primary endpoints. Results: The multimodal HAFNet achieved a macro-averaged AUC of 0.9886 and a classification accuracy of 98.66%, markedly outperforming the HSI-only baseline (AUC 0.9267, accuracy 87.25%; p < 0.001), highlighting the complementary value of MRI-derived radiomic features in enhancing discrimination beyond spectral information. Conclusions: Integrating HSI biochemical and microstructural insights with MRI radiomics of morphology and context, HAFNet provides a robust, reproducible, and efficient framework for accurately predicting 2021 WHO types and grades of ADGs, demonstrating the significant added value of multimodal integration for precise glioma diagnosis.

Objectives: The objective of this study is to explore the potential variations in metabolic activity across gliomas originating from distinct cortical regions, as assessed by O-(2-¹⁸F-fluoroethyl)-L-tyrosine positron emission tomography (¹⁸F-FET PET). Also, this study seeks to elucidate whether these metabolic disparities correlate with the molecular characteristics and clinical prognoses of the tumors. Specifically, this research aims to determine whether variations in ¹⁸F-FET PET uptake are indicative of underlying genetic or biochemical differences that could influence patients’ outcomes. Methods: The researchers retrospectively included 107 patients diagnosed with gliomas from neocortex and mesocortex, all of whom underwent hybrid PET/MR examinations, including ¹⁸F-FET PET and diffusion weighted imaging (DWI), prior to surgery. The mean and maximum tumor-to-background ratio (TBR) and apparent diffusion coefficient (ADC) values were calculated based on whole tumor volume segmentations. Comparisons of TBR, ADC values, and survival outcomes were performed to determine statistical differences between groups. Results: Among glioblastomas (GBMs, WHO grade 4) originating from the two cortical regions, there was a significant difference in the human Telomerase Reverse Transcriptase (TERT) promoter mutation rate, while no difference was observed in O⁶-Methylguanine-DNA Methyltransferase (MGMT) promoter methylation status. For WHO grade 3 gliomas, significant differences were found in the TERT promoter mutation rate and the proportion of 1p/19q co-deletion between the two cortical regions, whereas no difference was noted in MGMT methylation status. For WHO grade 2 gliomas, no molecular phenotypic differences were observed between the two cortical regions. In terms of survival, only GBMs originating from the mesocortex demonstrated significantly longer survival compared to those from the neocortex, while no statistically significant differences were found in survival for the other two groups. Conclusions: Gliomas originating from different cortical regions exhibit variations in metabolic activity, molecular phenotypes, and clinical outcomes.