Prediction of genetic status and grading in glioma based on fusion of macro⁃ and micro⁃imaging features

Objective To develop a dual⁃layer feature distillation multiple instance learning (DLFD⁃ MIL) model integrating MRI and whole slide image (WSI) features for precise prediction of IDH1 mutation, 1p/19q codeletion, and World Health Organization (WHO) grading in adult⁃type diffuse gliomas. Methods A retrospective cohort of 212 adult⁃type diffuse gliomas patients from Huashan Hospital, Fudan University (January 2021 to June 2024) and 42 cases from The Cancer Genome Atlas (TCGA) were included. Preoperative T2⁃FLAIR and postoperative WSI data were jointly analyzed. The DLFD⁃MIL model addressed the lack of instance⁃level labels in weakly supervised WSI learning via a pseudo⁃bag generation strategy. Multimodal feature fusion was achieved through Concat. Diagnostic performance for molecular subtyping and WHO grading was evaluated by comparing area under the curve (AUC) of receiver operating characteristic (ROC) curve between single⁃mode (WSI or MRI) and multi⁃mode. Results In the IDH1 mutation prediction task, AUC of the multi⁃mode feature fusion model surpassed single ⁃mode WSI model (Z = 2.752, P = 0.006) and single⁃mode T2⁃FLAIR model (Z = 5.662, P = 0.000). In the 1p/19q codeletion prediction task, no statistically significant differences in AUC were observed between the multi⁃mode feature fusion model and either single⁃mode WSI model (Z = ⁃ 0.245, P = 0.806) or T2⁃FLAIR model (Z = 0.781, P = 0.435). In the WHO grading prediction task, the multi⁃mode feature fusion model showed no significant differences in AUC compared to single⁃mode WSI model (Z = 1.739, P = 0.082), however its AUC was significantly higher than single⁃mode T2⁃FLAIR model (Z = 4.830, P = 0.000). Conclusions Multi⁃mode fusion of macro⁃ and micro⁃imaging features improves prediction accuracy for IDH1 genotyping and WHO grading in gliomas, providing a reliable artificial intelligence (AI) decision⁃support tool for personalized clinical management.