Dual-path parallel hierarchical diagnostic model of glioma based on pathomorphological feature

Lingling Fang, Yumeng Jiang

Abstract: Glioma is one of the most common malignant tumors in clinical practice, and its grading diagnosis provides an important clinical basis for the follow-up treatment and the formulation of a surgical plan. Different grades of glioma have varying degrees of invasion. In the context of medicine and engineering cooperation, to effectively achieve the clinical automatic grading of gliomas, this paper proposes a dual-path parallel hierarchical diagnostic model based on pathomorphological features. The model can extract the pathomorphological features of gliomas, and obtain the progressive enhancement result of the image to complete the enhancement of prior features of gliomas. The dual-path structure corresponds to the multi-modal input, and then the grading is completed with the help of multi-feature fusion. The model is verified on the clinical data samples provided by Liaoning Cancer Hospital, and its accuracy can reach 0.986. Experiments show that the proposed model has high accuracy and good generalization ability, which can complete the automatic grading diagnosis of glioma.