Fuzzy Bayesian Network-Based Inference in Predicting Astrocytoma Malignant Degree

摘要: This study proposes an improved fuzzy Bayesian network (FBN), which integrates theory into networks (BN) by introducing conditional Gaussian models to make a procedure. particular procedure will transform continuous variables discrete ones when dealing with inputs probabilistic and uncertain nature. Moreover, it describes features better than other methods. To validate our method, this paper applied the classification of astrocytoma malignant degree. We present model that employs FBN in fusing both low-level high-level semantics from MRI (magnetic resonance imaging). It realizes quantificational analysis predicting level provides novel assistant way for young doctors. An accuracy 81.67% was achieved out 60 test samples, satisfies basic requirement neuroradiologists.