A Hybrid-Based Computer Diagnosis System For Virtual Cystoscopy

Bladder cancer is the one of the leading causes of cancer deaths in the United States. By utilizing magnetic resonance imaging (MRI), virtual cystoscopy (VC) has shown its potential in early examinations of bladder lesions. In this paper, we present a hybrid-based computer diagnosis system for VC. The research objective of this paper are: (1) to incorporate a statistical maximum a posterior (MAP) framework, for tissue segmentation (local computation); (2) to determine a set of intrinsic parameters for modeling bladders (global computation); (3) to develop a hybrid-based diagnosis system based on both the local feature computations and the global parameters obtained.