Application of belief functions to medical image segmentation: A review

The investigation of uncertainty is major importance in risk-critical applications, such as medical image segmentation. Belief function theory, a formal framework for analysis and multiple evidence fusion, has made significant contributions to segmentation, especially since the development deep learning. In this paper, we provide an introduction topic segmentation methods using belief theory. We classify according fusion step explain how information with or imprecision modeled fused addition, discuss challenges limitations present function-based propose orientations future research. Future research could investigate both theory learning achieve more promising reliable results.