Discriminative anatomy detection: Classification vs regression

• We present a survey of methods for detecting one or more anatomies.
• Leveraging the anatomical context embedded in the medical image is the key.
• Discriminative learning methods are effective for appearance modeling.
• Classification-based and regression-based methods are compared.
• Different search strategies and their computational complexities are presented.

Detecting a single anatomy or a plurality of anatomical objects, such as landmarks or organs, in a medical image is important yet challenging. An anatomy detection method has to address offline model learning complexity related to modeling the appearance of a single object or a plurality of objects and online computational complexity related to search or inference strategy. In the paper, we present a survey of discriminative learning methods for appearance modeling as well as their corresponding search strategies and discuss how they leverage the anatomical context embedded in the medical image for more effective and more efficient detection.