Probabilistic Branching Node Detection Using Hybrid Local Features

Probabilistic branching node inference is an important step for analyzing branching patterns involved in many anatomic structures. We propose combining machine learning techniques and hybrid image statistics to perform branching node inference, using a support vector machine as a probabilistic inference framework. Then, we use local image statistics at different image scales for feature representation, including the Harris cornerness, the Laplacian, and the eigenvalues of the Hessian. The proposed approach is applied to a breast imaging dataset. Despite the challenge of the task, our approach achieves very encouraging results, which are helpful for further analysis of the breast ducts and other branching structures.

• Type: Conference
• Year: 2009
• Where: ISBI
• Authors: Haibin Ling, Michael Barnathan, Vasileios Megalooikonomou, Predrag R. Bakic, Andrew D. A. Maidment
• Keywords: Branching Node Inference, ISBI 2009, Medical Imaging, Probabilistic Branching Node, Probabilistic Inference Framework