A Manifold Learning Method to Detect Respiratory Signal from Liver Ultrasound Images

Respiration motion is a quasi-cyclic physiologic process and may lead to motion and deformation of abdominal organs, e.g. liver [1]. This physiologic process seriously affects the efficacy and efficiency of interventional and radio-therapeutic procedures performed for diagnosing and treating these diseased organs. A variety of respiratory motion modeling methods [2] have been proposed to overcome this problem, which inevitably involves detection of the respiratory signal. Here, respiratory signal can be considered as a generalized pattern of the human respiration and feature the principal component of the 3D respiratory motion.

Source: Computerized Medical Imaging and Graphics - December 1, 2014 Category: Radiology Authors: Jiaze Wu, Apoorva Gogna, Bien Soo Tan, London Lucien Ooi, Qi Tian, Feng Liu, Jimin Liu Source Type: research