Output details
11 - Computer Science and Informatics
University of Manchester
Automatic inference and measurement of 3D carpal bone kinematics from single view fluoroscopic sequences
<23>Inferring 3D structure from 2D projection images is important in several areas of medical imaging where successive investigations are required. This paper is significant because it demonstrates that, using a combined statistical pose and shape model, the 3D kinematics of the wrist – the most complex joint in the body – can be inferred from noisy 2D cinefluoroscopy sequences. Careful evaluation on simulated and real image sequences demonstrates that clinically useful, quantitative, information about abnormal joint kinematics can be inferred. The method has applications in imaging of other joints and more generally in video sequences of articulated objects.