Image Registration Method for Chest MDCT Images Based on 2-D Finite Element Method

Multi detector-row computed tomography (MDCT) device has been used for early detection of lung cancer. However, there is concern that an increase in the burden on doctors will be caused by improvements in CT performance. Therefore, developing a computer aided diagnosis (CAD) reduces the burden on doctors. A temporal subtraction (TS) technique is one of the CAD systems and it is the subtraction operation of the current image and the previous one of the same patients that emphasizes temporal changes. In the TS image, when the position of the current image and the previous image are misaligned, subtraction artifacts are remained. In this paper, we propose a registration method based on the 2-D finite element method (FEM). In our proposed method, to improve the high computed cost that is the biggest problem of the FEM, we introduce the 2D FEM registration. We applied this method to 31 series MDCT image sets which was obtained previous and current from the same subjects and evaluated. As a result, full width at half maximum (FWHM) of 28.0, artifact to lung volume ratio of 5.77% and computational time of 140 sec were obtained.