Automatic Identification of Corresponding CT Images Having the Same Lymph Node in Longitudinal Studies

The study of lymph node features over time is of great clinical significance. Identification of the corresponding CT image with the same lymph node is done manually in the current clinical practice. In this paper, we propose a search scheme to automate the process. Region of interest (ROIs) are located by mapping the center point of lymph node based on the transformation found in the rigid registration. Similarity values between ROI of the template image and ROIs of repository images are compared, the highest of which decides the best match. Our method generated a success rate of 77.78% in determining the correct match. We also investigated the efficiency of using different similarity measures, mutual information and cross correlation, in the scheme. The effect of varying sizes of ROIs on the identification results was examined as well.