A multilayered partitioning image registration method for chest-radiograph temporal subtraction

Lung cancer has been the most common cancer in the world. Early detection is the most important for reducing the death due to lung cancer. Chest radiography has been widely and frequently used for detection and diagnosis on lung cancer. To assess pathological changes in chest radiographs, radiologists often compare the previous chest radiograph and the current one obtained from the same patient at different times. A temporal subtraction image, which is constructed subtracting the previous radiograph from the current one, is often used to support this comparison work. This paper presents a multilayered partitioning image registration method for chest-radiograph temporal subtraction. First, we used global matching based on the mutual information of ribs. Then, we divide the images after global matching into four groups of temple subareas used multilayered partitioning method. For individual local subarea in each group, we use a genetic algorithm to efficiently find its corresponding area in the previous image. By the result of genetic algorithm, we construct the new matching image according to the four groups of temple subareas, and subtract the matching image to construct the temporal subtraction image.