Abstract
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 mutual-information-based image registration method for chest-radiograph temporal subtraction. First, we extract the lung regions of original radiographs. Then we get the center lines of lungs by the outer contours of lungs. We set the centre lines of lungs verticality and coincident in horizontal. We extract rib cages from the images of lung regions after centre line aligning. Then we constantly transform the rib cage image of the previous radiograph. As transforming, we calculate the mutual information between two rib cages images. We improve the transform parameters based on the mutual information, and subtract the radiographs translated by using the best parameters to construct the temporal subtraction image.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have