A Mutual-Information-Based 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 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 verticaliry 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.
Temporal substruction mutul information radiographs image registration
Qian Yu Tsuyosi Nakamura Lifeng He Kenji SUZUKI Yuyan Chao
Dept. of Information Science, Nagoya Institute of Technology Nagoya, Japan Graduate School of Information Science and Technology Aichi Prefectural University Nagakute-cho, Jap Department of Radiology, The University of Chicago Chicago, USA Graduate School of Environmental Management, Nagoya Sangyo University Owariasahi-city, Japan
国际会议
太原
英文
359-362
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）