%0 Journal Article
%T Markerless Lung Tumor Motion Tracking by Dynamic Decomposition of X-Ray Image Intensity
%A Noriyasu Homma
%A Yoshihiro Takai
%A Haruna Endo
%A Kei Ichiji
%A Yuichiro Narita
%A Xiaoyong Zhang
%A Masao Sakai
%A Makoto Osanai
%A Makoto Abe
%A Norihiro Sugita
%A Makoto Yoshizawa
%J Journal of Medical Engineering
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/340821
%X We propose a new markerless tracking technique of lung tumor motion by using an X-ray fluoroscopic image sequence for real-time image-guided radiation therapy (IGRT). A core innovation of the new technique is to extract a moving tumor intensity component from the fluoroscopic image intensity. The fluoroscopic intensity is the superimposition of intensity components of all the structures passed through by the X-ray. The tumor can then be extracted by decomposing the fluoroscopic intensity into the tumor intensity component and the others. The decomposition problem for more than two structures is ill posed, but it can be transformed into a well-posed one by temporally accumulating constraints that must be satisfied by the decomposed moving tumor component and the rest of the intensity components. The extracted tumor image can then be used to achieve accurate tumor motion tracking without implanted markers that are widely used in the current tracking techniques. The performance evaluation showed that the extraction error was sufficiently small and the extracted tumor tracking achieved a high and sufficient accuracy less than 1£¿mm for clinical datasets. These results clearly demonstrate the usefulness of the proposed method for markerless tumor motion tracking. 1. Introduction In radiation therapy, to irradiate sufficient dose to tumors and avoid unnecessary dose to the surrounding healthy tissues are crucial to achieve significant treatment effects and reduce adverse effects. Stereotactic body radiation therapy (SBRT) can satisfy such clinical demand for accurate isocenter positioning to the static center of the target tumor volume [1]. Intrafractional tumor motion can, however, badly affect the accuracy of the irradiating position and additional margins should thus be designed to account for such geometric uncertainties [2, 3]. Inevitably, the larger margins cover the wider regions of surrounding healthy tissues. In this sense, motion management is necessary for effective treatment, especially for abdominal and thoracic tumors [2¨C4]. Indeed, such tumors can move several centimeter due to mostly respiratory and cardiac motions [5, 6]. To achieve highly accurate irradiation to moving tumors, tumor tracking to measure or monitor the motion can be an ideal direction. Image-guided techniques to capture the tumor motion [7¨C11] have thus been developed for the tumor tracking. A kV X-ray fluoroscopy is widely used for such image-guided radiation therapy (IGRT) because of its capability of direct position measurement of a target tumor inside the patient's body.
%U http://www.hindawi.com/journals/jme/2013/340821/