To search, Click below search items.


All Published Papers Search Service


A Useful Implementation of Medical Image Registration for Brain Tumor Growth Investigation in a Three Dimensional Manner


Emrah Irmak¹, Mustafa Burak T?RK?Z²


Vol. 17  No. 6  pp. 155-161


Image registration or as sometimes called image matching is the operation of geometrically taking two or more than two images to the same coordinate system. Image registration is a fundamental job used to match two or more than two images acquired, for example, at different times, from different machines or sensors, or from different viewpoints. Aligning medical images for neurologic research, diagnosis and treatment can be considered as a specific example of image registration. Magnetic Resonance (MR) images of the brain contain anatomic sense for neurologic research, diagnosis and treatment. Therefore to evaluate changes in serial scans of MR images becomes an important issue in medical image registration field. In this paper an objective application of registration of multiple brain imaging scans is used to investigate brain tumor growth in a 3 dimensional (3D) manner. Using 3D medical image registration algorithm, multiple scans of MR images of a patient who has brain tumor are registered with different MR images of the same patient acquired at a different time so that growth of the tumor inside the patient's brain can be investigated. MR images are registered with 3D accuracy on the order of two corresponding images. Technique is implemented to 19 patients and satisfactory results are obtained. This study is a critical application for correlation of anatomic information obtained by MR for clinical and research purposes. This paper is intended to provide a comprehensive reference source for researchers involved in medical image registration and tumor growth investigation.


Geometrical Transformation, 3D Medical Image Registration, Optimization, Tumor Growth