Rapid advances in imaging modalities have increased the importance of image segmentation techniques. Image segmentation is a process that divides an image into regions based on the image’s internal components to distinguish between the component of interest and other components. We use this process to analyze the region of the component of interest and acquire more detailed quantitative data about the component. However, almost all processes of segmentation of anatomical structures have inherent problems such as the presence of image artifacts and the need for complex parameter settings. Here, we present a framework for a semi-automatic segmentation technique that incorporates a local classifier derived from a neighboring image. By using the local classifier, we were able to consider otherwise challenging cases of segmentation merely as two-class classifications without any complicated parameters. Our method is simple to implement and easy to operate. We successfully tested the method on computed tomography images.
CITATION STYLE
Takemoto, S., Yokota, H., Mishima, T., & Himeno, R. (2009). Segmentation of anatomical structure by using a local classifier derived from neighborhood information. In Advances in Intelligent and Soft Computing (Vol. 60, pp. 171–180). Springer Verlag. https://doi.org/10.1007/978-3-642-03202-8_14
Mendeley helps you to discover research relevant for your work.