Parallel Watershed method for Medical modality Image segmentation

Medical image processing on the GPU has become quite popular recently, since this technology makes it possible to apply more advanced algorithms and to perform computationally demanding tasks quickly in clinical context. Image segmentation in medical imaging is often used to segment brain structures, organs, blood vessels and bones. Combined interactive segmentation and visualization are impeccably suited to the GPU. The data already in GPU memory can be extracted very efficiently. As a consequence, the segmentation process often becomes more complex and time-consuming. This paper proposes the ways to improve the computational speed of watershed segmentation algorithm using GPU Computing. GPUs are used to solve a wide variety modality of problems in the field of medical imaging.