SEGMENTATION OF STRUCTURES IN 2D MEDICAL IMAGES

Medical image segmentation is one of the most actively studied fields in the past few decades. As the development of modern imaging modalities such as magnetic resonance imaging (MRI) and computed tomography (CT), physicians and technicians nowadays have to process the increasing number and size of medical images. Therefore, efficient and accurate computational segmentation algorithms become necessary to extract the desired information from these large data sets. Moreover, sophisticated segmentation algorithms can help the physicians delineate better the anatomical structures presented in the input images, enhance the accuracy of medical diagnosis and facilitate the best treatment planning. However, due to the specific and complex requirements of biomedical image segmentations, general image segmentation algorithms are either not applicable or need to be revised for accomplishing this image analysis task. Combining the medical knowledge with the techniques from modern mathematics, physics and biomechanics, researchers have proposed various algorithms to handle the segmentation problem. Many of the proposed algorithms could perform well in certain medical image applications. Our work aims to present a state-of-the-art review of the algorithms to segment 2D medical images. Compared with 3D medical images, 2D images have simpler anatomical structures, easier implementation, lower computational complexity, and reduced memory requirements. In certain applications that order real-time speed, like neurosurgical planning, technicians could apply 2D methods sequentially to the slices of 3D images.