Hippocampus is an important part of brain which is related with early memory storage and spatial navigation. By observing the anatomy of hippocampus, some brain diseases effecting human memory (e.g. Alzheimer, schizophrenia, etc.) can be diagnosed and predicted earlier. The diagnosis process is highly related with hippocampus segmentation. In this paper, hippocampus segmentation using Active Shape Model, which not only works based on image intensity, but also by using prior knowledge of hippocampus shape and intensity from the training images, is proposed. The results show that ASM is applicable in segmenting hippocampus from whole brain MR image. It also shows that adding more images in the training set results in better accuracy of hippocampus segmentation. Science, and Technology (2012-0002646). Also thanks to Haeundae Paik Hospital, Dong-A University Hospital, Pusan National University Hospital, and Gyeongsang National University Hospital for providing the MR images for this research.

An image segmentation result depends on pre-processing steps such as contrast enhancement, edge detection, and smooth filtering etc. Especially medical images are low contrast and contain some noises. Therefore, the contrast enhancement and noise removal techniques are required in the pre-processing. In this study, we present an extension by a novel histogram equalization in which both local and global contrast is enhanced using neighborhood metrics. When checking neighborhood information, filters can simultaneously improve image quality. Most important is that original image information can be used for both global brightness preserving and local contrast enhancement, and image quality improvement filtering. Our experiments confirmed that the proposed method is more effective than other similar techniques reported previously.

Utilization of automatic cell segmentation process is difficult to identify in a cell due to halo and shade-off distortions when observing the phase contrast microscopy images. Therefore, it is an important step to restore artifact-free images made ready for segmentation process. The main focus of this paper is to define a gradient projection algorithm to restore images based on the minimization problem of quadratic objective function with non-negative constraints. The proposed algorithm converges to a global minimum solution independent on initialization. The experimental result shows that the proposed algorithm can restore artifact-free images, which could produce high quality segmentation results using a simple thresholding method.