Jae-seok Kim

Adaptable fuzzy C-Means for improved classification as a preprocessing procedure of brain parcellation

Parcellation, one of several brain analysis methods, is a procedure popular for subdividing the regions identified by segmentation into smaller topographically defined units. The fuzzy clustering algorithm is mainly used to preprocess parcellation into several segmentation methods, because it is very appropriate for the characteristics of magnetic resonance imaging (MRI), such as partial volume effect and intensity inhomogeneity. However, some gray matter, such as basal ganglia and thalamus, may be misclassified into the white matter class using the conventional fuzzy C-Means (FCM) algorithm. Parcellation has been nearly achieved through manual drawing, but it is a tedious and time-consuming process. We propose improved classification using successive fuzzy clustering and implementing the parcellation module with the modified graphic user interface (GUI) for the convenience of users.

A study for watermark methods appropriate to medical images.

The network system, including the picture archiving and communication system (PACS), is essential in hospital and medical imaging fields these days. Many medical images are accessed and processed on the web, as well as in PACS. Therefore, any possible accidents caused by the illegal modification of medical images must be prevented. Digital image water-mark techniques have been proposed as a method to protect against illegal copying or modification of copyrighted material. Invisible signatures made by a digital image watermarking technique can be a solution to these problems. However, medical images have some different characteristics from normal digital images in that one must not corrupt the information contained in the original medical images. In this study, we suggest modified watermark methods appropriate for medical image processing and communication system that prevent clinically important data contained in original images from being corrupted.