Graph-based medical image clustering

With the development of medical imaging technology, more and more medical images affect the diagnosis. In order to effectively manage and utilize these medical images, researchers pay more attention on data clustering in medical images. Medical images are very complicated in structure and there are numerous characteristic. Most medical images are multidimensional data. So we convert images into a complete graph as an established form, then accomplish image´ clustering by graph clustering. This method combined with medical knowledge can obtain a good image clustering results that meet the requirements of the medical staff. The experimental results prove that this method has better accuracy.