Proposed Method for Automatic Segmentation of Medical Images

Abstract

Automatic segmentation of medical images is a key step in contouring during radiotherapy planning. Computed topography (CT) and Magnetic resonance (MR) imaging are the most widely used radiographic techniques in diagnosis, clinical studies and treatment planning. This paper proposed an unsupervised and automatic estimation of the required parameters for identifying the region of interest. The proposed methodology consists of four steps executed sequentially: First, a body region of interest is masked by a method based on Otsu thresholding and basic morphological operations. Second, a distance transformation is performed then results of distance transform function are normalized. Next, watershed marker-controlled identifications are performed by extract internal and external marker. Finally, the region of interest is identified and segmented according the resulted boundaries. According to the visual evaluation results, segmentation of the human body, from the Computed Tomography images, was seen to be precise and accurate (as confirmed by a specialist). The analysis provided evidence that the human body segmentation method could be applied to segmenting other organs, registering different image modalities or speeding-up the generation of digitally reconstructed radiographs.