Semi-Automatic Seeded Region Growing for Object Extracted in MRI [ READ ]
Ziad M. Abood, Iman Hussein AL-Qinani, Kawther Thabt Saleh, Mushtaq Talib Ajjah
This paper describes a semi-automatic method for object segmentation in medical images by using seeded region growing method, which increasingly became a popular method because of its ability to involve high-level knowledge of anatomical structures in seed selection process. Region based segmentation of the medical images is widely used in various clinical applications such as bone and tumor detection, visualization, and unsupervised image retrieval in clinical databases. Because of fuzziness of medical images in nature; segmenting regions depending on intensity is a very challenging task. In this paper, the popular seeded region grow methodology, which is used to segment anatomical structures in computed topography angiography images, is discussed. Homogeneity criteria used to control the region grow process during segmenting images is proposed.
Ziad M. Abood, Iman Hussein AL-Qinani, Kawther Thabt Saleh, Mushtaq Talib Ajjah
This paper describes a semi-automatic method for object segmentation in medical images by using seeded region growing method, which increasingly became a popular method because of its ability to involve high-level knowledge of anatomical structures in seed selection process. Region based segmentation of the medical images is widely used in various clinical applications such as bone and tumor detection, visualization, and unsupervised image retrieval in clinical databases. Because of fuzziness of medical images in nature; segmenting regions depending on intensity is a very challenging task. In this paper, the popular seeded region grow methodology, which is used to segment anatomical structures in computed topography angiography images, is discussed. Homogeneity criteria used to control the region grow process during segmenting images is proposed.
