Abstract—Image understanding needs to image analysis accurately in medical image engineering. Since segmentation is an effective and fundamental step in the medical image analysis (MIA), many efforts have being done to increase accuracy. One of the promising and fruitful efforts is using the artificial intelligence (AI) methods. This paper proposes a new notation for medical image segmentation (MIS) namely the status quo of AI techniques used to automate MIS. It considers four categories for segmentation methods based on applied AI techniques. These methods can decrease the human intervention gradually as well as showing this development; it tries to full automated segmentation. Each category facilitates the higher level of AI techniques than the previous one does. They are respectively based on Image Processing techniques, Hybrid AI methods, Expert systems development and ultimately registration-based in the multispectral and multi modal imaging.
Index Terms—Artificial intelligence methods, medical imaging, image segmentation, medical image analysis.
Maryam Rastgarpour is with the Computer Department, Faculty of Engineering, Science and Research branch, Islamic Azad University,Tehran, Iran. (e-mail: firstname.lastname@example.org, email@example.com)
Dr. Jamshid Shanbehzadeh is with the Department of Computer Engineering at Kharazmi University (Tarbiat Moallem University of Teheran), Tehran, I. R. Iran. (e-mail: firstname.lastname@example.org, email@example.com)
Cite: Maryam Rastgarpour and Jamshid Shanbehzadeh, "The Status Quo of Artificial Intelligence Methods in Automatic Medical Image Segmentation," International Journal of Computer Theory and Engineering vol. 5, no. 1, pp. 5-8, 2013.