Biomedical Engineering Reference
In-Depth Information
10
DEFORMABLE MODEL-BASED SEGMENTATION
OF THE PROSTATE FROM ULTRASOUND
IMAGES
Aaron Fenster
Robarts Research Institute, London, Ontario, Canada
Hanif Ladak
Department of Medical Biophysics
The University of Western Ontario, London, Ontario, Canada
Mingyue Ding
Institute for Pattern Recognition and Artificial Intelligence
Huazhong University of Science and Technology, Wuhan, China
1.
INTRODUCTION
Prostate cancer is the most commonly diagnosed malignancy in men, and is
the second leading cause of death due to cancer in men [1, 2]. It has been found
at autopsy that 30% of men at age 50, 40% at age 60, and almost 90% at age
90 have prostate cancer [3, 4]. Over the past decade, the prostate-specific antigen
(PSA) blood test has become well established for early detection of prostate cancer,
particularly for monitoring of prostate cancer after treatment [5-10]. The wide
availability of the PSA test [7,10], the public's increased awareness about prostate
cancer, and the growing number of men over 50 have all combined to increase
the proportion of prostate cancer diagnosed at an early stage [11]. Currently, 77%
