This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Shao, F. Articles by Wu, R. Y. Search for Related Content PubMed PubMed Citation Articles by Shao, F. Articles by Wu, R. Y.

Prostate Boundary Detection From Ultrasonographic Images

School of Electrical and Electronic Engineering (F.S., K.V.L.) and School of Mechanical and Production Engineering (W.S.N., R.Y.W.), Nanyang Technological University, Singapore.

Address correspondence and reprint requests to Wan Sing Ng, School of Mechanical and Production Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798; e-mail: MWSNG{at}ntu.edu.sg.

Objective. Prostate diseases are very common in adult and elderly men, and prostate boundary detection from ultrasonographic images plays a key role in prostate disease diagnosis and treatment. However, because of the poor quality of ultrasonographic images, prostate boundary detection still remains a challenging task. Currently, this task is performed manually, which is arduous and heavily user dependent. To improve the efficiency by automating the boundary detection process, numerous methods have been proposed. We present a review of these methods, aiming to find a good solution that could efficiently detect the prostate boundary on ultrasonographic images. Methods. A full description of various methods is beyond the scope of this article; instead, we focus on providing an introduction to the different methods with a discussion of their advantages and disadvantages. Moreover, verification methods for estimating the accuracies of the algorithms reported in the literature are discussed as well. Results. From the investigation, we summarize several key issues that might be confronted and project possible future research. Conclusions. Those model-based methods that minimize user involvement but allow for interactive guidance of experts will likely be most immediately successful.

Key Words: algorithm verification • boundary detection • prostate • ultrasonographic image

Abbreviations: DDC, discrete dynamic contour • MRF, Markov random field • RBR, radial bas-relief • 3D, three-dimensional • TRUS, transrectal ultrasonography • 2D, two-dimensional