Prostate and Bladder Segmentation Using a Statistically Trainable Model

Levy, Joshua H.; Broadhurst, Robert E.; Jeong, Jae Yeong; Liu, X.; Stough, Joshua V.; Tracton, Gregg; Pizer, Stephen M.; Chaney, Ed

doi:10.1016/j.ijrobp.2007.07.1442

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When Bayes theorem is applied, it follows that the z resulting from this segmentation approach is arg max z [-log p(z) + (-log p(I | z))]. This approach was most heavily developed in the segmentation of organs in the male pelvis from CT for planning of radiation therapy of prostate cancer (Levy et al, 2007), and the methods were the basis of segmentation by a spinoff corporation, Morphormics (Holloway et al, 2008), which was later bought by Accuray. Vicory (2016) applied this notion to the segmentation of the prostate from 3D ultrasound, given its shape in MRI.…”

Section: Single Object Applicationsmentioning

confidence: 99%

Skeletons, Object Shape, Statistics

Pizer

Marron

Damon

et al. 2022

Front. Comput. Sci.

View full text Add to dashboard Cite

Objects and object complexes in 3D, as well as those in 2D, have many possible representations. Among them skeletal representations have special advantages and some limitations. For the special form of skeletal representation called “s-reps,” these advantages include strong suitability for representing slabular object populations and statistical applications on these populations. Accomplishing these statistical applications is best if one recognizes that s-reps live on a curved shape space. Here we will lay out the definition of s-reps, their advantages and limitations, their mathematical properties, methods for fitting s-reps to single- and multi-object boundaries, methods for measuring the statistics of these object and multi-object representations, and examples of such applications involving statistics. While the basic theory, ideas, and programs for the methods are described in this paper and while many applications with evaluations have been produced, there remain many interesting open opportunities for research on comparisons to other shape representations, new areas of application and further methodological developments, many of which are explicitly discussed here.

show abstract

Section: Single Object Applicationsmentioning

confidence: 99%

Skeletons, Object Shape, Statistics

Pizer

Marron

Damon

et al. 2022

Front. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…To reduce the number of parameters to be determined in the segmentation procedure, parametric representations have been proposed for shape annotation. The parametric description used for the prostate shape include the Fourier descriptor [35], the hyperquadrics [133], the superquadrics [134,135,136,36], the medial model (m-rep) [137,138,139], the superellipses [37,140] and the spherical harmonics [141,38] [38]. However, the search for the model parameters was determined by minimizing distances between the fitted surface and a point cloud in edge map [26,37], in which extra attention had to be paid to elimiminating false-positive edge points.…”

Section: Shape-based Statistical Modelmentioning

confidence: 99%

Prostate segmentation and multimodal registration in 3D ultrasound images

Shao¹

View full text Add to dashboard Cite

Voon, for his persistent encouragement and guidance during the entire course of my PhD study. Without his support, the successful completion of my thesis is a mission impossible. I also want to express my deepest thankfulness and condolence to Associate Professor Ng Wan Sing, who just left us recently. As the founder and head of the Computer Integrated Medical Intervention Laboratory (CIMIL), he had influenced and supported me extensively in my research, career and life. His knowledgeable comments and suggestions in past days helped me a lot. His persistence and optimism shown in his fight against cancer has inspired me during my own hard days and this inspiration will last for my life. I would like to acknowledge Nanyang Technological University for providing the financial support and the research facilities. Thanks to Dr. Thng Choon Hua from National Cancer Centre of Singapore who has generously helped in my research work. Same gratitude to Dr. Henry Ho and Dr. Christopher Cheng from Singapore General Hospital who cooperated with us on this project and provided the medical support for my work.

show abstract

Prostate and Bladder Segmentation Using a Statistically Trainable Model

Cited by 2 publications

References 0 publications

Skeletons, Object Shape, Statistics

Skeletons, Object Shape, Statistics

Prostate segmentation and multimodal registration in 3D ultrasound images

Contact Info

Product

Resources

About