کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
528892 869616 2013 7 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Ultrasound kidney segmentation with a global prior shape
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله
Ultrasound kidney segmentation with a global prior shape
چکیده انگلیسی


• Global prior shape for ultrasound kidney segmentation.
• Maximum likelihood of Fisher–Tippett distribution as a region term.
• Fast algorithm for segmentation with region and shape term.

In this paper, we focus on segmentation of ultrasound kidney images. Unlike previous work by using trained prior shapes, we employ a parametric super-ellipse as a global prior shape for a human kidney. The Fisher–Tippett distribution is employed to describe the grey level statistics. Combining the grey level statistics with a global character of a kidney shape, we propose a new active contour model to segment ultrasound kidney images. The proposed model involves two subproblems. One subproblem is to optimize the parameters of a super-ellipse. Another subproblem is to segment an ultrasound kidney image. An alternating minimization scheme is used to optimize the parameters of a super-ellipse and segment an image simultaneously. To segment an image fast, a convex relaxation method is introduced and the split Bregman method is incorporated to propose a fast segmentation algorithm. The efficiency of the proposed method is illustrated by numerical experiments on both simulated images and real ultrasound kidney images.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Visual Communication and Image Representation - Volume 24, Issue 7, October 2013, Pages 937–943
نویسندگان
, , , ,