Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method

Yiqiang Zhan, Dinggang Shen

Research output: Contribution to journalArticlepeer-review

177 Citations (Scopus)


This paper presents a novel deformable model for automatic segmentation of prostates from three-dimensional ultrasound images, by statistical matching of both shape and texture. A set of Gabor-support vector machines (G-SVMs) are positioned on different patches of the model surface, and trained to adaptively capture texture priors of ultrasound images for differentiation of prostate and nonprostate tissues in different zones around prostate boundary. Each G-SVM consists of a Gabor filter bank for extraction of rotation-invariant texture features and a kernel support vector machine for robust differentiation of textures. In the deformable segmentation procedure, these pretrained G-SVMs are used to tentatively label voxels around the surface of deformable model as prostate or nonprostate tissues by a statistical texture matching. Subsequently, the surface of deformable model is driven to the boundary between the tentatively labeled prostate and nonprostate tissues. Since the step of tissue labeling and the step of label-based surface deformation are dependent on each other, these two steps are repeated until they converge. Experimental results by using both synthesized and real data show the good performance of the proposed model in segmenting prostates from ultrasound images.

Original languageEnglish
Pages (from-to)256-272
Number of pages17
JournalIEEE Transactions on Medical Imaging
Issue number3
Publication statusPublished - 2006 Mar


  • Deformable segmentation
  • Gabor filter bank
  • Gabor-Support Vector Machines
  • Kernel support vector machine
  • Prostate segmentation
  • Tissue differentiation
  • Transrectal ultrasound image

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method'. Together they form a unique fingerprint.

Cite this