Boundary delineation of breast lesions in series of 2D sonography by modeling the spatial-temporal prior and cell-based map approach

Jie Zhi Cheng, Chung Ming Chen, Yi Hong Chou, Wen-Huang Cheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a general boundary delineation method for 2D serial US images by modeling the spatial-temporal dynamics and generating the object boundary in each slice under the cell-based MAP scheme. The modeling of the spatial-temporal dynamics can serve as a prior to guide the cell-based MAP process and potentially maintain the contextual coherence. Experiments have been conducted on 8 sets of compression breast series and 5 sets of freehand breast acquisitions. The computer-generated results by our algorithm are compared to manual delineations prepared by experts. The experimental results suggest that the boundaries of the proposed method are not significantly different to manual outlines and are quite stable in terms of reproducibility.

Original languageEnglish
Title of host publicationProceedings - 2013 7th International Conference on Image and Graphics, ICIG 2013
Pages905-908
Number of pages4
DOIs
StatePublished - 1 Dec 2013
Event2013 7th International Conference on Image and Graphics, ICIG 2013 - Qingdao, Shandong, China
Duration: 26 Jul 201328 Jul 2013

Publication series

NameProceedings - 2013 7th International Conference on Image and Graphics, ICIG 2013

Conference

Conference2013 7th International Conference on Image and Graphics, ICIG 2013
CountryChina
CityQingdao, Shandong
Period26/07/1328/07/13

Keywords

  • Breast cancer
  • Kalman filter
  • MAP
  • Ultrasound

Fingerprint Dive into the research topics of 'Boundary delineation of breast lesions in series of 2D sonography by modeling the spatial-temporal prior and cell-based map approach'. Together they form a unique fingerprint.

Cite this