Semi-automatic segmentation for prostate interventions

被引:57
|
作者
Mandavi, S. Sara [1 ]
Chng, Nick [1 ,2 ]
Spadinger, Ingrid [2 ]
Morris, William J. [3 ]
Salcudean, Septimiu E. [1 ]
机构
[1] Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC V6T 1Z4, Canada
[2] British Columbia Canc Agcy, Dept Med Phys, Vancouver, BC V5Z 4E6, Canada
[3] British Columbia Canc Agcy, Dept Radiat Oncol, Vancouver, BC V5Z 4E6, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Prostate interventions; Segmentation; Trans-rectal ultrasound imaging; Prostate brachytherapy; ACTIVE SHAPE MODELS; ULTRASOUND IMAGES; BOUNDARY SEGMENTATION; TRUS IMAGES; 2D; BRACHYTHERAPY;
D O I
10.1016/j.media.2010.10.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we report and characterize a semi-automatic prostate segmentation method for prostate brachytherapy. Based on anatomical evidence and requirements of the treatment procedure, a warped and tapered ellipsoid was found suitable as the a-priori 3D shape of the prostate. By transforming the acquired endorectal transverse images of the prostate into ellipses, the shape fitting problem was cast into a convex problem which can be solved efficiently. The average whole gland error between non-overlapping volumes created from manual and semi-automatic contours from 21 patients was 6.63 +/- 0.9%. For use in brachytherapy treatment planning, the resulting contours were modified, if deemed necessary, by radiation oncologists prior to treatment. The average whole gland volume error between the volumes computed from semi-automatic contours and those computed from modified contours, from 40 patients, was 5.82 +/- 4.15%. The amount of bias in the physicians' delineations when given an initial semi-automatic contour was measured by comparing the volume error between 10 prostate volumes computed from manual contours with those of modified contours. This error was found to be 7.25 +/- 0.39% for the whole gland. Automatic contouring reduced subjectivity, as evidenced by a decrease in segmentation inter- and intra-observer variability from 4.65% and 5.95% for manual segmentation to 3.04% and 3.48% for semi-automatic segmentation, respectively. We characterized the performance of the method relative to the reference obtained from manual segmentation by using a novel approach that divides the prostate region into nine sectors. We analyzed each sector independently as the requirements for segmentation accuracy depend on which region of the prostate is considered. The measured segmentation time is 14 +/- 1 s with an additional 32 +/- 14s for initialization. By assuming 1-3 min for modification of the contours, if necessary, a total segmentation time of less than 4 min is required, with no additional time required prior to treatment planning. This compares favorably to the 5-15 min manual segmentation time required for experienced individuals. The method is currently used at the British Columbia Cancer Agency (BCCA) Vancouver Cancer Centre as part of the standard treatment routine in low dose rate prostate brachytherapy and is found to be a fast, consistent and accurate tool for the delineation of the prostate gland in ultrasound images. (C) 2010 Elsevier B.V. All rights reserved.
引用
收藏
页码:226 / 237
页数:12
相关论文
共 50 条
  • [1] Semi-automatic segmentation of the prostate
    Zwiggelaar, R
    Zhu, YN
    Williams, S
    [J]. PATTERN RECOGNITION AND IMAGE ANALYSIS, PROCEEDINGS, 2003, 2652 : 1108 - 1116
  • [2] Semi-automatic prostate segmentation of MR images based on flow orientation
    Samiee, Maryam
    Thomas, Gabriel
    Fazel-Rezai, Reza
    [J]. 2006 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, VOLS 1 AND 2, 2006, : 203 - +
  • [3] Semi-automatic segmentation for gonioscopic images
    Spagnuolo, Giusi
    De Giusti, Andrea
    [J]. INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2022, 63 (07)
  • [4] Semi-automatic knee cartilage segmentation
    Dam, Erik B.
    Folkesson, Jenny
    Pettersen, Paola C.
    Christiansen, Claus
    [J]. MEDICAL IMAGING 2006: IMAGE PROCESSING, PTS 1-3, 2006, 6144
  • [5] An improved image graph for semi-automatic segmentation
    Freedman, Daniel
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2012, 6 (04) : 533 - 545
  • [6] Technique for evaluation of semi-automatic segmentation methods
    Mao, F
    Gill, J
    Fenster, A
    [J]. MEDICAL IMAGING 1999: IMAGE PROCESSING, PTS 1 AND 2, 1999, 3661 : 1027 - 1036
  • [7] An improved image graph for semi-automatic segmentation
    Daniel Freedman
    [J]. Signal, Image and Video Processing, 2012, 6 : 533 - 545
  • [8] A semi-automatic method for vascular image segmentation
    School of Biology, Hunan University, Changsha, China
    不详
    [J]. Proc. - Int. Conf. Image Graph., ICIG, (3-7):
  • [9] Steerable semi-automatic segmentation of textured images*
    Micusík, B
    Hanbury, A
    [J]. IMAGE ANALYSIS, PROCEEDINGS, 2005, 3540 : 35 - 44
  • [10] Semi-automatic methods and segmentation of hyphal images
    Inglis, IM
    Gray, AJ
    Glasbey, CA
    [J]. 1998 IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION, 1998, : 53 - 58