Segmentation of prostate biopsy needles in transrectal ultrasound images

被引:2
作者
Krefting, Dagmar [1 ]
Haupt, Barbara [1 ]
Tolxdorff, Thomas [1 ]
Kempkensteffen, Carsten [2 ]
Miller, Kurt [2 ]
机构
[1] Charite Univ Med Berlin, Inst Med Informat, Hindenburgdamm 30, D-12200 Berlin, Germany
[2] Charite Univ Med Berlin, Urol Klin & Poliklin, D-12200 Berlin, Germany
来源
MEDICAL IMAGING 2007: IMAGE PROCESSING, PTS 1-3 | 2007年 / 6512卷
关键词
segmentation; ultrasound; prostate cancer; TRUS; mahalanobis distance;
D O I
10.1117/12.709549
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Prostate cancer is the most common cancer in men. Tissue extraction at different locations (biopsy) is the gold-standard for diagnosis of prostate cancer. These biopsies are commonly guided by transrectal ultrasound imaging (TRUS). Exact location of the extracted tissue within the gland is desired for more specific diagnosis and provides better therapy planning. While the orientation and the position of the needle within clinical TRUS image are limited, the appearing length and visibility of the needle varies strongly. Marker lines are present and tissue inhomogeneities and deflection artefacts may appear. Simple intensity, gradient oder edge-detecting based segmentation methods fail. Therefore a multivariate statistical classificator is implemented. The independent feature model is built by supervised learning using a set of manually segmented needles. The feature space is spanned by common binary object features as size and eccentricity as well as imaging-system dependent features like distance and orientation relative to the marker line. The object extraction is done by multi-step binarization of the region of interest. The ROI is automatically determined at the beginning of the segmentation and marker lines are removed from the images. The segmentation itself is realized by scale-invariant classification using maximum likelihood estimation and Mahalanobis distance as discriminator. The technique presented here could be successfully applied in 94% of 1835 TRUS images from 30 tissue extractions. It provides a robust method for biopsy needle localization in clinical prostate biopsy TRUS images.
引用
收藏
页数:8
相关论文
共 6 条
[1]  
Chandra MP., 1936, P NATL I SCI INDIA, V2, P49
[2]   A real-time biopsy needle segmentation technique using Hough Transform [J].
Ding, MY ;
Fenster, A .
MEDICAL PHYSICS, 2003, 30 (08) :2222-2233
[3]  
Duda RO, 2006, PATTERN CLASSIFICATI
[4]   Three-dimensional computer reconstruction of prostate cancer from radical prostatectomy specimens: Evaluation of the model by core biopsy simulation [J].
Egevad, L ;
Frimmel, H ;
Norberg, M ;
Mattson, S ;
Carlbom, I ;
Bengtsson, E ;
Busch, C .
UROLOGY, 1999, 53 (01) :192-198
[5]   Transrectal ultrasound guided biopsy of the prostate:: random sextant versus biopsies of sono-morphologically suspicious lesions [J].
Loch, T ;
Eppelmann, U ;
Lehmann, J ;
Wullich, B ;
Loch, A ;
Stöckle, M .
WORLD JOURNAL OF UROLOGY, 2004, 22 (05) :357-360
[6]   Oblique needle segmentation and tracking for 3D TRUS guided prostate brachytherapy [J].
Wei, ZP ;
Gardi, L ;
Downey, DB ;
Fenster, A .
MEDICAL PHYSICS, 2005, 32 (09) :2928-2941