Optimized prostate biopsy via a statistical atlas of cancer spatial distribution

A methodology is presented for constructing a statistical atlas of spatial distribution of prostate cancer from a large patient cohort, and it is used for optimizing needle biopsy. An adaptive-focus deformable model is used for the spatial normalization and registration of 100 prostate histological samples, which were provided by the Center for Prostate Disease Research of the US Department of Defense, resulting in a statistical atlas of spatial distribution of prostate cancer. Based on this atlas, a statistical predictive model was developed to optimize the needle biopsy sites, by maximizing the probability of detecting cancer. Experimental results using cross-validation show that the proposed method can detect cancer with a 99% success rate using seven needles, in these samples.

[1]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..

[2]  Martin Styner,et al.  Segmentation of Single-Figure Objects by Deformable M-reps , 2001, MICCAI.

[3]  M. Terris,et al.  Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate. , 1989, The Journal of urology.

[4]  Dinggang Shen,et al.  A Statistical Atlas of Prostate Cancer for Optimal Biopsy , 2001, MICCAI.

[5]  Paul A. Yushkevich,et al.  Multiscale deformable model segmentation and statistical shape analysis using medial descriptions , 2002, IEEE Transactions on Medical Imaging.

[6]  Louis R Kavoussi,et al.  Accuracy of digital rectal examination and transrectal ultrasonography in localizing prostate cancer. , 1994, The Journal of urology.

[7]  Milan Sonka,et al.  Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples , 2000, IEEE Transactions on Medical Imaging.

[8]  G. D. Taylor,et al.  Computer simulation of the probability of detecting low volume carcinoma of the prostate with six random systematic core biopsies. , 1995, Urology.

[9]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[11]  Dinggang Shen,et al.  Segmentation of prostate boundaries from ultrasound images using statistical shape model , 2003, IEEE Transactions on Medical Imaging.

[12]  Dinggang Shen,et al.  An Adaptive-Focus Deformable Model Using Statistical and Geometric Information , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  D. Johnston,et al.  Optimization of prostate biopsy strategy using computer based analysis. , 1997, The Journal of urology.

[14]  Dinggang Shen,et al.  An adaptive-focus statistical shape model for segmentation and shape modeling of 3-D brain structures , 2001, IEEE Transactions on Medical Imaging.

[15]  Christos Davatzikos,et al.  Spatial Transformation and Registration of Brain Images Using Elastically Deformable Models , 1997, Comput. Vis. Image Underst..

[16]  D L McCullough,et al.  Systematic 5 region prostate biopsy is superior to sextant method for diagnosing carcinoma of the prostate. , 1997, The Journal of urology.

[17]  Wei Zhang,et al.  Distribution of Prostrate Cancer for Optimized Biopsy Protocols , 2000, MICCAI.

[18]  Michael I. Miller,et al.  Deformable templates using large deformation kinematics , 1996, IEEE Trans. Image Process..

[19]  D. Johnston,et al.  Comparison of prostate biopsy schemes by computer simulation. , 1999, Urology.

[20]  Donohue Re,et al.  Adenocarcinoma of the prostate: biopsy to whole mount. Denver VA experience. , 1991 .

[21]  G J Miller,et al.  Adenocarcinoma of the prostate: biopsy to whole mount. Denver VA experience. , 1991, The Urologic clinics of North America.

[22]  A. Goodman,et al.  The benefit and cost of prostate cancer early detection , 1993, CA: a cancer journal for clinicians.