Automatic Prostate Segmentation in Ultrasound Images using GVF Active Contour

Dehghan, Bahram; Salimi, Ahad

Document Type : Review Article

Authors

Bahram Dehghan ¹
Ahad Salimi ²

¹ Department of Electrical Engineering, Sarvestan Branch, Islamic Azad University, Sarvestan, Iran

² Department of Electrical Engineering, Zarin dasht Branch, Islamic Azad University, Zarin dasht, Iran

Abstract

Prostate cancer is one of the leading causes of death by cancer among men in the world. Ultrasonography is said to be the safest technique in medical imaging so it is used extensively in prostate cancer detection. In the other hand determining of prostate’s boundary in TRUS (Transrectal Ultrasound) images is very necessary in lots of treatment methods prostate cancer. So first and essential step for computer aided diagnosis (CAD) is the automatic prostate segmentation that is an open problem still. But the low SNR, presence of strong speckle noise, Weakness edges and shadow artifacts in these kind of images limit the effectiveness of classical segmentation schemes. The classical segmentation methods fail completely or require post processing step to remove invalid object boundaries in the segmentation results. This paper has proposed a fully automatic algorithm for prostate segmentation in TRUS images that overcomes the explained problems completely. The presented algorithm contains three main stages. First morphological smoothing and sticks filter are used for noise removing. A neural network is employed in second step to find a point in prostate region. Finally in the last step, the prostate boundaries is extracted by GVF active contour. Some experiments for the performance validity of the presented method, compare the extracted prostate by the proposed algorithm with manually-delineated boundaries by radiologist. The results show that our method extracts prostate boundaries with mean square area error lower than 4.4%. التقسیم إلى شرائح البروستاتا التلقائی فی صور الموجات فوق الصوتیة باستخدام GVF محیط ACTIVEسرطان البروستات هو واحد من الأسباب الرئیسیة للوفاة من السرطان بین الرجال فی العالم. وقال الموجات فوق الصوتیة لیکون الأکثر أمانا التقنیة فی التصویر الطبی حتى یتم استخدامه على نطاق واسع فی الکشف عن سرطان البروستاتا. فی جهة أخرى تحدید من حدود البروستاتا فی TRUS (عبر المستقیم الموجات فوق الصوتیة) صور ضروری جدا فی الکثیر من علاج سرطان البروستاتا طرق. خطوة حتى الأولى والأساسیة لتشخیص بمساعدة الکمبیوتر (CAD) هو تجزئة البروستاتا التلقائیة التی هی مشکلة مفتوحة حتى الآن. لکن انخفاض SNR، وجود الضوضاء البقع قوی، حواف ضعف والتحف الظل فی هذا النوع من الصور تحد من فعالیة مخططات تجزئة الکلاسیکیة. طرق تجزئة الکلاسیکیة فشلت تماما أو تتطلب بعد خطوة من خطوات التجهیز لإزالة الحدود کائن غیر صالح فی نتائج تجزئة. وقد اقترحت هذه الورقة خوارزمیة التلقائی بالکامل للتجزئة البروستاتا فی الصور TRUS أن یتغلب على المشاکل أوضح تماما. الخوارزمیة المقدمة تحتوی على ثلاثة مراحل رئیسیة. وتستخدم تجانس الصرفی الأول، ومرشح العصی لإزالة الضوضاء. واستخدمت شبکة عصبیة فی الخطوة الثانیة لإیجاد نقطة فی منطقة البروستاتا. وأخیرا فی الخطوة الأخیرة، یتم استخراج حدود البروستاتا بنسبة GVF کفاف نشط. بعض التجارب لصحة أداء الطریقة المعروضة، مقارنة البروستاتا المستخرجة من الخوارزمیة المقترحة مع الحدود المرسومة یدویا من قبل طبیب الأشعة. وأظهرت النتائج أن أسلوبنا مقتطفات حدود البروستاتا مع الخطأ مساحة مربعة یعنی أقل من 4.4٪.自动分割前列腺的超声影像使用GVF主动轮廓线巴赫拉姆，艾哈迈德萨利米抽象前列腺癌是死亡的男性世界中的主要原因癌症之一。超声被说成是在医学成像的最安全的技术，以便它在前列腺癌的检测被广泛使用。在另一方面确定TRUS（经直肠超声）图像前列腺边界是很多治疗方法前列腺癌十分必要的。计算机辅助诊断（CAD），因此第一和关键的一步是自动前列腺分割是一个开放的问题依然。但是，低信噪比，强斑点噪声，虚弱的边缘，并在这类图像的阴影瑕疵存在限制古典分割计划的成效。经典的分割方法完全失败，或需要后处理步骤，以除去在分割结果无效的对象的边界。本文提出了在完全克服了解释问题TRUS图像分割前列腺全自动算法。该算法包括三个主要阶段。第一形态的平滑和棍子过滤器用于噪声消除。神经网络采用在第二步骤中找到的前列腺区域的一个点。最后，在最后的步骤中，前列腺的边界由GVF活动轮廓萃取。一些实验用于该方法的有效性表现，通过该算法与放射科医生手动划定边界比较提取前列腺。结果表明，我们的方法提取前列腺边界与均方误差面积比4.4％低。

Keywords

References

[1] Cancer Facts and Figures. American Cance Society. [Online] http://www.cancer.org, 2002.

[2] Mettlin C: American society national cancer Detection project. Cancer 1995, 75:1790-1794..

[3] Sayan D. Pathak, Vikram Chalana, David R. Haynor, and Yongmin Kim.”Edge-guided boundary delineation prostate ultrasound images”.IEEE Trans. Med. Imaging, 19(12):1211-1219, 2000.

[4] M. Fitzpatrick and J. M. Reinhardt, editors.’’Prostate ultrasound image segmentation using level set-based region flow with shapeguidance’’. SPIE, Apr. 2005.

[5] Ahmed Jendoubi, Jianchao Zeng, and Mohamed F. Chouikha.’’Top-down approach to segmentation of prostate boundaries in ultrasound images’’.In AIPR, pages 145-149, 2004.

[6] Farhang Sahba, Hamid R. Tizhoosh, and Magdy M.A. Salama.’’Segmentation of prostate boundaries using regional contrast enhancement’’. In the IEEE International Conference on Image Processing (ICIP), volume 2, pages1266-1269,Sept. 2005.

[7] Farhang Sahba, Hamid R. Tizhoosh, and Magdy M.A. Salama ‘’ A coarse-to-fine approach to prostate boundary segmentation in ultrasound images’’. BioMedical Engineering OnLine 2005.

[8] C.K. Kwoh, M. Teo, W. Ng, S. Tan, and M. Jones “Outlining the prostate boundary using the harmonics method,” Med. Biol. Eng. Computing, vol. 36, pp. 768–771, 1998.

[9] .G. Aarnink, R.J.B. Giesen, A. L. Huynen, J. J. de la Rosette, F.M. Debruyne, and H. Wijkstra, “A practical clinical method for contour determination in ultrasound prostate images,” Ultrasound Med. Biol., vol. 20, pp. 705–717, 1994.

[10] R.G. Aarnink, S.D. Pathak, J. J. de la Rosette, F.M. Debruyne, Y. Kim and H. Wijkstra, “Edge detection in ultrasound prostate images using integrated edge map.,” Ultrasound Med. Biol., vol. 36, pp. 635–642, 1998.

[11] Y. Zhan and D. Shen, “Deformable segmentation of 3-d ultrasound prostate images using statistical texture matching method,” IEEE Transactions on Medical Imaging, vol. 25, pp. 256–272, 2006.

[12] D. Freedman, R.J. Radke, T. Zhang, Y. Jeong, D.M. Lovelock, and G.T.Y. Chen, “Modelbased segmentation of medical imagery by matching distributions,” IEEE Transactions on Medical Imaging, vol. 24 pp. 281–292, 2005.

[13] A. Ghanei, H. Soltanian-Zadeh, A. Ratkewicz, and F. Yin, “A three dimentional deformable model for segmentation of human prostate from ultrasound images,” Med. Phys, vol. 28, pp. 2147–2153, 2001.

[14] C. Knoll, M. Alcaniz, V. Grau, C. Monserrat, and M. Juan, “Outlining of the prostate using snakes with restrictions based on the wavelet transform,” Pattern Recognition, vol. 32, pp. 1767–1781,1999.

[15] S. D. Pathak, V. Chalana, D. haynor, and Y. kim, “Edge guided boundary delineationin prostate ultrasound images,”IEEE Transactions on Medical Imaging, vol. 19, pp. 1211–1219, 2000.

[16] N.N.Kachouie, P.Fieguth '' A Medical Texture Local Binary Pattern For TRUS Prostate Segmentation''‌29th Annual International conference of Engineering in Medicine and Biology Society. pp 5605-5608, 2007.

[17] P.Yan, S.Xu, B.Turkbey , J.Kruecker. “Discrete Deformable Model Guided by Partial Active Shape Model for TRUS Image Segmentation” IEEE Transaction on Biomedical Engineering, Vol. 57, No. 5, MAY 2010.

[18] S.S.Mohamad, M.MA.Salama '' Spectral clustering for TRUS images'' BioMedical Engineering OnLine 2007.

[19] S .Ghose, A.Oliver, R.Martin, X.Liado, J.Freixente, J.Martin'' Statistical Shape and Probability Prior Model for Automatic Prostate Segmentation'' International Conference on Digital Image Computing Techniques and Applications (DICTA), pp 340-345. 2011.

[20] S .Ghose, A.Oliver, R.Martin, X.Liado, J.Freixente, J.Martin''A probabilistic framework for automatic prostate segmentation with a statistical model of shape and appearance'' Image Processing (ICIP), 2011 18th IEEE International Conference on. pp 713-716.2011.

[21] R.Manavalan, K.Thangavel ''TRUS image segmentation using morphological operators and DBSCAN clustering ''Information and Communication Technologies (WICT), World Congress on,pp 898-903,2011.

[22] S.Mahdaviani, E.Septimiu '' 3D prostate segmentation based on ellipsoid fitting, image tapering and warping'' Engineering in Medicine and Biology Society, EMBS . 30th Annual International Conference of the IEEE .pp 2988-2991, 2008.

[23] S .Ghose, A.Oliver, R.Martin, X.Liado, J.Freixente '' Prostate Segmentation with Texture Enhanced Active Appearance Model'' Signal-Image Technology and Internet-Based Systems (SITIS), Sixth International Conference on. pp 18-22. 2010.

[24] S .Ghose, A.Oliver, R.Martin, X.Liado, J.Freixente'' Spectral clustering of shape and probability prior models for automatic prostate segmentation'' Engineering in Medicine and Biology Society (EMBC) Annual International Conference of the IEEE .pp 2335-2338.2012.

[25] Wang Y, Cardinal HN, Downey DB, Fenster A.” Semiautomatic three-dimensional segmentation of the prostate using twodimensional ultrasound images. Medical physics30(5):887-897, 2003.

[26] R. N. Czerwinski, D.L. Jones, and W. D. O'Brien Jr.”Detection of lines and boundaries in speckle images”- application to medical ultrasound.IEEE Trans. on Medical Imaging, 18(2):126-136, Feb. 1999.

[27] R. N. Czerwinski, D.L. Jones, and W. D. O'Brien Jr.”Line and boundary detection in speckle images”.IEEE Trans. on Image Processing, 7(12):1700-1714, Dec. 1998.

[28] R.C. Gonzalez and R.E. Woods.Digital Image Processing, 2nd. Ed.Prentice-Hall, 2002.

[29] R.C. Gonzalez and R.E. Woods.Digital Image Processing using matlab. Ed.Prentice-Hall, 2004.

[30] Michael Kass, Andrew Witkin, and Demetri Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, pages 321-331, 1988.

[31] Chensheng Sun and Kin-Man Lam.” The GVF Snake with a Minimal Path Approach”, 6th IEEE/ACIS International Conference on Computer and Information Science, 2007.

Majlesi Journal of Electrical Engineering

Automatic Prostate Segmentation in Ultrasound Images using GVF Active Contour

References

References

Volume 8, Issue 1 - Serial Number 1
March 2014
Pages 19-26

Automatic Prostate Segmentation in Ultrasound Images using GVF Active Contour

References

References

Volume 8, Issue 1 - Serial Number 1March 2014Pages 19-26

Volume 8, Issue 1 - Serial Number 1
March 2014
Pages 19-26