Automatic Prostate Segmentation in Ultrasound Images using GVF Active Contour

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 prostateâs 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%. Ø§ÙتÙسÛ٠إÙ٠شرائح اÙبرÙستاتا اÙتÙÙØ§Ø¦Û ÙÛ ØµÙر اÙÙÙجات ÙÙ٠اÙصÙتÛØ© باستخدا٠GVF ÙØ­ÛØ· ACTIVEسرطا٠اÙبرÙستات ÙÙ Ùاحد Ù٠اÙأسباب اÙرئÛسÛØ© ÙÙÙÙاة Ù٠اÙسرطا٠بÛ٠اÙرجا٠ÙÛ Ø§ÙعاÙÙ. ÙÙا٠اÙÙÙجات ÙÙ٠اÙصÙتÛØ© ÙÛÚ©Ù٠اÙأکثر Ø£ÙاÙا اÙتÙÙÛØ© ÙÛ Ø§ÙتصÙÛر اÙØ·Ø¨Û Ø­ØªÙ Ûت٠استخداÙ٠عÙÙ Ùطا٠Ùاسع ÙÛ Ø§Ùکش٠ع٠سرطا٠اÙبرÙستاتا. ÙÛ Ø¬ÙØ© أخر٠تحدÛد Ù٠حدÙد اÙبرÙستاتا ÙÛ TRUS (عبر اÙÙستÙÛ٠اÙÙÙجات ÙÙ٠اÙصÙتÛØ©) صÙر ضرÙØ±Û Ø¬Ø¯Ø§ ÙÛ Ø§ÙÚ©Ø«Ûر Ù٠عÙاج سرطا٠اÙبرÙستاتا طرÙ. خطÙØ© حت٠اÙØ£ÙÙÙ ÙاÙأساسÛØ© ÙتشخÛص بÙساعدة اÙÚ©ÙبÛÙتر (CAD) Ù٠تجزئة اÙبرÙستاتا اÙتÙÙائÛØ© اÙØªÛ ÙÛ ÙØ´Ú©ÙØ© ÙÙتÙحة حت٠اÙØ¢Ù. Ùک٠اÙØ®Ùاض SNRØ ÙجÙد اÙضÙضاء اÙبÙع ÙÙÛØ Ø­Ùا٠ضع٠ÙاÙتح٠اÙظ٠ÙÛ Ùذا اÙÙÙع Ù٠اÙصÙر تحد ÙÙ ÙعاÙÛØ© Ùخططات تجزئة اÙÚ©ÙاسÛÚ©ÛØ©. طر٠تجزئة اÙÚ©ÙاسÛÚ©ÛØ© ÙØ´Ùت تÙاÙا أ٠تتطÙب بعد خطÙØ© Ù٠خطÙات اÙتجÙÛز ÙإزاÙØ© اÙحدÙد کائ٠غÛر صاÙØ­ ÙÛ Ùتائج تجزئة. ÙÙد اÙترحت Ùذ٠اÙÙرÙØ© Ø®ÙارزÙÛØ© اÙتÙÙØ§Ø¦Û Ø¨Ø§ÙکاÙÙ ÙÙتجزئة اÙبرÙستاتا ÙÛ Ø§ÙصÙر TRUS Ø£Ù ÛتغÙب عÙ٠اÙÙشاک٠أÙضح تÙاÙا. اÙØ®ÙارزÙÛØ© اÙÙÙدÙØ© تحتÙÛ Ø¹ÙÙ Ø«Ùاثة Ùراح٠رئÛسÛØ©. Ùتستخد٠تجاÙس اÙصرÙÛ Ø§ÙØ£ÙÙØ ÙÙرشح اÙØ¹ØµÛ ÙإزاÙØ© اÙضÙضاء. ÙاستخدÙت شبکة عصبÛØ© ÙÛ Ø§ÙخطÙØ© اÙثاÙÛØ© ÙØ¥Ûجاد ÙÙطة ÙÛ ÙÙØ·ÙØ© اÙبرÙستاتا. ÙأخÛرا ÙÛ Ø§ÙخطÙØ© اÙأخÛØ±Ø©Ø Ûت٠استخراج حدÙد اÙبرÙستاتا بÙسبة GVF Ú©Ùا٠Ùشط. بعض اÙتجارب Ùصحة أداء اÙطرÛÙØ© اÙÙعرÙØ¶Ø©Ø ÙÙارÙØ© اÙبرÙستاتا اÙÙستخرجة Ù٠اÙØ®ÙارزÙÛØ© اÙÙÙترحة Ùع اÙحدÙد اÙÙرسÙÙØ© ÛدÙÛا ÙÙ Ùب٠طبÛب اÙأشعة. ÙأظÙرت اÙÙتائج أ٠أسÙÙبÙا ÙÙتطÙات حدÙد اÙبرÙستاتا Ùع اÙخطأ Ùساحة Ùربعة ÛعÙÛ Ø£ÙÙ ÙÙ 4.4Ùª.èªå¨åå²ååèºçè¶å£°å½±å使ç¨GVF主å¨è½®å»çº¿å·´èµ«æå§ï¼è¾åè¿å¾·è¨å©ç±³æ½è±¡ååèºçæ¯æ­»äº¡çç·æ§ä¸ç中ç主è¦åå ççä¹ä¸ãè¶å£°è¢«è¯´ææ¯å¨å»å­¦æåçæå®å¨çææ¯ï¼ä»¥ä¾¿å®å¨ååèºççæ£æµè¢«å¹¿æ³ä½¿ç¨ãå¨å¦ä¸æ¹é¢ç¡®å®TRUSï¼ç»ç´è è¶å£°ï¼å¾åååèºè¾¹çæ¯å¾å¤æ²»çæ¹æ³ååèºçååå¿è¦çã计ç®æºè¾å©è¯æ­ï¼CADï¼ï¼å æ­¤ç¬¬ä¸åå³é®çä¸æ­¥æ¯èªå¨ååèºåå²æ¯ä¸ä¸ªå¼æ¾çé®é¢ä¾ç¶ãä½æ¯ï¼ä½ä¿¡åªæ¯ï¼å¼ºæç¹åªå£°ï¼èå¼±çè¾¹ç¼ï¼å¹¶å¨è¿ç±»å¾åçé´å½±ççµå­å¨éå¶å¤å¸åå²è®¡åçææãç»å¸çåå²æ¹æ³å®å¨å¤±è´¥ï¼æéè¦åå¤ç步骤ï¼ä»¥é¤å»å¨åå²ç»ææ æç对象çè¾¹çãæ¬ææåºäºå¨å®å¨åæäºè§£éé®é¢TRUSå¾ååå²ååèºå¨èªå¨ç®æ³ã该ç®æ³åæ¬ä¸ä¸ªä¸»è¦é¶æ®µã第ä¸å½¢æçå¹³æ»åæ£å­è¿æ»¤å¨ç¨äºåªå£°æ¶é¤ãç¥ç»ç½ç»éç¨å¨ç¬¬äºæ­¥éª¤ä¸­æ¾å°çååèºåºåçä¸ä¸ªç¹ãæåï¼å¨æåç步骤中ï¼ååèºçè¾¹çç±GVFæ´»å¨è½®å»èåãä¸äºå®éªç¨äºè¯¥æ¹æ³çæææ§è¡¨ç°ï¼éè¿è¯¥ç®æ³ä¸æ¾å°ç§å»çæå¨åå®è¾¹çæ¯è¾æåååèºãç»æ表æï¼æ们çæ¹æ³æåååèºè¾¹çä¸åæ¹è¯¯å·®é¢ç§¯æ¯4.4ï¼ä½ã