Gabor filter-based localization of straight and curved needles in 2D ultrasound images

2D ultrasound (US) is one of the most commonly used medical imaging devices for needle localization in biopsies. However, the produced images are low-resolution and contain an excessive number of artifacts, which makes the needle localization challenging. Image processing techniques can help resolve this issue. This paper presents a novel Gabor filter-based method for needle localization in 2D US images, which enhances the needle outline in the images while suppressing other structures. The scheme works in two stages: First, the Gabor filter is applied to the image, the needle insertion angle is estimated, and the needle trajectory is found using a RANSAC line fitting; then, the Gabor filter is repeated using the estimated insertion angle and the location of the needle tip is estimated using probability mapping. The proposed scheme works with both straight and curved needles. An automatic parameter tuning method, which is used to optimize the threshold value of the Otsu’s method, is also presented here. The tests on this needle localization scheme were done using two different water mixtures, three different gelatin-based phantoms, and ex vivo experiments. The accuracy was assessed using an infrared-camera-based tracking sensor and computed tomography images. The results showed that the suggested localization scheme can be effectively used in the 2D US image-guided needle procedures

PDF

___

1] Liberman L, Drotman M, Morris EA, LaTrenta LR, Abramson AF et al. Imaging–histologic discordance at per- cutaneous breast biopsy. Cancer 2000; 89 (12): 2538-2546. doi: 10.1002/1097-0142(20001215)89:12%3C2538::AID- CNCR4%3E3.0.CO;2-%23
[2] Kaya M, Bebek O. Needle localization using Gabor filtering in 2D ultrasound images. In: IEEE International Conference on Robotics and Automation; Hong Kong, China; 2014. pp. 4881-4886. doi: 10.1109/ICRA.2014.6907574
[3] Draper KJ, Blake CC, Gowman L, Downey DB, Fenster A. An algorithm for automatic needle localization in ultrasound‐guided breast biopsies. Medical Physics 2000; 27: 1971-1979. doi: 10.1118/1.1287437
[4] Ding M, Fenster A. A real-time biopsy needle segmentation technique using Hough transform. Medical Physics 2003; 30 (8): 2222-2233. doi: 10.1118/1.1591192
[5] Cheung S, Rohling R. Enhancement of needle visibility in ultrasound-guided percutaneous procedures. Ultrasound in Medicine & Biology 2004; 30 (5): 617-624. doi: 10.1016/j.ultrasmedbio.2004.02.001
[6] Barva M, Kybic J, Mari JM, Cachard C, Hlavác V. Automatic localization of curvilinear object in 3D ultrasound images. In: Ultrasonic Imaging and Signal Processing: Medical Imaging; San Diego, CA, USA; 2005. pp. 455-462. doi: 10.1117/12.594763
[7] Okazawa SH, Ebrahimi R, Chuang J, Rohling RN, Salcudean, SE. Methods for segmenting curved needles in ultrasound images. Medical Image Analysis 2006; 10 (3): 330-342. doi: 10.1016/j.media.2006.01.002
[8] Ayvali E, Desai JP. Optical flow-based tracking of needles and needle-tip localization using circular Hough transform in ultrasound images. Annals of Biomedical Engineering 2015; 43 (8): 1828-1840. doi: 10.1007/s10439-014-1208-0
[9] Neshat HRS, Patel RV. Real-time parametric curved needle segmentation in 3D ultrasound images. In: IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics; Scottsdale, AZ, USA; 2008. pp. 670-675. doi: 10.1109/BIOROB.2008.4762877
[10] Adebar TK, Okamura AM. 3D segmentation of curved needles using doppler ultrasound and vibration. In: Infor- mation Processing in Computer-Assisted Interventions; Heidelberg, Germany; 2013. pp. 61-70. doi: 10.1007/978-3- 642-38568-1_7
[11] Dong B, Savitsky E, Osher S. A novel method for enhanced needle localization using ultrasound-guidance. In: Advances in Visual Computing; Las Vegas, NV, USA; 2009. pp. 914-923. doi: 10.1007/978-3-642-10331-5_85
[12] Uherčík M, Kybic J, Cachard C, Liebgott H. Line filtering for detection of microtools in 3D ultrasound data. In: IEEE International Ultrasonics Symposium; Rome, Italy; 2009. pp. 594-597. doi: 10.1109/ULTSYM.2009.5441538
[13] Zhao Y, Bernard A, Cachard C, Liebgott H. Biopsy needle localization and tracking using ROI-RK method. Abstract and Applied Analysis 2014; 2014: 973147. doi: 10.1155/2014/973147
[14] Aboofazeli M, Abolmaesumi P, Mousavi P, Fichtinger G. A new scheme for curved needle segmentation in three- dimensional ultrasound images. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro; Boston, MA, USA; 2009. pp. 1067-1070. doi: 10.1109/ISBI.2009.5193240
[15] Waine M, Rossa C, Sloboda R, Usmani N, Tavakoli M. 3D needle shape estimation in TRUS-guided prostate brachytherapy using 2D ultrasound images. IEEE Journal of Biomedical and Health Informatics 2016; 20 (6): 1621-1631. doi: 10.1109/JBHI.2015.2477829
[16] Wen X, Salcudean SE, Lawrence PD. Detection of brachytherapy seeds using 3-D transrectal ultrasound. IEEE Transactions on Biomedical Engineering 2010; 57 (10): 2467-2477. doi: 10.1109/TBME.2010.2053926
[17] Ayvaci A, Yan P, Xu S, Soatto S, Kruecker J. Biopsy needle detection in transrectal ultrasound. Computerized Medical Imaging and Graphics 2011; 35 (7): 653-659. doi: 10.1016/j.compmedimag.2011.03.005
[18] Cao K, Mills D, Patwardhan KA. Automated catheter detection in volumetric ultrasound. In: IEEE 10th International Symposium on Biomedical Imaging; San Francisco, CA, USA; 2013. pp. 37-40. doi: 10.1109/ISBI.2013.6556406
[19] Vrooijink GJ, Abayazid M, Misra S. Real-time three-dimensional flexible needle tracking using two-dimensional ultrasound. In: IEEE International Conference on Robotics and Automation; Karlsruhe, Germany; 2013. pp. 1688- 1693. doi: 10.1109/ICRA.2013.6630797
[20] Chatelain P, Krupa A, Navab N. 3D ultrasound-guided robotic steering of a flexible needle via visual servoing. In: IEEE International Conference on Robotics and Automation; Seattle, WA, USA; 2015. pp. 2250-2255. doi: 10.1109/ICRA.2015.7139497
21] Renfrew M, Bai Z, Cavusoglu MC. Particle filter based active localization of target and needle in robotic image- guided intervention systems. In: IEEE International Conference on Automation Science and Engineering; Madison, WI, USA; 2013. pp. 448-454. doi: 10.1109/CoASE.2013.6653938
[22] Mathiassen K, Dall’Alba D, Muradore R, Fiorini P, Elle OJ. Real-time biopsy needle tip estimation in 2D ultrasound images. In: IEEE International Conference on Robotics and Automation; Karlsruhe, Germany; 2013. pp. 4363-4369. doi: 10.1109/ICRA.2013.6631195
[23] Beigi P, Rohling R. Needle localization using a moving stylet/catheter in ultrasound-guided regional anesthesia: a feasibility study. In: SPIE Medical Imaging: Image-Guided Procedures, Robotic Interventions, and Modeling; San Diego, CA, USA; 2014. pp. 90362Q-90362Q. doi: 10.1117/12.2043957
[24] Mwikirize C, Nosher JL, Hacihaliloglu I. Convolution neural networks for real-time needle detection and localization in 2D ultrasound. International Journal of Computer Assisted Radiology and Surgery 2018; 13: 647-657. doi: 10.1007/s11548-018-1721-y
[25] Mwikirize C, Nosher JL, Hacihaliloglu I. Signal attenuation maps for needle enhancement and localization in 2D ultrasound. International Journal of Computer Assisted Radiology and Surgery 2018; 13: 363-374. doi: 10.1007/s11548-017-1698-y
[26] Daoud MI, Khraiwesh S, Zayadeen A, Alazrai R. Accurate needle localization in two-dimensional ultrasound images. In: International Conference on Electrical and Electronics Engineering; Bursa; 2017. pp. 578-582.
[27] Lee JY, Islam M, Woh JR, Washeem TSM, Ngoh LYC et al. Ultrasound needle segmentation and trajectory prediction using excitation network. International Journal of Computer Assisted Radiology and Surgery 2020; 15: 437–443. doi: 10.1007/s11548-019-02113-x
[28] Xu F, Gao D, Wang S, Zhanwen A. MLESAC based localization of needle insertion using 2D ultrasound images. Journal of Physics: Conference Series 2018; 1004 (1): 012037. doi: 10.1088/1742-6596/1004/1/012037
[29] Novotny PM, Stoll JA, Vasilyev NV, Pedro J, Dupont PE et al. GPU based real-time instrument tracking with three-dimensional ultrasound. Medical Image Analysis 2007; 11 (5): 458-464. doi: 10.1016/j.media.2007.06.009
[30] Chatelain P, Krupa A, Marchal M. Real-time needle detection and tracking using a visually servoed 3D ultrasound probe. In: IEEE International Conference on Robotics and Automation; Karlsruhe, Germany; 2013. pp. 1676-1681. doi: 10.1109/ICRA.2013.6630795
[31] Pourtaherian A, Zinger S, de With PHN, Korsten HH, Mihajlovic N. Gabor-based needle detection and tracking in three-dimensional ultrasound data volumes. In: IEEE International Conference on Image Processing; Paris, France; 2014. pp. 3602-3606. doi: 10.1109/ICIP.2014.7025731
[32] Hacihaliloglu I, Beigi P, Ng G, Rohling RN, Salcudean S et al. Projection-based phase features for localization of a needle tip in 2D curvilinear ultrasound. In: International Conference on Medical Image Computing and Computer- Assisted Intervention; Munich, Germany; 2015. pp. 347-354. doi: 10.1007/978-3-319-24553
[33] Hatt CR, Ng G, Parthasarathy V. Enhanced needle localization in ultrasound using beam steering and learning-based segmentation. Computerized Medical Imaging and Graphics 2015; 41: 46-54. doi: 10.1016/j.compmedimag.2014.06.016
[34] Kaya M, Bebek O. Gabor filter based localization of needles in ultrasound guided robotic interventions. In: IEEE International Conference on Imaging Systems and Techniques; Santorini, Greece; 2014. pp. 112-117. doi: 10.1109/IST.2014.6958456
[35] Kaya M, Senel E, Ahmad A, Orhan O, Bebek O. Real-time needle tip localization in 2D ultrasound images for robotic biopsies. In: International Conference on Advanced Robotics; Istanbul, Turkey; 2015. pp. 47-52. doi: 10.1109/ICAR.2015.7251432
[36] Hong L, Wan Y, Jain A. Fingerprint image enhancement: algorithm and performance evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence 1998; 20 (8): 777-789. doi: 10.1109/34.709565
[37] Ma L, Wang Y, Tan T. Iris recognition using circular symmetric filters. In: International Conference on Pattern Recognition; Quebec, Canada; 2002. pp. 414-417. doi: 10.1109/ICPR.2002.1048327
[38] Vicas C, Lupsor M, Badea R, Nedevschi S. Detection of anatomical structures on ultrasound liver images using Gabor filters. In: IEEE International Conference on Automation, Quality and Testing, Robotics; Cluj-Napoca, Romania; 2010. pp. 1-5. doi: 10.1109/AQTR.2010.5520792
[39] Yang J, Shi Y, Yang J. Finger-vein recognition based on a bank of Gabor filters. In: Asian Conference on Computer Vision; Xi’an, China; 2009. pp. 374-383. doi: 10.1007/978-3-642-12307-8_35
[40] Hou Z. Measuring Technology and Mechatronics Automation in Electrical Engineering. New York, NY, USA: Springer, 2012.
[41] Frangi AF, Niessen WJ, Vincken KL, Viergever MA. Multiscale vessel enhancement filtering. In: Medi- cal Image Computing and Computer-Assisted Interventation; Cambridge, MA, USA; 1998. pp. 130-137. doi: 10.1007/BFb0056195
[42] Fogel I, Sagi D. Gabor filters as texture discriminator. Biological Cybernetics 1989; 61 (2): 103-113. doi: 10.1007/BF00204594
[43] Otsu N. A threshold selection method from gray-level histograms. Automatica 1975; 11 (285-296): 23-27.
[44] Li JW, Karmakar MK, Li X, Kwok WH, Kee WDN. Gelatin-agar lumbosacral spine phantom. Journal of Ultrasound in Medicine 2011; 30 (2): 263-272. doi: 10.7863/jum.2011.30.2.263
[45] Culjat MO, Goldenberg D, Tewari P, Singh RS. A review of tissue substitutes for ultrasound imaging. Ultrasound in Medicine & Biology 2010; 36 (6): 861-873. doi: 10.1016/j.ultrasmedbio.2010.02.012
[46] Ahmad A, Bebek Ö. Özyeğin Biopsy Robot: System integration architecture and motion compensation of a moving target. Turkish Journal of Electrical Engineering & Computer Sciences 2018; 26: 1651-1661. doi: 10.3906/elk-1701- 193
[47] Leveridgea MJ, Finellib A, Kachurac JR, Evansd A, Chungb H, et al. Outcomes of small renal mass needle core biopsy, nondiagnostic percutaneous biopsy, and the role of repeat biopsy. European Urology 2011; 60 (3): 578-584. doi: 10.1016/j.eururo.2011.06.021