Segmentation of laparoscopic images for computer assisted surgery
Abstract
This paper presents a learning-based approach to the problem of segmentation of laparoscopic images. The first step of the proposed method is to preprocess input images with a homomorphic filter. An initial segmentation map is then computed using a region growing based image segmentation algorithm. The obtained regions are finally classified using a support vector machine (SVM) to produce the final segmentation. The preliminary results computed on two image sets were promising. The first set includes laparoscopic imugvs recorded in a controlled environment. The second set includes laparoscopic images recorded during three disk removal surgeries performed laparoscopically at Sainte-Justine Hospital.
References
[1]
Kuhnapfel, U., Cakmak, H., Maass, H.: Endoscopic surgery training using virtual reality and deformable tissue simulation. Computers & Graphics UK 24 (2000) 671-682.
[2]
Cotin, S., Delingette, H., Anache, N.: Real-time elastic deformations of soft tissues for surgery simulation stéphane cotin, hervé delingette: and nicholas ayache. IEEE Trans. on Visualization and Computer Graphics 5 (1999) 62-73.
[3]
Basdogan, C., Ho, C., Srinivasan, M.: Simulation of tissue cutting and bleeding for laparoscopic surgery using auxiliary surfaces. In: Proc. Medicine Meets Virtual Reality IOS Press (1999) 38-44.
[4]
Dey, D., Gobbi, D., Slomka, P., Surry K., Peter, T.: Automatic fusion of freehand endoscopic brain images to threedimensional surfaces: Creating stereoscopic panoramas. IEEE Trans. on Medical Imaging 21 (2002) 23-30.
[5]
Bricault, I., Ferretti, G., Cinquin, P.: Registration of real and ct-derived virtual bronchoscopic images to assist transbronchial biopsy. IEEE Trans. on Medical Imaging 17 (2002) 703-714.
[6]
Lunn, K., Hartov, A., Roberts, D., Sun, H., Paulsen, K.: Extracting displacement data from coregistered ultrasound for brain modeling. In: Proc. of the SPIE Medical Imaging. (2002).
[7]
Wei, G., Arbter, K., Hirzinger, G.: Real-time visual servoing for laparoscopic surgery, controlling robot motion with color image segmentation. IEEE Engineering in Medicine and Biology Magazine 16 (1997) 40-45.
[8]
Zhang, X., Payandeh, S.: Application of visual tracking ibr robot-assisted laparoscopic surgery. Journal of Robotic Systems 19 (2002) 315-328.
[9]
Gonzalez, R., Woods, R.: Digital Image Processing. Prentice Hall (2002).
[10]
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. International Journal of Computer Vision 22 (1997) 61-79.
[11]
Deng, Y., Manjunath, B.: Unsupervised segmentation of color-texture regions in images aatd video. IEEE Trans. on Pattern Analysis and Machine Intelligence 23 (2001) 800-810.
[12]
Vapnik, V.: The Nature of Statistical Learning Theory. Springer-Verlag (1995).
[13]
Chapelle, O., Haffner, P., Vapnick, V.: Support vector machines for histogram-based classification. IEEE Trans. on Neural Networks 10 (1995) 1055-1064.
[14]
Tsutsumi, F., Nakajima, C.: Hybrid approach of video indexing and machine learning for rapid indexing and highly precise object recognition. In: Proc. ICIP. Volume 2. (2001) 645-648.
[15]
Hu, M.K.: Visual pattern recogidtion by moment invariants. IRE Trans. Information Theory 8 (1962) 179-187.
[16]
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Sig-graph 2000, Computer Graphics Proceedings, ACM Press/ACM SIGGRAPH/ Addison Wesley Longman (2000) 417-424.
[17]
Ballester, C., Bertalmio, M., Caselles, V., Sapiro, G., Verdera, J.: Filling-in by joint interpolation of vector fields and grey levds. IEEE Trans. on Image Processing 10 (2000) 1200-1211.
- Segmentation of laparoscopic images for computer assisted surgery
Recommendations
Computer-Assisted Soft-Tissue Surgery Training and Monitoring
MICCAI '01: Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted InterventionLast year at MICCAI, a computer-assisted surgical training system (CASTS) for Transurethral Resection of the Prostate (TURP), was presented [1]. Unpredictable deformation of the prostate phantom caused unacceptable inaccuracies. Solutions have now been ...
Segmentation of Laparoscopic Images: Integrating Graph-Based Segmentation and Multistage Region Merging
CRV '05: Proceedings of the 2nd Canadian conference on Computer and Robot VisionThis paper presents a method that combines graph-based segmentation and multistage region merging to segment laparoscopic images. Starting with image pre-processing, including Gaussian smoothing, brightness and contrast enhancement, and histogram ...
Robot-assisted laparoscopic ultrasound
IPCAI'10: Proceedings of the First international conference on Information processing in computer-assisted interventionsNovel tools for existing robotic surgical systems present opportunities for exploring improved techniques in minimally invasive surgery. Specifically, intraoperative ultrasonography is a tool that is being used with increased frequency, yet has ...
Comments
Information & Contributors
Information
Published In
Sponsors
- IAPR: International Association for Pattern Recognition
- SSBA: Swedish Society for Automated Image Analysis
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 29 June 2003
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Jan 2025