Automatic Segmentation of Extraocular Muscles Using Superpixel and Normalized Cuts

详细信息    查看全文

• 关键词：Automatic image segmentation ; Extraocular muscle ; Superpixel ; Region adjacency graph ; Normalized Cuts
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9474
• 期：1
• 页码：501-510
• 全文大小：1,735 KB
• 参考文献：1.Bijlsma, W.R., Mourits, M.P.: Radiologic measurement of extraocular muscle volumes in patients with Graves’ orbitopathy: a review and guideline. Orbit 25, 83–91 (2006)CrossRef
  2.Ben Simon, G.J., Syed, H.M., Douglas, R., McCann, J.D., Goldberg, R.A.: Extraocular muscle enlargement with tendon involvement in thyroid-associated orbitopathy. Am. J. Ophthalmol. 137, 1145–1147 (2004)CrossRef
  3.Dal Canto, A.J., Crowe, S., Perry, J.D., Traboulsi, E.I.: Intraoperative relaxed muscle positioning technique for strabismus repair in thyroid eye disease. Ophthalmology 113, 2324–2330 (2006)CrossRef
  4.Gupta, A., Sadeghi, P.B., Akpek, E.K.: Occult thyroid eye disease in patients presenting with dry eye symptoms. Am. J. Ophthalmol. 147, 919–923 (2009)CrossRef
  5.Kono, R., Poukens, V., Demer, J.L.: Quantitative analysis of the structure of the human extraocular muscle pulley system. Invest. Ophth. Vis. Sci. 43, 2923–2932 (2002)
  6.Chaudhuri, Z., Demer, J.L.: Sagging eye syndrome: connective tissue involution as a cause of horizontal and vertical strabismus in older patients. JAMA Ophthalmol. 131, 619–625 (2013)CrossRef
  7.Firbank, M.J., Coulthard, A.: Evaluation of a technique for estimation of extraocular muscle volume using 2D MRI. Brit. J. Radiol. 73, 1282–1289 (2000)CrossRef
  8.Firbank, M.J., Harrison, R.M., Williams, E.D., Coulthard, A.: Measuring extraocular muscle volume using dynamic contours. Magn. Reson. Imaging 19, 257–265 (2001)CrossRef
  9.Souza, A.D.A., Ruiz, E.E.S., Cruz, A.A.V.: Extraocular muscle quantification using mathematical morphology: a semi-automatic method for analyzing muscle enlargement in orbital diseases. Comput. Med. Imag. Grap. 31, 39–45 (2007)CrossRef
  10.Szucs-Farkas, Z., Toth, J., Balazs, E., Galuska, L., Burman, K.D., Karanyi, Z., Leovey, A., Nagy, E.V.: Using morphologic parameters of extraocular muscles for diagnosis and follow-up of Graves’ ophthalmopathy: diameters, areas, or volumes? Am. J. Roentgenol. 179, 1005–1010 (2002)CrossRef
  11.Lv, B., Wu, T.N., Lu, K., Xie, Y.: Automatic segmentation of extraocular muscle using level sets methods with shape prior. In: Long, M. (ed.) IFMBE Proceedings. IFMBE, vol. 39, pp. 904–907. Springer, Heidelberg (2012)
  12.Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE T. Pattern Anal. 34, 2274–2282 (2012)CrossRef
  13.Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV, pp. 10–17 (2003)
  14.Fulkerson, B., Vedaldi, A., Soatto, S.: Class segmentation and object localization with superpixel neighborhoods. In: ICCV, pp. 670–677 (2009)
  15. Levinshtein, A., Sminchisescu, C., Dickinson, S.: Optimal contour closure by superpixel grouping. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 480–493. Springer, Heidelberg (2010) CrossRef
  16.Chan, T., Vese, L.: Active contours without edges. IEEE T. Image Process. 10, 266–277 (2001)MATH CrossRef
  17.Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vision 1, 321–331 (1988)CrossRef
  18.Souza, A., Ruiz, E.: Fast and accurate detection of extraocular muscle borders using mathematical morphology. In: IEMBS, pp. 1779–1782 (2000)
  19.Wei, Q., Sueda, S., Miller, J., Demer, J., Pai, D.: Template-based reconstruction of human extraocular muscles from magnetic resonance images. In: ISBI, pp. 105–108 (2009)
  20.Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59, 167–181 (2004)CrossRef
  21. Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008) CrossRef
  22. Conrad, C., Mertz, M., Mester, R.: Contour-relaxed superpixels. In: Heyden, A., Kahl, F., Olsson, C., Oskarsson, M., Tai, X.-C. (eds.) EMMCVPR 2013. LNCS, vol. 8081, pp. 280–293. Springer, Heidelberg (2013) CrossRef
  23.Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. Int. J. Comput. Vision 80, 300–316 (2008)CrossRef
  24.Tremeau, A., Colantoni, P.: Regions adjacency graph applied to color image segmentation. IEEE T. Image Process. 9, 735–744 (2000)CrossRef
  25.Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE T. Pattern Anal. 22, 888–905 (2000)CrossRef
  26.Sharifi, M., Fathy, M., Tayefeh Mahmoudi, M.: A classified and comparative study of edge detection algorithms. In: ITCC, pp. 117–120 (2002)
  27.Thorndike, R.L.: Who belongs in the family? Psychometrika 18, 267–276 (1953)CrossRef
  28.Tibshirani, R., Walther, G., Hastie, T.: Estimating the number of clusters in a data set via the gap statistic. J. Roy. Stat. Soc. B Met. 63, 411–423 (2001)MATH CrossRef MathSciNet
  29.Meila, M.: Comparing clusterings: an axiomatic view. In: ICML, pp. 577–584, New York (2005)
  30.Rand, W.M.: Objective criteria for the evaluation of clustering methods. J. Am. Stat. Assoc. 66, 846–850 (1971)CrossRef
  31.Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: BMVC, pp. 1–10 (2007)
  32.Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE T. Pattern Anal. 33, 898–916 (2011)CrossRef
  
• 作者单位：Qi Xing (25)
  Yifan Li (26)
  Brendan Wiggins (27)
  Joseph L. Demer (28)
  Qi Wei (27)
  
  25. Department of Computer Science, George Mason University, Fairfax, VA, USA
  26. Lake Braddock Secondary School, Burke, VA, USA
  27. Department of Bioengineering, George Mason University, Fairfax, VA, USA
  28. Department of Neurology, Jules Stein Eye Institute, David Geffen Medical School at University of California, Los Angeles, USA
  
• 丛书名：Advances in Visual Computing
• ISBN：978-3-319-27857-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper proposes a novel automatic method to segment extraocular muscles and orbital structures. Instead of conventional segmentation at the pixel level, superpixels at the structure level were used as the basic image processing unit. A region adjacency graph was built based on the neighborhood relationship among superpixels. Using Normalized Cuts on the region adjacency graph, we refined the segmentation by using a variety of features derived from the classical shape cues, including contours and continuity. To demonstrate the efficiency of the method, segmentation of Magnetic Resonance images of five healthy subjects was performed and analyzed. Three region-based image segmentation evaluation metrics were applied to quantify the automatic segmentation accuracy against manual segmentation. Our novel method could produce accurate and reproducible eye muscle segmentation.