Automatic Articular Cartilage Segmentation Based on Pattern Recognition from Knee MRI Images

详细信息    查看全文

• 作者：Jianfei Pang ; PengYue Li ; Mingguo Qiu ; Wei Chen ; Liang Qiao
• 关键词：Knee ; Articular cartilage ; Segmentation ; MRI ; Pattern recognition
• 刊名：Journal of Digital Imaging
• 出版年：2015
• 出版时间：December 2015
• 年：2015
• 卷：28
• 期：6
• 页码：695-703
• 全文大小：3,759 KB
• 参考文献：1.Kapur T: Model Based Three Dimensional Medical Image Segmentation. Massachusetts Institute of Technology, Cambridge, 1999, pp 54鈥?0
  2.Ghosh S, Beuf O, Ries M, Lane NE, Steinbach LS, Link TM, Majumdar S: Watershed Segmentation of High Resolution Magnetic Resonance Images of Articular Cartilage of the Knee. Proceedings of the 22nd Annual International Conference of the IEEE 4, 2000, pp 3174鈥?176
  3.Folkesson J: Segmenting Articular Cartilage Automatically Using a Voxel Classification Approach. IEEE Trans Med Imaging 26:106鈥?15, 2007CrossRef PubMed
  4.Zhang K: Segmenting Human Knee Cartilage Automatically From Multi-contrast MRI Images Using Support Vector Machines and Discriminative Random Fields. IEEE International Conference on Image Processing, 2011, pp 721鈥?24
  5.Fripp J: Automatic Segmentation and Quantitative Analysis of the Articular Cartilages From Magnetic Resonance Images of the Knee. IEEE Trans Med Imaging 29:56鈥?5, 2010CrossRef
  6.Tejos C, Hall L D, Cardenas-Blanco A: Segmentation of Articular Cartilage Using Active Contours and Prior Knowledge. 26th Annual International Conference of the IEEE 1, 2004, pp 1648鈥?651
  7.Chi Y: Automatic Segmentation of Cartilage in MR Images using CDCG: Chessboard Directional Compensated GVF Snakes. Medical Information Visualisation-BioMedical Visualisation (MediVis 2006), 2006, pp 45鈥?0
  8.Canny J: A Computational Approach to Edge Detection. IEEE Trans Pattern Anal Mach Intell PAMI-8:679鈥?98, 1986CrossRef
  9.Huo YK, Wei G, Zhang YD, Wu LN: An Adaptive Threshold for the Canny Operator of Edge Detection. International Conference on Image Analysis and Signal Processing (IASP), 2010, pp 371鈥?74
  10.Harris C, Stephens M: A combined corner and edge detector. Proceedings of the 4th Alvey Vision Conference, 1988, pp 147鈥?51
  11.Protter, Murray H, Morrey Jr, Charles B: College Calculus with Analytic Geometry, 2nd edition. Addison-Wesley, LCCN, 1970, pp 520
  12.Friedman JH: Another Approach to Polyehotomous Classification, Technical report, Stanford University, From:http://鈥媤ww-stat.鈥媠tanford.鈥媏du/鈥媬jhf/鈥?/span> , 1996
  13.Rish, Irina: An empirical study of the naive Bayes classifier. IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, 2001
  14.Folkesson J, Dam E, Fogh Olsen O, Pettersen P, Christiansen C: Automatic segmentation of the articular cartilage in knee MRI using a hierarchical multi-class classification scheme. Med Image Comput Comput Assist Interv (MICCAI 2005) 327鈥?34, 2005
  
• 作者单位：Jianfei Pang (1)
  PengYue Li (1)
  Mingguo Qiu (1)
  Wei Chen (2)
  Liang Qiao (3)
  
  1. Department of Medical Image, College of Biomedical Engineering, Third Military Medical University, Chongqing, China
  2. Department of Radiology, Southwest Hospital, Third Military Medical University, Chongqing, China
  3. Department of Computer Science, College of Biomedical Engineering, Third Military Medical University, Chongqing, China
  
• 刊物类别：Medicine
• 刊物主题：Medicine & Public Health
  Imaging and Radiology
  
• 出版者：Springer New York
• ISSN：1618-727X

文摘

An automatic method for cartilage segmentation using knee MRI images is described. Three binary classifiers with integral and partial pixel features are built using the Bayesian theorem to segment the femoral cartilage, tibial cartilage and patellar cartilage separately. First, an iterative procedure based on the feedback of the number of strong edges is designed to obtain an appropriate threshold for the Canny operator and to extract the bone-cartilage interface from MRI images. Second, the different edges are identified based on certain features, which allow for different cartilage to be distinguished synchronously. The cartilage is segmented preliminarily with minimum error Bayesian classifiers that have been previously trained. According to the cartilage edge and its anatomic location, the speed of segmentation is improved. Finally, morphological operations are used to improve the primary segmentation results. The cartilage edge is smooth in the automatic segmentation results and shows good consistency with manual segmentation results. The mean Dice similarity coefficient is 0.761. Keywords Knee Articular cartilage Segmentation MRI Pattern recognition