Automatic Landmark Detection on Epicondyles of Distal Femur in X-Ray Images

被引:0
|
作者
Heidari, B. [1 ]
Khaksar, F. Madeh [2 ]
FitzPatrick, D. [1 ]
机构
[1] Univ Coll Dublin, Sch Elect Elect & Mech Engn, Dublin 2, Ireland
[2] Tehran Azad Univ, Biomed Engn Fac, Sci & Res Branch, Tehran, Iran
来源
4TH EUROPEAN CONFERENCE OF THE INTERNATIONAL FEDERATION FOR MEDICAL AND BIOLOGICAL ENGINEERING | 2009年 / 22卷 / 1-3期
关键词
Landmark detection; femur; digital X-Ray radiograph; edge detection; shortest path algorithm;
D O I
暂无
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Orthopaedic condition such as degenerative arthritis (e.g., osteoarthritis) can deteriorate the osteoarticular systems, causing pain and affecting activities of daily living. Treatments such as Total Knee Arthroplasty (TKA) or Spinal Arthroplasty are commonly used to relieve the pain/disability and provide mobility. This requires an accurate definition of key anatomical landmarks both for surgical operation and implant design. Utilization of the X-ray images is essential for diagnostic purposes (e.g., to identify the extent of pathological conditions), and demand for their use is ever-increasing. Moreover, radiological images are used for shape extraction/bone geometry for orthopaedic application (such as implant design or surgical/non-surgical planning) [1,2,3]. However, visual inspection/manual extraction is a subjective task and error prone, and geometrical analysis (through shape extraction), in particular, is a time consuming process [4]. In this paper we present a method to find anatomical landmarks from X-ray images, using MATLAB software (The MathWorks Inc., Natick, MA, USA) [11]. Segmentation and shortest path algorithm together with implementation of proper constraints were employed to find medial and lateral edges of the femur, enabling automatically extract parameters such as the epicondylar width of the femur. Some of the constraints applied to the program include adjusting image intensity values [10] particularly on the medial side of the knee, and separating image in to two parts, due to differences in the intensity of the image caused by patella projection. Initially, twenty series of digital X-ray images of the distal femur were used as input data to extract their anatomical landmarks, providing a means to automatically measure morphometric dimensions in different populations (by exporting the detected edges in 2-D coordinate system). The results show that the developed algorithm can detect the landmark in a robust way. Further integration of the result with Principal Component Analysis (PCA) technique is envisaged to identify the statistically important parameters required for orthopaedic planning or optimization of implants in the knee & spine area.
引用
收藏
页码:533 / 536
页数:4
相关论文
共 50 条
  • [21] An automatic algorithm for detection of infestations in X-ray images of agricultural products
    R. P. Haff
    T. C. Pearson
    Sensing and Instrumentation for Food Quality and Safety, 2007, 1 (3): : 143 - 150
  • [22] Automatic extraction of femur contours from calibrated x-ray images using statistical information
    MEM Research Center, Bern University, Bern, Switzerland
    J. Multimedia, 2007, 5 (46-54):
  • [23] Automatic extraction of femur contours from calibrated x-ray images: A Bayesian inference approach
    Dong, Xiao
    Zheng, Guoyan
    2008 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, VOLS 1-4, 2008, : 57 - +
  • [24] AUTOMATIC CLASSIFICATION OF MEDICAL X-RAY IMAGES
    Zare, Mohammad Reza
    Seng, Woo Chaw
    Mueen, Ahmed
    MALAYSIAN JOURNAL OF COMPUTER SCIENCE, 2013, 26 (01) : 9 - 22
  • [25] Automatic Tongue Tracking in X-Ray Images
    LUO Changwei
    LI Rui
    YU Lingyun
    YU Jun
    WANG Zengfu
    Chinese Journal of Electronics, 2015, 24 (04) : 767 - 771
  • [26] AUTOMATIC EVALUATION OF X-RAY AND ACOUSTIC IMAGES
    JACOBY, M
    MATERIALS EVALUATION, 1982, 40 (03) : A12 - A12
  • [27] Automatic Tongue Tracking in X-Ray Images
    Luo Changwei
    Li Rui
    Yu Lingyun
    Yu Jun
    Wang Zengfu
    CHINESE JOURNAL OF ELECTRONICS, 2015, 24 (04) : 767 - 771
  • [28] Heatmap-Based Active Shape Model for Landmark Detection in Lumbar X-ray Images
    Choi, Minho
    Jang, Jun-Su
    JOURNAL OF IMAGING INFORMATICS IN MEDICINE, 2025, 38 (01): : 291 - 308
  • [29] Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge
    Wang, Ching-Wei
    Huang, Cheng-Ta
    Hsieh, Meng-Che
    Li, Chung-Hsing
    Chang, Sheng-Wei
    Li, Wei-Cheng
    Vandaele, Remy
    Maree, Raphal
    Jodogne, Sebastien
    Geurts, Pierre
    Chen, Cheng
    Zheng, Guoyan
    Chu, Chengwen
    Mirzaalian, Hengameh
    Hamarneh, Ghassan
    Vrtovec, Tomaz
    Ibragimov, Bulat
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2015, 34 (09) : 1890 - 1900
  • [30] Automatic Detection of Spherical Gold Fiducials in KV X-Ray Images Having Scattered KV and MV X-Ray
    Yamada, M.
    Sawada, A.
    Takahashi, K.
    Mukumoto, N.
    Ueki, N.
    Miyabe, Y.
    Mizowaki, T.
    Kokubo, M.
    Hiraoka, M.
    MEDICAL PHYSICS, 2013, 40 (06)