Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment

Solving problems in medical image processing is either generic (being applicable to many problems) or specific (optimized for a certain task). For example, bone age assessment (BAA) on hand radiographs is a frequent but cumbersome task for radiologists. For this problem, many specific solutions have been proposed. However, general-purpose feature descriptors are used in many computer vision applications. Hence, the aim of this study is (i) to compare the five leading keypoint descriptors on BAA, and, in doing so, (ii) presenting a generic approach for a specific task. Two methods for keypoint selection were applied: sparse and dense feature points. For each type, SIFT, SURF, BRIEF, BRISK, and FREAK feature descriptors were extracted within the epiphyseal regions of interest (eROI). Classification was performed using a support vector machine. Reference data (1101 radiographs) of the University of Southern California was used for 5-fold cross-validation. The data was grouped into 30 classes representing the bone age range of 0-18 years. With a mean error of 0.605 years, dense SIFT gave best results and outperforms all published methods. The accuracy was 98.36% within the range of 2 years. Dense SIFT represents a generic method for a specific question.

[1]  Thomas Martin Deserno,et al.  Web-based bone age assessment by content-based image retrieval for case-based reasoning , 2012, International Journal of Computer Assisted Radiology and Surgery.

[2]  Sven Kreiborg,et al.  The BoneXpert Method for Automated Determination of Skeletal Maturity , 2009, IEEE Transactions on Medical Imaging.

[3]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[5]  Luo Juan,et al.  A comparison of SIFT, PCA-SIFT and SURF , 2009 .

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Pau-Choo Chung,et al.  A Fast Algorithm for Multilevel Thresholding , 2001, J. Inf. Sci. Eng..

[8]  B. Vogt,et al.  Bestimmung des Skelettalters , 2012, Der Orthopäde.

[9]  Tai-Lang Jong,et al.  A Fully Automatic Computerized Bone Age Assessment Procedure Based on Phalange Ossification Analysis , 2003 .

[10]  Whoi-Yul Kim,et al.  Computerized Bone Age Assessment Using DCT and LDA , 2007, MIRAGE.

[11]  Hendrik Simon,et al.  Bone Age Assessment Using Support Vector Machine Regression , 2013, Bildverarbeitung für die Medizin.

[12]  H. K. Huang,et al.  Computer-assisted bone age assessment: image preprocessing and epiphyseal/metaphyseal ROI extraction , 2001, IEEE Transactions on Medical Imaging.

[13]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[14]  A. Oestreich.  Hand Bone Age: A Digital Atlas of Skeletal Maturity , 2005 .

[15]  L. Bocchi,et al.  An artificial neural network architecture for skeletal age assessment , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[16]  Hong Zhang,et al.  Performance evaluation of visual SLAM using several feature extractors , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[18]  Daniel Haak,et al.  Bone age assessment meets SIFT , 2015, Medical Imaging.

[19]  James M. Tanner,et al.  Assessment of skeletal maturity and prediction of adult height:(TW3 Method) , 2001 .

[20]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[21]  Erik Maehle,et al.  A comparison of feature descriptors for visual SLAM , 2013, 2013 European Conference on Mobile Robots.

[22]  W. Greulich,et al.  Radiographic Atlas of Skeletal Development of the Hand and Wrist , 1999 .

[23]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[24]  H. K. Huang,et al.  Bone age assessment of children using a digital hand atlas , 2007, Comput. Medical Imaging Graph..

[25]  Daniel Nissman,et al.  Text-Atlas of Skeletal Age Determination: MRI of the Hand and Wrist in Children , 2013 .

[26]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[27]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[28]  James M. Tanner,et al.  Assessment of skeletal maturity and prediction of adult height : (TW2 method) , 1986 .

[29]  H. H. Thodberg,et al.  Validation and reference values of automated bone age determination for four ethnicities. , 2010, Academic radiology.

[30]  F Schiedel,et al.  [Determination of skeletal age : comparison of the methods of Greulich and Pyle and Tanner and Whitehouse]. , 2012, Der Orthopade.

[31]  H T Uytterschaut,et al.  Determination of skeletal age by histological methods. , 1985, Zeitschrift fur Morphologie und Anthropologie.

[32]  S. Govindarajulu,et al.  A Comparison of SIFT, PCA-SIFT and SURF , 2012 .

[33]  M. J. Collins,et al.  Age estimation: The state of the art in relation to the specific demands of forensic practise , 2000, International Journal of Legal Medicine.

[34]  Chih-Jen Lin,et al.  A Comparison of Methods for Multi-class Support Vector Machines , 2015 .

[35]  V. De Sanctis,et al.  Hand X-ray in pediatric endocrinology: Skeletal age assessment and beyond , 2014, Indian journal of endocrinology and metabolism.

[36]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[37]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[38]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[39]  Thomas Martin Deserno,et al.  Support Vector Machine Classification Based on Correlation Prototypes Applied to Bone Age Assessment , 2013, IEEE Journal of Biomedical and Health Informatics.

[40]  I.W. Ricketts,et al.  Classification of hand bones for bone age assessment , 1996, Proceedings of Third International Conference on Electronics, Circuits, and Systems.

[41]  João Ascenso,et al.  Evaluation of low-complexity visual feature detectors and descriptors , 2013, 2013 18th International Conference on Digital Signal Processing (DSP).