Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge

Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

[1]  J. Mcdonnell,et al.  Advancement genioplasty: a retrospective cephalometric analysis of osseous and soft tissue changes. , 1977, Journal of oral surgery.

[2]  R. M. Little,et al.  Surgical mandibular advancement: a cephalometric analysis of treatment response. , 1981, American journal of orthodontics.

[3]  Thomas Rakosi,et al.  An atlas and manual of cephalometric radiography , 1982 .

[4]  M Partinen,et al.  Women and the obstructive sleep apnea syndrome. , 1988, Chest.

[5]  R. Blanks,et al.  Cephalometric analysis for diagnosis and treatment of obstructive sleep apnea , 1988, The Laryngoscope.

[6]  A K Melnik,et al.  A cephalometric study of mandibular asymmetry in a longitudinally followed sample of growing children. , 1992, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[7]  R S Nanda,et al.  Cephalometric assessment of sagittal relationship between maxilla and mandible. , 1994, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[8]  Matti Pietikäinen,et al.  Performance evaluation of texture measures with classification based on Kullback discrimination of distributions , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[9]  U. Brandenburg,et al.  Morphology of the viscerocranium in obstructive sleep apnoea syndrome--cephalometric evaluation of 400 patients. , 1994, Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery.

[10]  P. Major,et al.  Effect of head orientation on posterior anterior cephalometric landmark identification. , 2010, The Angle orthodontist.

[11]  C. Gyldensted,et al.  Comparison of the Reliability of Craniofacial Anatomic Landmarks Based on Cephalometric Radiographs and Three-Dimensional CT Scans , 1997 .

[12]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[13]  Y J Chen,et al.  Comparison of landmark identification in traditional versus computer-aided digital cephalometry. , 2009, The Angle orthodontist.

[14]  R. Verbeeck,et al.  The clinical significance of error measurement in the interpretation of treatment results. , 2001, European journal of orthodontics.

[15]  José Tarcísio Lima Ferreira,et al.  Evaluation of the reliability of computerized profile cephalometric analysis. , 2002, Brazilian dental journal.

[16]  M. Ahmadi,et al.  Automatic localization of craniofacial landmarks for assisted cephalometry , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[17]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[18]  Mohammad Y Hajeer,et al.  Three-dimensional assessment of facial soft-tissue asymmetry before and after orthognathic surgery. , 2004, The British journal of oral & maxillofacial surgery.

[19]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[20]  Alex Jacobson,et al.  Reliability of Digital Versus Conventional Cephalometric Radiology: A Comparative Evaluation of Landmark Identification Error , 2005 .

[21]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[22]  Guoping Wang,et al.  Automated 2-D Cephalometric Analysis on X-ray Images by a Model-Based Approach , 2006, IEEE Transactions on Biomedical Engineering.

[23]  Jaime Gateno,et al.  The accuracy of cephalometric tracing superimposition. , 2003, Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons.

[24]  H. Ryoo,et al.  A comparison of craniofacial morphology in patients with and without facial asymmetry--a three-dimensional analysis with computed tomography. , 2006, International journal of oral and maxillofacial surgery.

[25]  Saeed Sadri,et al.  Discrimination of Bony Structures in Cephalograms for Automatic Landmark Detection , 2008, CSICC.

[26]  W Tharanon,et al.  3D vs. 2D cephalometric analysis comparisons with repeated measurements from 20 Thai males and 20 Thai females , 2009, Biomedical imaging and intervention journal.

[27]  Brandon Burke,et al.  Observer reliability of three-dimensional cephalometric landmark identification on cone-beam computerized tomography. , 2009, Oral surgery, oral medicine, oral pathology, oral radiology, and endodontics.

[28]  A. L. Pereira,et al.  Reproducibility of natural head position in profile photographs of children aged 8 to 12 years with and without the aid of a cephalostat , 2010 .

[29]  Predrag Vucinić,et al.  Automatic landmarking of cephalograms using active appearance models. , 2010, European journal of orthodontics.

[30]  Antonio Criminisi,et al.  Regression Forests for Efficient Anatomy Detection and Localization in CT Studies , 2010, MCV.

[31]  A. L. Pereira,et al.  Reprodutibilidade da posição natural da cabeça em fotografias de perfil de crianças de 8 a 12 anos, com e sem o auxílio de um cefalostato , 2010 .

[32]  G S Liedke,et al.  Influence of a programme of professional calibration in the variability of landmark identification using cone beam computed tomography-synthesized and conventional radiographic cephalograms. , 2010, Dento maxillo facial radiology.

[33]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[34]  Junzhou Huang,et al.  Sparse shape composition: A new framework for shape prior modeling , 2011, CVPR 2011.

[35]  Raphaël Marée,et al.  Automatic Localization of Interest Points in Zebrafish Images with Tree-Based Methods , 2011, PRIB.

[36]  A. Kaur,et al.  Cephalometric X-Ray Registration using Angular Radial Transform , 2012 .

[37]  Bostjan Likar,et al.  A Game-Theoretic Framework for Landmark-Based Image Segmentation , 2012, IEEE Transactions on Medical Imaging.

[38]  Timothy F. Cootes,et al.  Fully Automatic Segmentation of the Proximal Femur Using Random Forest Regression Voting , 2013, IEEE Transactions on Medical Imaging.

[39]  Laszlo Seres,et al.  Correction of a severe facial asymmetry with computerized planning and with the use of a rapid prototyped surgical template: a case report/technique article , 2014, Head & Face Medicine.

[40]  Guoyan Zheng,et al.  Fully Automatic Cephalometric X-Ray Landmark Detection Using Random Forest Regression and Sparse shape composition , 2014 .

[41]  Guoyan Zheng,et al.  Automatic X-ray landmark detection and shape segmentation via data-driven joint estimation of image displacements , 2014, Medical Image Anal..

[42]  Bostjan Likar,et al.  Shape Representation for Efficient Landmark-Based Segmentation in 3-D , 2014, IEEE Transactions on Medical Imaging.

[43]  Bulat Ibragimov.  Automatic Cephalometric X-Ray Landmark Detection by Applying Game Theory and Random Forests , 2014 .

[44]  G. Hamarneh,et al.  Automatic Globally-Optimal Pictorial Structures with Random Decision Forest Based Likelihoods For Cephalometric X-Ray Landmark Detection , 2014 .

[45]  Raphaël Marée,et al.  Automatic Cephalometric X-Ray Landmark Detection Challenge 2014: A machine learning tree-based approach , 2014 .

[46]  Amandeep Kaur,et al.  Automatic cephalometric landmark detection using Zernike moments and template matching , 2015, Signal Image Video Process..