Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning

This paper presents a new approach to automatic three-dimensional (3D) cephalometric annotation for diagnosis, surgical planning, and treatment evaluation. There has long been considerable demand for automated cephalometric landmarking, since manual landmarking requires considerable time and experience as well as objectivity and scrupulous error avoidance. Due to the inherent limitation of two-dimensional (2D) cephalometry and the 3D nature of surgical simulation, there is a trend away from current 2D to 3D cephalometry. Deep learning approaches to cephalometric landmarking seem highly promising, but there exist serious difficulties in handling high dimensional 3D CT data, dimension referring to the number of voxels. To address this issue of dimensionality, this paper proposes a shadowed 2D image-based machine learning method which uses multiple shadowed 2D images with various lighting and view directions to capture 3D geometric cues. The proposed method using VGG-net was trained and tested using 2700 shadowed 2D images and corresponding manual landmarkings. Test data evaluation shows that our method achieved an average point-to-point error of 1.5 mm for the seven major landmarks.

[1]  P Hammond,et al.  An evaluation of active shape models for the automatic identification of cephalometric landmarks. , 2000, European journal of orthodontics.

[2]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[3]  John K. Tsotsos,et al.  Knowledge-based landmarking of cephalograms. , 1986, Computers and biomedical research, an international journal.

[4]  P. Corre,et al.  Three-dimensional architectural and structural analysis--a transition in concept and design from Delaire's cephalometric analysis. , 2014, International journal of oral and maxillofacial surgery.

[5]  J M Coggins,et al.  Automatic computerized radiographic identification of cephalometric landmarks. , 1998, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[6]  Giovanni Montana,et al.  Deep neural networks for anatomical brain segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  Hongbin Zha,et al.  Anatomical Structure Sketcher for Cephalograms by Bimodal Deep Learning , 2013, BMVC.

[8]  Rasmus Larsen,et al.  An Ensemble of 2D Convolutional Neural Networks for Tumor Segmentation , 2015, SCIA.

[9]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Dinggang Shen,et al.  Deep Learning Based Imaging Data Completion for Improved Brain Disease Diagnosis , 2014, MICCAI.

[11]  Gert Cauwenberghs,et al.  Robust cephalometric landmark identification using support vector machines , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

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

[13]  Daniela Giordano,et al.  Automatic Landmarking of Cephalograms by Cellular Neural Networks , 2005, AIME.

[14]  S T Nugent,et al.  Automatic landmarking of cephalograms. , 1989, Computers and biomedical research, an international journal.

[15]  Rajiv Balachandran,et al.  A knowledge-based algorithm for automatic detection of cephalometric landmarks on CBCT images , 2015, International Journal of Computer Assisted Radiology and Surgery.

[16]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[17]  Maher A. Sid-Ahmed,et al.  An image processing system for locating craniofacial landmarks , 1994, IEEE Trans. Medical Imaging.

[18]  Dorin Comaniciu,et al.  Robust Multi-scale Anatomical Landmark Detection in Incomplete 3D-CT Data , 2017, MICCAI.

[19]  Ching-Wei Wang,et al.  Fully Automatic System for Accurate Localisation and Analysis of Cephalometric Landmarks in Lateral Cephalograms , 2016, Scientific Reports.

[20]  Mohammad A. Dabbah,et al.  Detection and location of 127 anatomical landmarks in diverse CT datasets , 2014, Medical Imaging.

[21]  Marc Kachelrieß,et al.  Empirical beam hardening correction (EBHC) for CT. , 2010, Medical physics.

[22]  Marcelo Romero,et al.  Automatic 3‐dimensional cephalometric landmarking based on active shape models in related projections , 2018, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[23]  Rajiv Balachandran,et al.  Accuracy of 3D cephalometric measurements based on an automatic knowledge-based landmark detection algorithm , 2016, International Journal of Computer Assisted Radiology and Surgery.

[24]  Giuseppe Baselli,et al.  Computer-aided cephalometric landmark annotation for CBCT data , 2016, International Journal of Computer Assisted Radiology and Surgery.

[25]  Bulat Ibragimov,et al.  Fully automated quantitative cephalometry using convolutional neural networks , 2017, Journal of medical imaging.

[26]  Victor Ciesielski,et al.  Landmark Detection for Cephalometric Radiology Images Using Pulse Coupled , 2002, IC-AI.

[27]  M Oshagh,et al.  Accuracy of computerized automatic identification of cephalometric landmarks by a designed software. , 2013, Dento maxillo facial radiology.

[28]  A. Barron.  Approximation and Estimation Bounds for Artificial Neural Networks , 1991, COLT '91.

[29]  Ronald M. Summers,et al.  A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations , 2014, MICCAI.