Abhishek Gupta1,2, Om Prakash Kharbanda3, Viren Sardana4, Rajiv Balachandran5, Harish Kumar Sardana6,7. 1. Academy of Scientific and Innovative Research (AcSIR), New Delhi, India. abhishekgupta10@yahoo.co.in. 2. CSIR-Central Scientific Instruments Organisation, Chandigarh, 160030, India. abhishekgupta10@yahoo.co.in. 3. Division of Orthodontics and Dentofacial Deformities, Centre for Dental Education and Research, All India Institute of Medical Sciences, New Delhi, 110029, India. opk15@hotmail.com. 4. CSIR-Central Scientific Instruments Organisation, Chandigarh, 160030, India. sardana.viren@gmail.com. 5. Division of Orthodontics and Dentofacial Deformities, Centre for Dental Education and Research, All India Institute of Medical Sciences, New Delhi, 110029, India. drrajivmds@gmail.com. 6. Academy of Scientific and Innovative Research (AcSIR), New Delhi, India. hk_sardana@csio.res.in. 7. CSIR-Central Scientific Instruments Organisation, Chandigarh, 160030, India. hk_sardana@csio.res.in.
Abstract
PURPOSE: Cone-beam computed tomography (CBCT) is now an established component for 3D evaluation and treatment planning of patients with severe malocclusion and craniofacial deformities. Precision landmark plotting on 3D images for cephalometric analysis requires considerable effort and time, notwithstanding the experience of landmark plotting, which raises a need to automate the process of 3D landmark plotting. Therefore, knowledge-based algorithm for automatic detection of landmarks on 3D CBCT images has been developed and tested. METHODS: A knowledge-based algorithm was developed in the MATLAB programming environment to detect 20 cephalometric landmarks. For the automatic detection, landmarks that are physically adjacent to each other were clustered into groups and were extracted through a volume of interest (VOI). Relevant contours were detected in the VOI and landmarks were detected using corresponding mathematical entities. The standard data for validation were generated using manual marking carried out by three orthodontists on a dataset of 30 CBCT images as a reference. RESULTS: Inter-observer ICC for manual landmark identification was found to be excellent (>0.9) amongst three observers. Euclidean distances between the coordinates of manual identification and automatic detection through the proposed algorithm of each landmark were calculated. The overall mean error for the proposed method was 2.01 mm with a standard deviation of 1.23 mm for all the 20 landmarks. The overall landmark detection accuracy was recorded at 64.67, 82.67 and 90.33 % within 2-, 3- and 4-mm error range of manual marking, respectively. CONCLUSIONS: The proposed knowledge-based algorithm for automatic detection of landmarks on 3D images was able to achieve relatively accurate results than the currently available algorithm.
PURPOSE: Cone-beam computed tomography (CBCT) is now an established component for 3D evaluation and treatment planning of patients with severe malocclusion and craniofacial deformities. Precision landmark plotting on 3D images for cephalometric analysis requires considerable effort and time, notwithstanding the experience of landmark plotting, which raises a need to automate the process of 3D landmark plotting. Therefore, knowledge-based algorithm for automatic detection of landmarks on 3D CBCT images has been developed and tested. METHODS: A knowledge-based algorithm was developed in the MATLAB programming environment to detect 20 cephalometric landmarks. For the automatic detection, landmarks that are physically adjacent to each other were clustered into groups and were extracted through a volume of interest (VOI). Relevant contours were detected in the VOI and landmarks were detected using corresponding mathematical entities. The standard data for validation were generated using manual marking carried out by three orthodontists on a dataset of 30 CBCT images as a reference. RESULTS: Inter-observer ICC for manual landmark identification was found to be excellent (>0.9) amongst three observers. Euclidean distances between the coordinates of manual identification and automatic detection through the proposed algorithm of each landmark were calculated. The overall mean error for the proposed method was 2.01 mm with a standard deviation of 1.23 mm for all the 20 landmarks. The overall landmark detection accuracy was recorded at 64.67, 82.67 and 90.33 % within 2-, 3- and 4-mm error range of manual marking, respectively. CONCLUSIONS: The proposed knowledge-based algorithm for automatic detection of landmarks on 3D images was able to achieve relatively accurate results than the currently available algorithm.
Authors: Lucia H C Cevidanes; Ana Emilia Figueiredo Oliveira; Dan Grauer; Martin Styner; William R Proffit Journal: Semin Orthod Date: 2011-03-01 Impact factor: 0.970
Authors: Manuel O Lagravère; Jillian M Gordon; Ines H Guedes; Carlos Flores-Mir; Jason P Carey; Giseon Heo; Paul W Major Journal: Angle Orthod Date: 2009-11 Impact factor: 2.079
Authors: Chunfeng Lian; Fan Wang; Hannah H Deng; Li Wang; Deqiang Xiao; Tianshu Kuang; Hung-Ying Lin; Jaime Gateno; Steve G F Shen; Pew-Thian Yap; James J Xia; Dinggang Shen Journal: Med Image Comput Comput Assist Interv Date: 2020-09-29
Authors: Neslisah Torosdagli; Denise K Liberton; Payal Verma; Murat Sincan; Janice S Lee; Ulas Bagci Journal: IEEE Trans Med Imaging Date: 2018-10-12 Impact factor: 10.048