Balder Croquet1,2, Harold Matthews1,3,4, Jules Mertens1, Yi Fan4,5,6, Nele Nauwelaers1,2, Soha Mahdi1,2, Hanne Hoskens1,2, Ahmed El Sergani7, Tianmin Xu5,6, Dirk Vandermeulen1,2, Michael Bronstein8,9, Mary Marazita10, Seth Weinberg7, Peter Claes1,2,3,4. 1. Medical Imaging Research Center, UZ Leuven, Leuven, Belgium. 2. Department of Electrical Engineering, ESAT/PSI, Katholieke Universiteit Leuven, Leuven, Belgium. 3. Department of Human Genetics, Katholieke Universiteit Leuven, Leuven, Belgium. 4. Facial Science Research Group, Murdoch Children's Research Institute, Parkville, Australia. 5. Department of Orthodontics, Peking University School and Hospital of Stomatology, Beijing, China. 6. National Engineering Laboratory for Digital and Material Technology of Stomatology, Beijing Key Laboratory of Digital Stomatology, Peking University School and Hospital of Stomatology, Beijing, China. 7. Center for Craniofacial and Dental Genetics, Department of Oral and Craniofacial Sciences, University of Pittsburgh, Pittsburgh, Pennsylvania, USA. 8. Department of Computing, Imperial College London, London, UK. 9. Institute of Computational Science, USI Lugano, Lugano, Switzerland. 10. Department of Oral and Craniofacial Sciences, Center for Craniofacial and Dental Genetics, Department of Human Genetics University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
Abstract
OBJECTIVES: To develop and evaluate a geometric deep-learning network to automatically place seven palatal landmarks on digitized maxillary dental casts. SETTINGS AND SAMPLE POPULATION: The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts. MATERIALS AND METHODS: A geometric deep-learning network was developed to hierarchically learn features from point-clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks. RESULTS: Repeat-measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size. CONCLUSIONS: The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.
OBJECTIVES: To develop and evaluate a geometric deep-learning network to automatically place seven palatal landmarks on digitized maxillary dental casts. SETTINGS AND SAMPLE POPULATION: The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts. MATERIALS AND METHODS: A geometric deep-learning network was developed to hierarchically learn features from point-clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks. RESULTS: Repeat-measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size. CONCLUSIONS: The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.
Authors: Roberta Lione; Lorenzo Franchi; Luis Tomas Huanca Ghislanzoni; Jasmina Primozic; Marco Buongiorno; Paola Cozza Journal: Eur J Orthod Date: 2014-07-12 Impact factor: 3.075
Authors: Julie D White; Alejandra Ortega-Castrillón; Harold Matthews; Arslan A Zaidi; Omid Ekrami; Jonatan Snyders; Yi Fan; Tony Penington; Stefan Van Dongen; Mark D Shriver; Peter Claes Journal: Sci Rep Date: 2019-04-15 Impact factor: 4.379