Qingchuan Ma1, Etsuko Kobayashi2, Bowen Fan3, Keiichi Nakagawa3, Ichiro Sakuma3, Ken Masamune2, Hideyuki Suenaga1. 1. Department of Oral-Maxillofacial Surgery and Orthodontics, The University of Tokyo Hospital, Tokyo, Japan. 2. Institute of Advanced BioMedical Engineering and Science, Tokyo Women's Medical University, Tokyo, Japan. 3. Department of Precision Engineering, The University of Tokyo, Tokyo, Japan.
Abstract
BACKGROUND: Manual landmarking is a time consuming and highly professional work. Although some algorithm-based landmarking methods have been proposed, they lack flexibility and may be susceptible to data diversity. METHODS: The CT images from 66 patients who underwent oral and maxillofacial surgery (OMS) were landmarked manually in MIMICS. Then the CT slices were exported as images for recreating the 3D volume. The coordinate data of landmarks were further processed in Matlab using a principal component analysis (PCA) method. A patch-based deep neural network model with a three-layer convolutional neural network (CNN) was trained to obtain landmarks from CT images. RESULTS: The evaluating experiment showed that this CNN model could automatically finish landmarking in an average processing time of 37.871 seconds with an average accuracy of 5.785 mm. CONCLUSION: This study shows a promising potential to relieve the workload of the surgeon and reduces the dependence on human experience for OMS landmarking.
BACKGROUND: Manual landmarking is a time consuming and highly professional work. Although some algorithm-based landmarking methods have been proposed, they lack flexibility and may be susceptible to data diversity. METHODS: The CT images from 66 patients who underwent oral and maxillofacial surgery (OMS) were landmarked manually in MIMICS. Then the CT slices were exported as images for recreating the 3D volume. The coordinate data of landmarks were further processed in Matlab using a principal component analysis (PCA) method. A patch-based deep neural network model with a three-layer convolutional neural network (CNN) was trained to obtain landmarks from CT images. RESULTS: The evaluating experiment showed that this CNN model could automatically finish landmarking in an average processing time of 37.871 seconds with an average accuracy of 5.785 mm. CONCLUSION: This study shows a promising potential to relieve the workload of the surgeon and reduces the dependence on human experience for OMS landmarking.
Authors: Samar Adel; Abbas Zaher; Nadia El Harouni; Adith Venugopal; Pratik Premjani; Nikhilesh Vaid Journal: Biomed Res Int Date: 2021-06-16 Impact factor: 3.411
Authors: Yashodhan M Bichu; Ismaeel Hansa; Aditi Y Bichu; Pratik Premjani; Carlos Flores-Mir; Nikhilesh R Vaid Journal: Prog Orthod Date: 2021-07-05 Impact factor: 2.750