Loading [MathJax]/extensions/MathZoom.js
Automatic 3D Registration of Dental CBCT and Face Scan Data Using 2D Projection Images | IEEE Journals & Magazine | IEEE Xplore

Automatic 3D Registration of Dental CBCT and Face Scan Data Using 2D Projection Images


This paper proposes a fully automatic registration method for dental cone-beam computed tomography (CBCT) and face scan data. The proposed method adopts a machine learnin...

Abstract:

This paper presents a fully automatic registration method of dental cone-beam computed tomography (CBCT) and face scan data. Difficulties in accurately merging facial sca...Show More

Abstract:

This paper presents a fully automatic registration method of dental cone-beam computed tomography (CBCT) and face scan data. Difficulties in accurately merging facial scans and CBCT images arise from the different image acquisition methods and limited area of correspondence between the two facial surfaces. In addition, it is difficult to use machine learning techniques because they use face-related 3D medical data with radiation exposure, which are difficult to obtain for training. The proposed method addresses these problems by reusing an existing machine-learning-based 2D landmark detection algorithm in an open-source library and developing a novel mathematical algorithm that identifies paired 3D landmarks from knowledge of the corresponding 2D landmarks. A main contribution of this study is that the proposed method does not require annotated training data of facial landmarks because it uses a pre-trained facial landmark detection algorithm that is known to be robust and generalized to various 2D face image models. Note that this reduces a 3D landmark detection problem to a 2D problem of identifying the corresponding landmarks on two 2D projection images generated from two different projection angles. Here, the 3D landmarks for registration were selected from the sub-surfaces with the least geometric change under the CBCT and face scan environments. For the final fine-tuning of the registration, the Iterative Closest Point method was applied, which utilizes geometrical information around the 3D landmarks. The proposed method achieved an averaged mean surface distance error of 0.74 mm for three pairs of CBCT and face scan datasets.
This paper proposes a fully automatic registration method for dental cone-beam computed tomography (CBCT) and face scan data. The proposed method adopts a machine learnin...
Published in: IEEE Access ( Volume: 12)
Page(s): 101289 - 101298
Date of Publication: 22 July 2024
Electronic ISSN: 2169-3536

Funding Agency:

Author image of Hyoung Suk Park
National Institute for Mathematical Sciences, Daejeon, Republic of Korea
Hyoung Suk Park received the B.S. degree in mathematics and biomedical engineering and the Ph.D. degree in mathematics from Yonsei University, South Korea, in 2010 and 2015, respectively. From 2015 to 2016, he was a Postdoctoral Researcher with Yonsei University. He is currently a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), South Korea. His research interests include medical imaging and...Show More
Hyoung Suk Park received the B.S. degree in mathematics and biomedical engineering and the Ph.D. degree in mathematics from Yonsei University, South Korea, in 2010 and 2015, respectively. From 2015 to 2016, he was a Postdoctoral Researcher with Yonsei University. He is currently a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), South Korea. His research interests include medical imaging and...View more
Author image of Chang Min Hyun
Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
Chang Min Hyun received the Ph.D. degree in applied mathematics from Yonsei University, Seoul, South Korea, in 2021. From 2021 to 2023, he was a Postdoctoral Researcher with the School of Mathematics and Computing, Science College, Yonsei University. In 2023, he was a Postdoctoral Researcher with the Department of Orthodontics, College of Dentistry, Yonsei University. Since 2023, he has been a Postdoctoral Research Fellow...Show More
Chang Min Hyun received the Ph.D. degree in applied mathematics from Yonsei University, Seoul, South Korea, in 2021. From 2021 to 2023, he was a Postdoctoral Researcher with the School of Mathematics and Computing, Science College, Yonsei University. In 2023, he was a Postdoctoral Researcher with the Department of Orthodontics, College of Dentistry, Yonsei University. Since 2023, he has been a Postdoctoral Research Fellow...View more
Author image of Sang-Hwy Lee
Department of Oral and Maxillofacial Surgery, Oral Science Research Center, College of Dentistry, Yonsei University, Seoul, Republic of Korea
Sang-Hwy Lee received the Ph.D. degree from Yonsei University, South Korea, in 1996. He has been a Professor with the Department of Oral and Maxillofacial Surgery, Yonsei University, since 2002. He is currently a Dentist and Maxillofacial Surgeon. His research interests the deep learning- and computer-assisted orthognathic surgery, craniofacial growth, dentofacial deformity, and cleft lip and palate.
Sang-Hwy Lee received the Ph.D. degree from Yonsei University, South Korea, in 1996. He has been a Professor with the Department of Oral and Maxillofacial Surgery, Yonsei University, since 2002. He is currently a Dentist and Maxillofacial Surgeon. His research interests the deep learning- and computer-assisted orthognathic surgery, craniofacial growth, dentofacial deformity, and cleft lip and palate.View more
Author image of Jin Keun Seo
School of Mathematics and Computing, Yonsei University, Seoul, Republic of Korea
Jin Keun Seo received the Ph.D. degree from the University of Minnesota, in 1991. He has been a Professor with Yonsei University, South Korea, since 1995. Recently, he wrote books titled Nonlinear Inverse Problems in Imaging (Wiley Press) and Deep Learning and Medical Applications (Springer). His research interests include inverse problems, mathematical modeling, image processing, partial differential equations, harmonic ...Show More
Jin Keun Seo received the Ph.D. degree from the University of Minnesota, in 1991. He has been a Professor with Yonsei University, South Korea, since 1995. Recently, he wrote books titled Nonlinear Inverse Problems in Imaging (Wiley Press) and Deep Learning and Medical Applications (Springer). His research interests include inverse problems, mathematical modeling, image processing, partial differential equations, harmonic ...View more
Author image of Kiwan Jeon
National Institute for Mathematical Sciences, Daejeon, Republic of Korea
Kiwan Jeon received the Ph.D. degree from Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2010. Since 2011, he has been a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), Daejeon. His research interests include medical imaging, numerical analysis, scientific computing, and software developments.
Kiwan Jeon received the Ph.D. degree from Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2010. Since 2011, he has been a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), Daejeon. His research interests include medical imaging, numerical analysis, scientific computing, and software developments.View more

Author image of Hyoung Suk Park
National Institute for Mathematical Sciences, Daejeon, Republic of Korea
Hyoung Suk Park received the B.S. degree in mathematics and biomedical engineering and the Ph.D. degree in mathematics from Yonsei University, South Korea, in 2010 and 2015, respectively. From 2015 to 2016, he was a Postdoctoral Researcher with Yonsei University. He is currently a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), South Korea. His research interests include medical imaging and deep learning.
Hyoung Suk Park received the B.S. degree in mathematics and biomedical engineering and the Ph.D. degree in mathematics from Yonsei University, South Korea, in 2010 and 2015, respectively. From 2015 to 2016, he was a Postdoctoral Researcher with Yonsei University. He is currently a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), South Korea. His research interests include medical imaging and deep learning.View more
Author image of Chang Min Hyun
Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
Chang Min Hyun received the Ph.D. degree in applied mathematics from Yonsei University, Seoul, South Korea, in 2021. From 2021 to 2023, he was a Postdoctoral Researcher with the School of Mathematics and Computing, Science College, Yonsei University. In 2023, he was a Postdoctoral Researcher with the Department of Orthodontics, College of Dentistry, Yonsei University. Since 2023, he has been a Postdoctoral Research Fellow with the Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA. His research interests include computational mathematics, medical image analysis, and bio-signal analysis.
Chang Min Hyun received the Ph.D. degree in applied mathematics from Yonsei University, Seoul, South Korea, in 2021. From 2021 to 2023, he was a Postdoctoral Researcher with the School of Mathematics and Computing, Science College, Yonsei University. In 2023, he was a Postdoctoral Researcher with the Department of Orthodontics, College of Dentistry, Yonsei University. Since 2023, he has been a Postdoctoral Research Fellow with the Department of Radiology, Perelman School of Medicine, University of Pennsylvania, USA. His research interests include computational mathematics, medical image analysis, and bio-signal analysis.View more
Author image of Sang-Hwy Lee
Department of Oral and Maxillofacial Surgery, Oral Science Research Center, College of Dentistry, Yonsei University, Seoul, Republic of Korea
Sang-Hwy Lee received the Ph.D. degree from Yonsei University, South Korea, in 1996. He has been a Professor with the Department of Oral and Maxillofacial Surgery, Yonsei University, since 2002. He is currently a Dentist and Maxillofacial Surgeon. His research interests the deep learning- and computer-assisted orthognathic surgery, craniofacial growth, dentofacial deformity, and cleft lip and palate.
Sang-Hwy Lee received the Ph.D. degree from Yonsei University, South Korea, in 1996. He has been a Professor with the Department of Oral and Maxillofacial Surgery, Yonsei University, since 2002. He is currently a Dentist and Maxillofacial Surgeon. His research interests the deep learning- and computer-assisted orthognathic surgery, craniofacial growth, dentofacial deformity, and cleft lip and palate.View more
Author image of Jin Keun Seo
School of Mathematics and Computing, Yonsei University, Seoul, Republic of Korea
Jin Keun Seo received the Ph.D. degree from the University of Minnesota, in 1991. He has been a Professor with Yonsei University, South Korea, since 1995. Recently, he wrote books titled Nonlinear Inverse Problems in Imaging (Wiley Press) and Deep Learning and Medical Applications (Springer). His research interests include inverse problems, mathematical modeling, image processing, partial differential equations, harmonic analysis, and deep learning for medical image analysis.
Jin Keun Seo received the Ph.D. degree from the University of Minnesota, in 1991. He has been a Professor with Yonsei University, South Korea, since 1995. Recently, he wrote books titled Nonlinear Inverse Problems in Imaging (Wiley Press) and Deep Learning and Medical Applications (Springer). His research interests include inverse problems, mathematical modeling, image processing, partial differential equations, harmonic analysis, and deep learning for medical image analysis.View more
Author image of Kiwan Jeon
National Institute for Mathematical Sciences, Daejeon, Republic of Korea
Kiwan Jeon received the Ph.D. degree from Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2010. Since 2011, he has been a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), Daejeon. His research interests include medical imaging, numerical analysis, scientific computing, and software developments.
Kiwan Jeon received the Ph.D. degree from Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2010. Since 2011, he has been a Senior Researcher with the National Institute for Mathematical Sciences (NIMS), Daejeon. His research interests include medical imaging, numerical analysis, scientific computing, and software developments.View more

References

References is not available for this document.