3DentAI: U-Nets for 3D Oral Structure Reconstruction from Panoramic X-rays
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Extra-oral imaging techniques such as Panoramic X-rays (PXs) and Cone Beam Computed Tomography (CBCT) are the most preferredimaging modalities in dental clinics owing to its patient convenience during imaging as well as their ability to visualize entire teethinformation. PXs are preferred for routine clinical treatments and CBCTs for complex surgeries and implant treatments. However, PXsare limited by the lack of third dimensional spatial information whereas CBCTs inflict high radiation exposure to patient. When a PXis already available, it is beneficial to reconstruct the 3D oral structure from the PX to avoid further expenses and radiation dose. Inthis paper, we propose 3DentAI – an U-Net based deep learning framework for 3D reconstruction of oral structure from a PX image. Our framework consists of three module – a reconstruction module based on attention U-Net for estimating depth from a PX image,a realignment module for aligning the predicted flattened volume to the shape of jaw using a predefined focal trough and ray data,and lastly a refinement module based on 3D U-Net for interpolating the missing information to obtain a smooth representation of oralcavity. Synthetic PXs obtained from CBCT by ray tracing and rendering were used to train the networks without the need of paired PXand CBCT datasets. Our method, trained and tested on a diverse datasets of 600 patients, achieved superior performance to GAN-basedmodels even with low computational complexity.
Abstract
Extra-oral imaging techniques such as Panoramic X-rays (PXs) and Cone Beam Computed Tomography (CBCT) are the most preferredimaging modalities in dental clinics owing to its patient convenience during imaging as well as their ability to visualize entire teethinformation. PXs are preferred for routine clinical treatments and CBCTs for complex surgeries and implant treatments. However, PXsare limited by the lack of third dimensional spatial information whereas CBCTs inflict high radiation exposure to patient. When a PXis already available, it is beneficial to reconstruct the 3D oral structure from the PX to avoid further expenses and radiation dose. Inthis paper, we propose 3DentAI – an U-Net based deep learning framework for 3D reconstruction of oral structure from a PX image. Our framework consists of three module – a reconstruction module based on attention U-Net for estimating depth from a PX image,a realignment module for aligning the predicted flattened volume to the shape of jaw using a predefined focal trough and ray data,and lastly a refinement module based on 3D U-Net for interpolating the missing information to obtain a smooth representation of oralcavity. Synthetic PXs obtained from CBCT by ray tracing and rendering were used to train the networks without the need of paired PXand CBCT datasets. Our method, trained and tested on a diverse datasets of 600 patients, achieved superior performance to GAN-basedmodels even with low computational complexity.
참고문헌 (16)
- A. G. Farman, "Panoramic radiology: Seminars on maxillofacial imaging and interpretation" (2007), Springer
- R. Izzetti, "Basic knowledge and new advances in panoramic radiography imaging techniques : A narrative review on what dentists and radiologists should know", Applied Sciences, 11(17), pp.7858~ (2021)
- S. C. White, "Oral radiology:Principles and interpretation" (2014), Elsevier
- R. Jacobs, "Cone beam computed tomography in implant dentistry : Recommendations for clinical use", BMC Oral Health, 18, pp.88~ (2018)
- A. Al-Okshi, "Using GafChromic film to estimate the effective dose from dental cone beam CT and panoramic radiography", Dentomaxillofacial Radiology, 42, pp.20120343~ (2013)
- Y. Liang, "OralViewer : 3D Demonstration of Dental Surgeries for Patient Education with Oral Cavity Reconstruction from a 2D Panoramic X-ray", 26th International Conference on Intelligent User Interfaces, Association for Computing Machinery, pp.553~563 (2021)
- Goodfellow, "Generative adversarial nets, in Advances in Neural Information Processing Systems(NIPS)", pp.2672~2680 (2014)
- B. Mildenhall, "Computer Vision – ECCV 2020", pp.405~421 (2020), Springer International Publishing
- Y. Liang, "Medical Image Computing and Computer Assisted Intervention – MICCAI 2020", pp.400~409 (2020), Springer International Publishing
- W. Song, "Oral-3D : Reconstructing the 3D structure of oral cavity from panoramic X-ray", Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), pp.566~573 (2021)
- N. Burgos, "Iterative framework for the joint segmentation and CT synthesis of MR images : Application to MRI-only radiotherapy treatment planning", Physics in Medicine & Biology, 62(11), pp.4237~4253 (2017)
- Y. Huang, "Simultaneous superresolution and cross-modality synthesis of 3d medical images using weakly-supervised joint convolutional sparse coding", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5787~5796 (2017), IEEE
- P. Henzler, "Singleimage tomography : 3d volumes from 2d cranial x-rays", Computer Graphics Forum, 37(2), pp.377~388 (2018)
- X. Ying, "X2CT-GAN : reconstructing CT from biplanar X-rays with generative adversarial networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.10619~10628 (2019)