Oral-3D: Reconstructing the 3D Structure of Oral Cavity from Panoramic X-ray

Song, Weinan; Liu, Yuan; Jiang, Yang; Wang, Kun; He, Lei

doi:10.1609/aaai.v35i1.16135

Cited by 21 publications

(18 citation statements)

References 20 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tooth Feature Representation. Deep learning-based dental tasks using the intraoral scan model include tooth segmentation (Cui et al 2021;Qiu et al 2022;Cui et al 2022), tooth classification (Ma et al 2020), tooth landmark/axis detection (Wei et al 2022;Yf et al 2022), tooth alignment target prediction (Wei et al 2020;Yang et al 2020;Wang et al 2022), and so on (Song et al 2021;Zhang et al 2022). Most of them first take the segmented point cloud of an intraoral scan model as input and then utilize the point cloud feature extraction network (Qi et al 2017a,b;Wu, Qi, and Fuxin 2019;Wang et al 2019) to extract tooth point cloud features for downstream works.…”

Section: Related Workmentioning

confidence: 99%

Collaborative Tooth Motion Diffusion Model in Digital Orthodontics

Fan,

Wei,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

Tooth motion generation is an essential task in digital orthodontic treatment for precise and quick dental healthcare, which aims to generate the whole intermediate tooth motion process given the initial pathological and target ideal tooth alignments. Most prior works for multi-agent motion planning problems usually result in complex solutions. Moreover, the occlusal relationship between upper and lower teeth is often overlooked. In this paper, we propose a collaborative tooth motion diffusion model. The critical insight is to remodel the problem as a diffusion process. In this sense, we model the whole tooth motion distribution with a diffusion model and transform the planning problem into a sampling process from this distribution. We design a tooth latent representation to provide accurate conditional guides consisting of two key components: the tooth frame represents the position and posture, and the tooth latent shape code represents the geometric morphology. Subsequently, we present a collaborative diffusion model to learn the multi-tooth motion distribution based on inter-tooth and occlusal constraints, which are implemented by graph structure and new loss functions, respectively. Extensive qualitative and quantitative experiments demonstrate the superiority of our framework in the application of orthodontics compared with state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Collaborative Tooth Motion Diffusion Model in Digital Orthodontics

Fan,

Wei,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Henzler (Henzler et al 2018) uses real cranial X-ray images acquired in a controlled setting to recover the 3D bone structure. Song (Song et al 2020) uses a single Panoramic X-ray with a photo of the patient's mouth to reconstruct the 3D structure. As clinical evidence supports that bone suppression on radiograph can improve diagnostic accuracy (Laskey 1996), Li (Li et al 2020) proposes to achieve bone suppression by learning a bone segmentation network based on DRRs, and apply the network on real radiographs with handcrafted post-processes.…”

Section: Related Workmentioning

confidence: 99%

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

Cheng

Liao

Wong

et al. 2021

AAAI

View full text Add to dashboard Cite

A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane. Hence, radiograph analysis naturally requires physicians to relate their prior knowledge about 3D human anatomy to 2D radiographs. Synthesizing novel radiographic views in a small range can assist physicians in interpreting anatomy more reliably; however, radiograph view synthesis is heavily ill-posed, lacking in paired data, and lacking in differentiable operations to leverage learning-based approaches. To address these problems, we use Computed Tomography (CT) for radiograph simulation and design a differentiable projection algorithm, which enables us to achieve geometrically consistent transformations between the radiography and CT domains. Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs. To the best of our knowledge, this is the first work on radiograph view synthesis. We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without requiring groundtruth bone labels.

show abstract

“…Previous studies (Liang et al 2020;Song et al 2021) used conventional encoder-decoder models for 3D reconstruction from PX data. Those models are trained with synthetic PX data generated from CBCT, instead of real-world PX.…”

Section: Introductionmentioning

confidence: 99%

NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographs

Park,

Kim,

Kwon

et al. 2024

AAAI

View full text Add to dashboard Cite

Panoramic radiography (Panoramic X-ray, PX) is a widely used imaging modality for dental examination. However, PX only provides a flattened 2D image, lacking in a 3D view of the oral structure. In this paper, we propose NeBLa (Neural Beer-Lambert) to estimate 3D oral structures from real-world PX. NeBLa tackles full 3D reconstruction for varying subjects (patients) where each reconstruction is based only on a single panoramic image. We create an intermediate representation called simulated PX (SimPX) from 3D Cone-beam computed tomography (CBCT) data based on the Beer-Lambert law of X-ray rendering and rotational principles of PX imaging. SimPX aims at not only truthfully simulating PX, but also facilitates the reverting process back to 3D data. We propose a novel neural model based on ray tracing which exploits both global and local input features to convert SimPX to 3D output. At inference, a real PX image is translated to a SimPX-style image with semantic regularization, and the translated image is processed by generation module to produce high-quality outputs. Experiments show that NeBLa outperforms prior state-of-the-art in reconstruction tasks both quantitatively and qualitatively. Unlike prior methods, NeBLa does not require any prior information such as the shape of dental arches, nor the matched PX-CBCT dataset for training, which is difficult to obtain in clinical practice. Our code is available at https://github.com/sihwa-park/nebla.

show abstract

Oral-3D: Reconstructing the 3D Structure of Oral Cavity from Panoramic X-ray

Cited by 21 publications

References 20 publications

Collaborative Tooth Motion Diffusion Model in Digital Orthodontics

Collaborative Tooth Motion Diffusion Model in Digital Orthodontics

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographs

Contact Info

Product

Resources

About