Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning

Lee, S.; Woo, Seongyoun; Yu, Jiachen; Seo, Jin Keun; Lee, J.; Lee, C.

doi:10.1109/access.2020.2975826

Cited by 68 publications

(40 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For maxilla segmentation, a lower mean DSC of 0.800 ± 0.029 was found by S. , who used a learning-based multisource integration framework. For teeth segmentation, Lee et al (2020) applied a multiphase strategy to train a U-Net-based architecture, which resulted in DSCs ranging from 0.910 to 0.918. Furthermore, Cui et al (2019) employed a 2-stage network consisting of a tooth edge map extraction network and a region proposal network and reported a mean DSC of 0.926.…”

Section: Discussionmentioning

confidence: 99%

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

et al. 2021

View full text Add to dashboard Cite

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network–based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

show abstract

Section: Discussionmentioning

confidence: 99%

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The ultimate goal is the development and implementation of similar AI-driven segmentation tools in 3D, as CBCT is the most commonly used imaging modality in the virtual preoperative treatment planning of various dental and maxillofacial procedures. Accurate detection, labeling, and segmentation of anatomical structures on CBCT will always be the first and most challenging step in this process [34][35][36]. CNNs can supplement the clinicians in this very time-consuming and tedious task.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence (AI)-Driven Molar Angulation Measurements to Predict Third Molar Eruption on Panoramic Radiographs

Vranckx

Gerven²,

Willems³

et al. 2020

IJERPH

View full text Add to dashboard Cite

The purpose of the presented Artificial Intelligence (AI)-tool was to automatically segment the mandibular molars on panoramic radiographs and extract the molar orientations in order to predict the third molars’ eruption potential. In total, 838 panoramic radiographs were used for training (n = 588) and validation (n = 250) of the network. A fully convolutional neural network with ResNet-101 backbone jointly predicted the molar segmentation maps and an estimate of the orientation lines, which was then iteratively refined by regression on the mesial and distal sides of the segmentation contours. Accuracy was quantified as the fraction of correct angulations (with predefined error intervals) compared to human reference measurements. Performance differences between the network and reference measurements were visually assessed using Bland−Altman plots. The quantitative analysis for automatic molar segmentation resulted in mean IoUs approximating 90%. Mean Hausdorff distances were lowest for first and second molars. The network angulation measurements reached accuracies of 79.7% [−2.5°; 2.5°] and 98.1% [−5°; 5°], combined with a clinically significant reduction in user-time of >53%. In conclusion, this study validated a new and unique AI-driven tool for fast, accurate, and consistent automated measurement of molar angulations on panoramic radiographs. Complementing the dental practitioner with accurate AI-tools will facilitate and optimize dental care and synergistically lead to ever-increasing diagnostic accuracies.

show abstract

“…Thanks to the above mentioned model, the model converges faster and empty voxels are handled. Minnema et al [15] and Lee et al [26] obtained better results (0.917 vs 0.87 DSC) segmenting teeth from CBCT scan, with more training data and more scans (precisely 73) with metal artifacts. Nevertheless the MS-D network [15] achieved the same outcomes with less training parameters.…”

Section: Segmentation 2dmentioning

confidence: 98%

“…Output of the network has 5 classes: bone, tooth, lesion, restorative materials and background. Lee et al [26] similarly to previous authors choose U-Net architecture as a method for tooth segmentation from a CBCT scan. They elaborated a multi-phase training method with each phase increasing the area around the teeth.…”

Section: Segmentation 2dmentioning

confidence: 99%

Machine learning methods as an aid in planning orthodontic treatment on the example of Cone-Beam Computed Tomography analysis: a literature review

Płotka¹,

Wlodarczyk²,

Szczerba³

et al. 2021

J Educ Health Sport

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) are used in many areas of computer vision, such as object tracking and recognition, security, military, and biomedical image analysis. In this work, we describe the current methods, the architectures of deep convolutional neural networks used in CBCT. Literature from 2000-2020 from the PubMed database, Google Scholar, was analyzed. Account has been taken of publications in English that describe architectures of deep convolutional neural networks used in CBCT. The results of the reviewed studies indicate that deep learning methods employed in orthodontics can be far superior in comparison to other high-performing algorithms.

show abstract

Automated CNN-Based Tooth Segmentation in Cone-Beam CT for Dental Implant Planning

Cited by 68 publications

References 34 publications

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Artificial Intelligence (AI)-Driven Molar Angulation Measurements to Predict Third Molar Eruption on Panoramic Radiographs

Machine learning methods as an aid in planning orthodontic treatment on the example of Cone-Beam Computed Tomography analysis: a literature review

Contact Info

Product

Resources

About