Machine Learning in Orthodontics: <i>Introducing a 3d Auto-segmentation and Auto-landmark Finder of Cbct Images To Assess Maxillary Constriction in Unilateral Impacted Canine patients</i>

Chen, Si; Wang, Li; Li, Gang; Wu, Tai-Hsien; Diachina, Shannon; Tejera, Beatriz; Kwon, Jane; Lin, Feng; Lee, Yan Ting; Xu, Tianmin; Shen, Dinggang; Ko, Ching Chang

doi:10.2319/012919-59.1

Cited by 60 publications

(46 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For mandible segmentation, Qiu et al (2018) obtained a mean DSC of 0.896 by training 3 CNNs using CBCT slices from axial, sagittal, or coronal planes and then combining the segmentation results from all 3 CNNs. For maxilla segmentation, a lower mean DSC of 0.800 ± 0.029 was found by S. Chen et al (2020), who used a learning-based multisource integration framework.…”

Section: Discussionmentioning

confidence: 92%

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: 92%

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…1,2 In orthodontics, there have also been efforts to utilize machine learning techniques in a variety of ways, one of which was the automated identification of cephalometric landmarks via artificial intelligence (AI). [3][4][5][6][7][8][9][10] Although research using three-dimensional images has attracted attention, [11][12][13] the two-dimensional cephalometric image is still important and is the most commonly utilized tool in orthodontics for diagnosis, treatment planning, and outcome prediction. 3,[14][15][16][17][18] As more attempts were made to incorporate AI into cephalometric analysis, worldwide AI challenges began in 2014 at the International Symposium on Biomedical Imaging conferences under the support of the Institute of Electrical and Electronics Engineers (IEEE ISBI).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of automated cephalometric analysis based on the latest deep learning method

Hwang¹,

Moon²,

Kim³

et al. 2021

The Angle Orthodontist

View full text Add to dashboard Cite

Objectives To compare an automated cephalometric analysis based on the latest deep learning method of automatically identifying cephalometric landmarks (AI) with previously published AI according to the test style of the worldwide AI challenges at the International Symposium on Biomedical Imaging conferences held by the Institute of Electrical and Electronics Engineers (IEEE ISBI). Materials and Methods This latest AI was developed by using a total of 1983 cephalograms as training data. In the training procedures, a modification of a contemporary deep learning method, YOLO version 3 algorithm, was applied. Test data consisted of 200 cephalograms. To follow the same test style of the AI challenges at IEEE ISBI, a human examiner manually identified the IEEE ISBI-designated 19 cephalometric landmarks, both in training and test data sets, which were used as references for comparison. Then, the latest AI and another human examiner independently detected the same landmarks in the test data set. The test results were compared by the measures that appeared at IEEE ISBI: the success detection rate (SDR) and the success classification rates (SCR). Results SDR of the latest AI in the 2-mm range was 75.5% and SCR was 81.5%. These were greater than any other previous AIs. Compared to the human examiners, AI showed a superior success classification rate in some cephalometric analysis measures. Conclusions This latest AI seems to have superior performance compared to previous AI methods. It also seems to demonstrate cephalometric analysis comparable to human examiners.

show abstract

“…This study design focused on comparing the treatment modalities rather than the canine location. Further information could be gathered in larger samples by relating the displacement timespan to a threedimensional assessment of impaction severity [18][19][20]. Future studies including also analysis of direct digital scans may also provide information regarding differences in gingival thickness that may play a role in determining the final eruption time [21][22][23][24].…”

Section: Generalizability and Interpretationmentioning

confidence: 99%

Three dimensional movement analysis of maxillary impacted canine using TADs: a pilot study

Migliorati

Cevidanes

Sinfonico³

et al. 2021

Head Face Med

View full text Add to dashboard Cite

Background The aim of the present study was to compare two different anchorage systems efficiency to disinclude impacted maxillary canines using as evaluation tool superimposed Cone Beam Computed Tomography (CBCTs). Methods The study has been conducted with two parallel groups with an allocation ratio of 1:1. Group test received treatment using as anchorage a miniscrew, control group was treated using an anchorage unit a trans palatal arch (TPA). Both groups received a calibrated traction force of 50 g. CBCT before treatment and 3 months after traction were superimposed and canine tip and root movement were evaluated in mm/month ratio. Results No differences were observed between groups for apex displacement, tip displacement and observation timespan. Twenty-two patients (12 female, 10 male, mean age:13.4 years) undergoing orthodontic treatment for impacted maxillary canines were recruited for this study. No differences were observed between groups for apex displacement, tip displacement and observation timespan. Conclusions The present pilot study provided no evidence that indirect anchorage on miniscrews could make canine disimpaction faster than anchorage on a TPA. An apex root movement of 0.4–0.8 mm per month was found, while average canine tip movement ranged between 1.08 mm and 1.96 mm per month. No miniscrews failures were observed. Trial registration The study reports the preliminary results of the randomized clinical trial registered at www.register.clinicaltrials.gov (registration number: NCT01717417).

show abstract

Machine Learning in Orthodontics: Introducing a 3d Auto-segmentation and Auto-landmark Finder of Cbct Images To Assess Maxillary Constriction in Unilateral Impacted Canine patients

Cited by 60 publications

References 18 publications

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Evaluation of automated cephalometric analysis based on the latest deep learning method

Three dimensional movement analysis of maxillary impacted canine using TADs: a pilot study

Contact Info

Product

Resources

About