This study was supported by Seoul National University Bundang Hospital (SNUBH) Research Fund. (Grant no. 14-2019-0023).

This retrospective study was reviewed and approved by the Institutional Review Board of Seoul National University Bundang Hospital (B-2205-759-101) and complied with the principles of the Declaration of Helsinki. Digital Imaging and Communications in Medicine (DICOM) files from CBCT and DDI in Standard Tessellation Language (STL) format from the dental cast were utilized in the study. The need for informed consent was waived due to the retrospective nature of the study.
1. CBCT and Digital Dental Images (DDI) acquisition
<ol>
	<li>Select patients based on the following inclusion criteria: skeletal Class III malocclusion; bimaxillary surgery via computer-aided planning; and orthodontic treatment with fixed edgewise appliances.</li>
	<li>Exclude patients with craniofacial syndromes, cleft lip/palate, or missing maxillary first molars or right central incisor.</li>
	<li>Obtain CBCT scans with a field of view of 200 mm x 180 mm, a voxel size of 0.2 mm, and exposure conditions of 80 kVp, 15 mA, and 10.8 s. Ensure that patients are in an upright position with their teeth in maximum intercuspation. Save the scans as Digital Imaging and Communications in Medicine (DICOM) data files.</li>
	<li>Acquire DDIs from dental stone casts or direct intraoral scanning and save them in the Standard Tessellation Language (STL) format as separate maxillary and mandibular dentition.</li>
</ol>
2. AI-based Registration Protocol (ABR)
<ol>
	<li>CBCT reorientation and digitization
	<ol>
		<li>Open the software and click the Load DICOM File button to import CBCT DICOM files into the software.</li>
		<li>Select any one of the DICOM files in the DICOM data folder and click open. 
		NOTE: When DICOM files are loaded, the software automatically reconstructs them into a CBCT craniofacial volume.</li>
		<li>Click on&#160;the Reorientation button in the Landmark panel (Figure 1).</li>
		<li>N (Nasion): click the V notch of the frontal bone in the 3D view (Figure 2). Immediately after the click, observe that the blue dot (activated) turns into a red cross that will appear in the axial, sagittal, and coronal views as well. Click the blue triangular arrows back and forth to identify the landmark.
		<ol>
			<li>In the sagittal view, scroll the mouse wheel up and down to find the most anterior point where the frontonasal suture meets the nasal and frontal bones and click to determine the vertical and anteroposterior position of the landmark.</li>
			<li>In the coronal view, scroll the mouse wheel up and down to find the moment just before the nasal bone disappears to ensure the most anterior point and click to determine the horizontal position of the Nasion.</li>
			<li>In the axial view, adjust the anteroposterior position as it is on the most anterior point.</li>
		</ol>
		</li>
		<li>R Or (Orbitale): click the most inferior point on the margin of the right orbital contour in the 3D model (Figure 2).
		<ol>
			<li>In the coronal view, scroll the mouse wheel up and down to find the lowest point on the inferior margin of the right orbit and click.</li>
			<li>In the sagittal view, click the most superior point of the right maxilla or zygomatic bone structure that constitutes the lower boundary of the orbit.</li>
			<li>In the axial view, scroll through the mouse and click so that the red cross is positioned where the eye orbit rim meets.</li>
		</ol>
		</li>
		<li>L Or (Orbitale): click the most inferior point on the margin of the left orbital contour in the 3D model (Figure 2) and modify the point on the three views as in the process for R Or.</li>
		<li>R Po (Porion): click the most superior point of the outline of the right external auditory meatus in the 3D model (Figure 2).
		<ol>
			<li>In the coronal view, click the lowest point of the right temporal bone to determine the horizontal and vertical positions.</li>
			<li>In the sagittal view, click the most superior point of the outline of the right external auditory meatus to adjust the vertical and anterior-posterior positions.</li>
			<li>In the axial view, scroll the mouse wheel to click where the external auditory canal appears, in which the line of the temporal bone disappears.</li>
		</ol>
		</li>
		<li>L Po (Porion): click the most superior point of the outline of the left external auditory meatus in the 3D model (Figure 2) and modify the point in the three multiplanar views as in the process for R Po. 
		NOTE: The five basic skeletal landmarks, including Nasion, right and left orbitales, and right and left porions in the reconstructed craniofacial model (Figure 2), are now identified.</li>
		<li>Click on the Done button to complete the reorientation of the reconstructed craniofacial model.</li>
		<li>Click on the Preliminary Landmark Picking button in the Landmark panel and select the Dentition I landmark group. 
		NOTE: Landmark groups of cranial base, TMJ, Maxillary Skeletal, Mandibular Skeletal, Dentition I, and Soft tissue are already selected for craniofacial analysis.</li>
		<li>Click on the Execute button in the Preliminary Landmark Picking panel and let the software automatically pick preliminary landmarks and determine their coordinates.</li>
		<li>When modifying the landmarks, press the Manual Landmark Picking button in the Volume tab, make the necessary adjustments, and click on the Done button to confirm (Figure 3).</li>
	</ol>
	</li>
</ol>
3. DDI merging procedure
<ol>
	<li>Click on the Registration of Dentition Scan button in the Tools panel (Figure 4).</li>
	<li>Select maxilla dentition and click on the Load button in the Dentition Registration panel.</li>
	<li>Select the STL files of the same patient with the CBCT model in the folder to load maxilla dentition STL files. Once the STL files are open, look for DDIs on the right side of the screen and four views (3D, axial, sagittal, and coronal) of the CBCT on the left side of the screen.</li>
	<li>Pick the registration landmarks on the loaded DDI: the mesiobuccal cusps of the right maxillary first molar (R U6CP), the right maxillary central incisor midpoint on incisal edge (R U1CP), and the mesiobuccal cusp of the left maxillary first molar (L U6CP) (Figure 5) by switching the blue triangular arrows back and forth. 
	NOTE: Left-click and drag the mouse to rotate the DDI and right-click and drag to zoom in and out. The registration landmarks are simultaneously calibrated by machine-learned automation after being digitized manually.</li>
	<li>Click on the Done button in the Dentition Registration panel.</li>
	<li>Click on the Yes button to confirm the automatic registration (Figure 6).</li>
	<li>For mandibular dentition merging, select mandible dentition and click on the Load button in the Dentition Registration panel. Repeat steps 3.2 to 3.6. Pick the registration landmarks on the mandibular dentition: the mesiobuccal cusp of the right/left lower first molar (R-/L- L6CP), right lower first incisor midpoint on the incisal edge (R L1CP).</li>
	<li>The DDI is now merged with the reconstructed CBCT model (Figure 7).
	<ol>
		<li>When modifying the merging, click on the Pick Registration Landmark button in the Dentition Registration panel (Figure 8).</li>
	</ol>
	</li>
</ol>
4. Obtaining the 3D coordinate values (x, y, and z) of each landmark
<ol>
	<li>Click on the Manual Landmark Picking button in the Volume tab or click the Analysis tab to obtain the 3D coordinate values of the landmarks. For data export, go to analysis tab<s>&#8594;</s>data export panel, and click on the Landmark button to save the data as a file. 
	NOTE: The X-plane (horizontal) is the plane that passes through the Nasion, parallel to the Frankfort horizontal (FH) plane which passes through the left and right Orbitales and right Porion. The Y-plane (midsagittal) is perpendicular to the X-plane, passing through the Nasion and basion. The Z-plane (coronal) sets the plane perpendicular to the horizontal and midsagittal planes via the Nasion (zero point; 0, 0, and 0) (Figure 9).</li>
</ol>

Artificial Intelligence-Based Integration of Dental Images

<ol>
	<li>Plooij, J. M., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Digital+three-dimensional+image+fusion+processes+for+planning+and+evaluating+orthodontics+and+orthognathic+surgery.+A+systematic+review.">Digital three-dimensional image fusion processes for planning and evaluating orthodontics and orthognathic surgery. A systematic review.</a> J Oral Maxillofac Surg. 40 (4), 341-352 (2011).</li><li>Badiali, G., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Virtual+orthodontic+surgical+planning+to+improve+the+accuracy+of+the+surgery-first+approach:+A+prospective+evaluation.">Virtual orthodontic surgical planning to improve the accuracy of the surgery-first approach: A prospective evaluation.</a> J Oral Maxillofac Surg. 77 (10), 2104-2115 (2019).</li><li>Lee, C. Y., Ganz, S. D., Wong, N., Suzuki, J. B. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Use+of+cone+beam+computed+tomography+and+a+laser+intraoral+scanner+in+virtual+dental+implant+surgery:+part+1.">Use of cone beam computed tomography and a laser intraoral scanner in virtual dental implant surgery: part 1.</a> Implant Dent. 21 (4), 265-271 (2012).</li><li>Park, J. H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Creation+of+digital+virtual+patient+by+integrating+CBCT,+intraoral+scan,+3D+facial+scan:+an+approach+to+methodology+for+integration+accuracy.">Creation of digital virtual patient by integrating CBCT, intraoral scan, 3D facial scan: an approach to methodology for integration accuracy.</a> J Craniofac Surg. 33 (4), e396-e398 (2022).</li><li>Almutairi, T., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Replacement+of+the+distorted+dentition+of+the+cone-beam+computed+tomography+scans+for+orthognathic+surgery+planning.">Replacement of the distorted dentition of the cone-beam computed tomography scans for orthognathic surgery planning.</a> J Oral Maxillofac Surg. 76 (7), 1561.e1-1561.e8 (2018).</li><li>Rangel, F. A., Maal, T. J., Berge, S. J., Kuijpers-Jagtman, A. M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Integration+of+digital+dental+casts+in+cone-beam+computed+tomography+scans.">Integration of digital dental casts in cone-beam computed tomography scans.</a> ISRN Dent. 2012, 949086 (2012).</li><li>Yang, W. M., Ho, C. T., Lo, L. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automatic+superimposition+of+palatal+fiducial+markers+for+accurate+integration+of+digital+dental+model+and+cone+beam+computed+tomography.">Automatic superimposition of palatal fiducial markers for accurate integration of digital dental model and cone beam computed tomography.</a> J Oral Maxillofac Surg. 73 (8), 1616.e1-1616.e10 (2015).</li><li>Swennen, G. R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+cone-beam+computed+tomography+triple+scan+procedure+to+obtain+a+three-dimensional+augmented+virtual+skull+model+appropriate+for+orthognathic+surgery+planning.">A cone-beam computed tomography triple scan procedure to obtain a three-dimensional augmented virtual skull model appropriate for orthognathic surgery planning.</a> J Craniofac Surg. 20 (2), 297-307 (2009).</li><li>Noh, H., Nabha, W., Cho, J. H., Hwang, H. S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Registration+accuracy+in+the+integration+of+laser-scanned+dental+images+into+maxillofacial+cone-beam+computed+tomography+images.">Registration accuracy in the integration of laser-scanned dental images into maxillofacial cone-beam computed tomography images.</a> Am J Orthod Dentofacial Orthop. 140 (4), 585-591 (2011).</li><li>Zou, B., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Accuracy+of+a+surface-based+fusion+method+when+integrating+digital+models+and+the+cone+beam+computed+tomography+scans+with+metal+artifacts.">Accuracy of a surface-based fusion method when integrating digital models and the cone beam computed tomography scans with metal artifacts.</a> Sci Rep. 12 (1), 8034 (2022).</li><li>Lin, H. H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Artifact-resistant+superimposition+of+digital+dental+models+and+cone-beam+computed+tomography+images.">Artifact-resistant superimposition of digital dental models and cone-beam computed tomography images.</a> J Oral Maxillofac Surg. 71 (11), 1933-1947 (2013).</li><li>Park, J. H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Use+of+artificial+intelligence+to+predict+outcomes+of+nonextraction+treatment+of+Class+II+malocclusions.">Use of artificial intelligence to predict outcomes of nonextraction treatment of Class II malocclusions.</a> Semin Orthodontics. 27 (2), 87-95 (2021).</li><li>Bao, H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Evaluating+the+accuracy+of+automated+cephalometric+analysis+based+on+artificial+intelligence.">Evaluating the accuracy of automated cephalometric analysis based on artificial intelligence.</a> BMC Oral Health. 23 (1), 1-10 (2023).</li><li>Gillot, M., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automatic+landmark+identification+in+cone-beam+computed+tomography.">Automatic landmark identification in cone-beam computed tomography.</a> Orthod Craniofac Res. , (2023).</li><li>Blum, F. M. S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Evaluation+of+an+artificial+intelligence-based+algorithm+for+automated+localization+of+craniofacial+landmarks.">Evaluation of an artificial intelligence-based algorithm for automated localization of craniofacial landmarks.</a> Clin Oral Invest. 27, 2255-2265 (2023).</li><li>Al-Ubaydi, A. S., Al-Groosh, D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=The+validity+and+reliability+of+automatic+tooth+segmentation+generated+using+artificial+intelligence.">The validity and reliability of automatic tooth segmentation generated using artificial intelligence.</a> The Scientific World Journal. 2023, 5933003 (2023).</li><li>Urban, R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=AI-assisted+CBCT+data+management+in+modern+dental+practice:+Benefits,+limitations+and+innovations.">AI-assisted CBCT data management in modern dental practice: Benefits, limitations and innovations.</a> Electronics. 12 (7), 1710 (2023).</li><li>Faul, F., Erdfelder, E., Buchner, A., Lang, A. G. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Statistical+power+analyses+using+G*Power+3.1:+tests+for+correlation+and+regression+analyses.">Statistical power analyses using G*Power 3.1: tests for correlation and regression analyses.</a> Behav Res Methods. 41 (4), 1149-1160 (2009).</li><li>Landis, J. R., Koch, G. G. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=The+measurement+of+observer+agreement+for+categorical+data.">The measurement of observer agreement for categorical data.</a> Biometrics. 33, 159-174 (1977).</li><li>Uechi, J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+novel+method+for+the+3-dimensional+simulation+of+orthognathic+surgery+by+using+a+multimodal+image-fusion+technique.">A novel method for the 3-dimensional simulation of orthognathic surgery by using a multimodal image-fusion technique.</a> Am J Orthod Dentofacial Orthop. 130 (6), 786-798 (2006).</li><li>Nkenke, E., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Fusion+of+computed+tomography+data+and+optical+3D+images+of+the+dentition+for+streak+artifact+correction+in+the+simulation+of+orthognathic+surgery.">Fusion of computed tomography data and optical 3D images of the dentition for streak artifact correction in the simulation of orthognathic surgery.</a> Dentomaxillofac Radiol. 33 (4), 226-232 (2004).</li><li>Lagrav&#232;re, M. O., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Intraexaminer+and+interexaminer+reliabilities+of+landmark+identification+on+digitized+lateral+cephalograms+and+formatted+3-dimensional+cone-beam+computerized+tomography+images.">Intraexaminer and interexaminer reliabilities of landmark identification on digitized lateral cephalograms and formatted 3-dimensional cone-beam computerized tomography images.</a> Am J Orthod Dentofacial Orthop. 137 (5), 598-604 (2010).</li></ol>

The authors declare no conflicts of interest.

Using the presented protocol, digitization of landmarks and integrating CBCT and DDI can be easily accomplished using machine-learned software. This protocol requires the following critical steps: i) reorientation of the head in the CBCT scan, ii) digitization of CBCT and DDI, and iii) merging CBCT images with the DDI. The digitization of five landmarks for the reorientation of the head is critical because it determines the 3D position of the head with reference planes in spatial areas. Three landmarks (R-/L-U6CP and R U...

Three-dimensional (3D) digital technology has broadened the scope of diagnosis and planning for orthodontic or surgical-orthodontic treatment. A virtual head constructed from a facial cone-beam computed tomography (CBCT) image can be used to evaluate dentofacial and dental abnormalities, plan orthognathic surgery, fabricate dental wafers&#160;and implant surgical guides using computer-aided design and manufacturing1,2,3,4. However, CBCT scans have a low representation of dentition, including dental morphology and interocclusal relationship, which are due to their limited resolution and streak artifacts from dental restoration or orthodontic brackets5. Therefore, the dental features have been substituted on CBCT images with digital dental images (DDI), such as scanned casts or intraoral scan images.
For reliable integration of DDI on CBCT images, numerous studies reported various methods such as the use of fiducial markers6,7, voxel-based8, and surface-based registrations (SBRs)9,10. These procedures have their methods of using extraoral markers, multiple CBCT scans, and extra process steps such as cleaning metal artifacts on CBCT images. Regarding SBR accuracy, several previous studies reported errors ranging from 0.10 to 0.43mm9,11. In addition, Zou et al. evaluated intra-/inter-observer reliability and errors between a digital engineer and an orthodontist using SBR and reported the need for clinical experience and repeated learning10.
Artificial intelligence (AI) has been used to predict treatment outcomes12 and digitize landmarks on cephalometric radiographs13 or CBCT images14,15,16, and some commercial software is currently available to assist in this process17. Accurate identification of anatomical landmarks on 3D images is challenging because of the ambiguity of flat surfaces or curved structures, areas of low density, and the wide variability of the anatomical structures.
AI-based, machine-learned automation can be applied not only for digitization but also for the integration of DDI and dentofacial CBCT. However, there is little research on the accuracy of an AI-based registration (ABR) compared to the existing surface-based method. To achieve more accurate outcomes of 3D skeletal and dental changes through bimaxillary orthognathic surgery, it is necessary to evaluate the accuracy of AI-based programs when merging CBCT and DDI. Therefore, this article presents a step-by-step protocol for digitizing and integrating CBCT and DDI with an AI-based registration (ABR) and to evaluate its reliability and reproducibility compared to that of SBR.

<table><tbody><tr><td>G*Power&amp;nbsp;</td><td>Heinrich Heine Universit&amp;auml;t, D?sseldorf, Germany</td><td>v. 3.1.9.7</td><td>A sample size calculuation software</td></tr><tr><td>Geomagic Qualify&amp;reg;</td><td>3D Systems,&lt;br/&gt; Morrisville, NC, USA</td><td>v 2013</td><td>3D metrology feature and automation software,&lt;br/&gt; which transform scan and probe data into 3D to be used in design, manufacturing and metrology applications&amp;nbsp;</td></tr><tr><td>KODAK 9500</td><td>Carestream Health Inc., Rochester, NY, USA</td><td>5159538</td><td>Cone Beam Computed Tomograph (CBCT)</td></tr><tr><td>MD-ID0300</td><td>Medit Co, Seoul, South Korea&lt;br/&gt; Seoul, Korea</td><td>61010-1</td><td>Desktop model scanner&amp;nbsp;</td></tr><tr><td>ON3D</td><td>3D ONS Inc.,&lt;br/&gt; Seoul, Korea</td><td>v 1.3.0</td><td>Software for 3D CBCT evaluation; AI-based landmark identification, craniofacial and TMJ analysis, superimposition, and virtual orthognathic surgery</td></tr><tr><td>SPSS&amp;nbsp;</td><td>IBM, Armonk, NY, USA</td><td>v 22.0&amp;nbsp;</td><td>A statistic analysis program</td></tr></tbody></table>

reliability of artificial intelligence-based cone beam computed tomography integration with digital dental images

This study aimed to introduce cone-beam computed tomography (CBCT) digitization and integration of digital dental images (DDI) based on artificial intelligence (AI)-based registration (ABR) and to evaluate the reliability and reproducibility using this method compared with those of surface-based registration (SBR). This retrospective study consisted of CBCT images and DDI of 17 patients who had undergone computer-aided bimaxillary orthognathic surgery. The digitization of CBCT images and their integration with DDI were repeated using an AI-based program. CBCT images and DDI were integrated using a point-to-point registration. In contrast, with the SBR method, the three landmarks were identified manually on the CBCT and DDI, which were integrated with the iterative closest points method.
After two repeated integrations of each method, the three-dimensional coordinate values of the first maxillary molars and central incisors and their differences were obtained. Intraclass coefficient (ICC) testing was performed to evaluate intra-observer reliability with each method&#39;s coordinates and compare their reliability between the ABR and SBR. The intra-observer reliability showed significant and almost perfect ICC in each method. There was no significance in the mean difference between the first and second registrations in each ABR and SBR and between both methods; however, their ranges were narrower with ABR than with the SBR method. This study shows that AI-based digitization and integration are reliable and reproducible.

Here we described the integration process of CBCT and DDI using an AI-based program. To evaluate its reliability and reproducibility, a comparative study with surface-based registration (SBR) was conducted. It was determined that a minimum sample size of ten was required after a power analysis under correlation &#961; H1 = 0.77, &#945; = 0.05, and power (1&#8722;&#946;) = 0.8018. A total of 17 sets of CBCT scans and digital dental images from orthognathic patients at Seoul National University Bund...

Watch this Scientific Journal Video about Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization at JoVE.com

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

A process of registering cone-beam computed tomography scans and digital dental images has been presented using artificial intelligence (AI) -assisted identification of landmarks and merging. A comparison with surface-based registration shows that AI-based digitization and integration are reliable and reproducible.

Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images

This study aimed to introduce cone-beam computed tomography (CBCT) digitization and integration of digital dental images (DDI) based on artificial ...

reliability-artificial-intelligence-based-cone-beam-computed

Research

JoVE Journal

Medicine

734 Views.  Seoul National University Bundang Hospital. A process of registering cone-beam computed tomography scans and digital dental images has been presented using artificial intelligence (AI) -assisted identification of landmarks and merging. A comparison with surface-based registration shows that AI-based digitization and integration are reliable and reproducible.

Video: Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

The advent of cone-beam computed tomography (CBCT) in the angiography suite has been revolutionary in interventional radiology. CBCT offers 3 dimensional&#160;(3D) diagnostic imaging in the interventional suite and can enhance minimally-invasive therapy beyond the limitations of 2D angiography alone. The role of CBCT has been recognized in transarterial chemo-embolization (TACE) treatment of hepatocellular carcinoma (HCC). The recent introduction of a CBCT technique: dual-phase CBCT (DP-CBCT) improves intra-arterial HCC treatment with drug-eluting beads (DEB-TACE). DP-CBCT can be used to localize liver tumors with the diagnostic accuracy of multi-phasic multidetector computed tomography (M-MDCT) and contrast enhanced magnetic resonance imaging (CE-MRI) (See the tumor), to guide intra-arterially guidewire and microcatheter to the desired location for selective therapy (Reach the tumor), and to evaluate treatment success during the procedure (Treat the tumor). The purpose of this manuscript is to illustrate how DP-CBCT is used in DEB-TACE to see, reach, and treat HCC.

Dual-phase cone-beam computed tomography (DP-CBCT) is a useful intraprocedural imaging technique for transarterial chemo-embolization treatment with drug-eluting beads of hepatocellular carcinoma. DP-CBCT has been used to perform three major steps in oncologic interventional radiology: tumor localization (see), navigation and intraprocedural catheter guidance (reach), and intraprocedural evaluation of treatment success (treat).

The advent of cone-beam computed tomography (CBCT) in the angiography suite has been revolutionary in interventional radiology. CBCT offers 3 ...

Measuring the Complete-arch Distortion of an Optical Dental Impression

Digital workflows have actively been used to produce dental restorations or oral appliances since dentists started to make digital impressions by acquiring 3D images with an intraoral scanner. Because of the nature of scanning the oral cavity in the patient&#39;s mouth, the intraoral scanner is a handheld device with a small optical window, stitching together small data to complete the entire image. During the complete-arch impression procedure, a deformation of the impression body can occur and affect the fit of the restoration or appliance. In order to measure these distortions, a master specimen was designed and produced with a metal 3D printer. Designed reference geometries allow setting independent coordinate systems for each impression and measure x, y, and z displacements of the cylinder top circle center where the distortion of the impression can be evaluated. In order to evaluate the reliability of this method, the coordinate values of the cylinder are calculated and compared between the original computer-aided design (CAD) data and the reference data acquired with the industrial scanner. The coordinate differences between the two groups were mostly less than 50 &#181;m, but the deviations were high due to the tolerance of 3D printing in the z coordinates of the obliquely designed cylinder on the molar. However, since the printed model sets a new standard, it does not affect the results of the test evaluation. The reproducibility of the reference scanner is 11.0 &#177; 1.8 &#181;m. This test method can be used to identify and improve upon the intrinsic problems of an intraoral scanner or to establish a scanning strategy by measuring the degree of distortion at each part of the complete-arch digital impression.

Here, we present a protocol to measure the degree of distortion at each part of the compete-arch digital impression acquired from an intraoral scanner with 3D-printed metal phantom with standard geometries.

Digital workflows have actively been used to produce dental restorations or oral appliances since dentists started to make digital impressions by ...

Engineering

Computed Tomography and Optical Imaging of Osteogenesis-angiogenesis Coupling to Assess Integration of Cranial Bone Autografts and Allografts

A major parameter determining the success of a bone-grafting procedure is vascularization of the area surrounding the graft. We hypothesized that implantation of a bone autograft would induce greater bone regeneration by abundant blood vessel formation. To investigate the effect of the graft on neovascularization at the defect site, we developed a micro&#8211;computed tomography (&#181;CT) approach to characterize newly forming blood vessels, which involves systemic perfusion of the animal with a polymerizing contrast agent. This method enables detailed vascular analysis of an organ in its entirety. Additionally, blood perfusion was assessed using fluorescence imaging (FLI) of a blood-borne fluorescent agent. Bone formation was quantified by FLI using a hydroxyapatite-targeted probe and &#181;CT analysis. Stem cell recruitment was monitored by bioluminescence imaging (BLI) of transgenic mice that express luciferase under the control of the osteocalcin promoter. Here we describe and demonstrate preparation of the allograft, calvarial defect surgery, &#181;CT scanning protocols for the neovascularization study and bone formation analysis (including the in vivo perfusion of contrast agent), and the protocol for data analysis.
The 3D high-resolution analysis of vasculature demonstrated significantly greater angiogenesis in animals with implanted autografts, especially with respect to arteriole formation. Accordingly, blood perfusion was significantly higher in the autograft group by the 7th day after surgery. We observed superior bone mineralization and measured greater bone formation in animals that received autografts. Autograft implantation induced resident stem cell recruitment to the graft-host bone suture, where the cells differentiated into bone-forming cells between the 7th and 10th postoperative day. This finding means that enhanced bone formation may be attributed to the augmented vascular feeding that characterizes autograft implantation. The methods depicted may serve as an optimal tool to study bone regeneration in terms of tightly bounded bone formation and neovascularization.

Implantation of autologous and allogeneic bone grafts constitute accepted approaches to treat major craniofacial bone loss. Yet the effect of graft composition on the interplay among neovascularization, cell differentiation and bone formation is unclear. We present a multimodal imaging protocol aimed to elucidate the angiogenesis-osteogenesis interdependence at the graft proximity.

A major parameter determining the success of a bone-grafting procedure is vascularization of the area surrounding the graft. We hypothesized that ...

Bioengineering

Accuracy in Dental Medicine, A New Way to Measure Trueness and Precision

Reference scanners are used in dental medicine to verify a lot of procedures. The main interest is to verify impression methods as they serve as a base for dental restorations. The current limitation of many reference scanners is the lack of accuracy scanning large objects like full dental arches, or the limited possibility to assess detailed tooth surfaces. A new reference scanner, based on focus variation scanning technique, was evaluated with regards to highest local and general accuracy. A specific scanning protocol was tested to scan original tooth surface from dental impressions. Also, different model materials were verified. The results showed a high scanning accuracy of the reference scanner with a mean deviation of 5.3 &#177; 1.1 &#181;m for trueness and 1.6 &#177; 0.6 &#181;m for precision in case of full arch scans. Current dental impression methods showed much higher deviations (trueness: 20.4 &#177; 2.2 &#181;m, precision: 12.5 &#177; 2.5 &#181;m) than the internal scanning accuracy of the reference scanner. Smaller objects like single tooth surface can be scanned with an even higher accuracy, enabling the system to assess erosive and abrasive tooth surface loss. The reference scanner can be used to measure differences for a lot of dental research fields. The different magnification levels combined with a high local and general accuracy can be used to assess changes of single teeth or restorations up to full arch changes.

Accuracy is a major demand in dental medicine. To verify accuracy, reference scanners are needed. This article presents a new reference scanner with an adjusted scanning method to acquire a broad variety of dental morphologies with high trueness and precision.

Reference scanners are used in dental medicine to verify a lot of procedures. The main interest is to verify impression methods as they serve as a base ...

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

Valid comparisons of postoperative accuracy results in computer-assisted reconstruction of the mandible are difficult due to heterogeneity in imaging modalities, mandibular defect classification, and evaluation methodologies between studies. This guideline uses a step-by-step approach guiding the process of imaging, classification of mandibular defects and volume assessment of three-dimensional (3D) models, after which a legitimized quantitative accuracy evaluation method can be performed between the postoperative clinical situation and the preoperative virtual plan. The condyles and the vertical and horizontal corners of the mandible are used as bony landmarks to define virtual lines in the computer-assisted surgery (CAS) software. Between these lines the axial, coronal, and both sagittal mandibular angles are calculated on both pre- and postoperative 3D models of the (neo)mandible and subsequently the deviations are calculated. By superimposing the postoperative 3D model to the preoperative virtually planned 3D model, which is fixed to the XYZ axis, the deviation between pre- and postoperative virtually planned dental implant positions can be calculated. This protocol continues and specifies an earlier publication of this evaluation guideline.

Here, we propose a practical, feasible and reproducible evaluation guideline for computer-assisted reconstruction of the mandible in order to create uniformity between studies regarding postoperative accuracy evaluation. This protocol continues and specifies an earlier publication of this evaluation guideline.

Valid comparisons of postoperative accuracy results in computer-assisted reconstruction of the mandible are difficult due to heterogeneity in imaging ...

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Virtual, hybrid three-dimensional (3D) model acquisition is presented in this article, utilizing the sequence of radiographic image segmentation, spatial registration, and free-form surface modeling. Firstly cone-beam computed tomography datasets were reconstructed with a semi-automatic segmentation method. Alveolar bone and teeth are separated into different segments, allowing 3D morphology, and localization of periodontal intrabony defects to be assessed. The severity, extent, and morphology of acute and chronic alveolar ridge defects are validated concerning adjacent teeth. On virtual complex tissue models, positions of dental implants can be planned in 3D. Utilizing spatial registration of IOS and CBCT data and subsequent free-form surface modeling, realistic 3D hybrid models can be acquired, visualizing alveolar bone, teeth, and soft tissues. With the superimposition of IOS and CBCT soft tissue, thickness above the edentulous ridge can be assessed about the underlying bone dimensions; therefore, flap design and surgical flap management can be determined, and occasional complications may be avoided.

A workflow for creating three-dimensional (3D) virtual hybrid models has been designed based on cone-beam computed tomography dataset and intraoral optical scans utilizing radiographic image segmentation methods and free-form surface modeling. Digital models are used for the virtual planning of reconstructive dentoalveolar surgical procedures.

Virtual, hybrid three-dimensional (3D) model acquisition is presented in this article, utilizing the sequence of radiographic image segmentation, spatial ...

Dynamic Navigation for Dental Implant Placement

In modern implantology, the application of surgical navigation systems is becoming increasingly important. In addition to static surgical navigation methods, a guide-independent dynamic navigation implant placement procedure is becoming more widespread. The procedure is based on computer-guided dental implant placement utilizing optical control. This work aims to demonstrate the technical steps of a new dynamic computer-aided implant surgery (DCAIS)&#160;system (design, calibration, surgery) and check the accuracy of the results. Based on cone-beam computed tomography (CBCT) scans, the exact positions of implants are determined with dedicated software. The first step of the operation is the calibration of the navigation system, which can be performed in two ways: 1) based on CBCT images taken with a marker or 2) based on CBCT images without markers. Implants are inserted with the aid of real-time navigation according to the preoperative plans. The accuracy of the interventions can be evaluated based on postoperative CBCT images. The preoperative images containing the planned positions of the implants and postoperative CBCT images were compared based on the angulation (degree), platform, and apical deviation (mm) of the implants. To evaluate the data, we calculated the standard deviation (SD), mean, and standard error of the mean (SEM) of deviations within planned and performed implant positions. Differences between the two calibration methods were compared based on this data. Based on the interventions performed so far, the use of DCAIS allows for high-precision implant placement. A calibration system that does not require labeled CBCT recording allows for surgical intervention with similar accuracy as a system that uses labeling. The accuracy of the intervention can be improved by training.

Dynamic computer-aided implant surgery (DCAIS) is a controlled implant surgical placement method performed without a surgical template using optical control. The real-time intraoperative control of movement and position of the surgical device simplifies the procedure and gives more freedom to the surgeon, providing similar precision as static navigation methods.

In modern implantology, the application of surgical navigation systems is becoming increasingly important. In addition to static surgical navigation ...

Dynamic Navigation in Endodontics: Guided Access Cavity Preparation by Means of a Miniaturized Navigation System

In the case of teeth with pulp canal calcification (PCC) and apical pathology or pulpitis, root canal treatment can be very challenging. PCC are common sequelae of dental trauma but can also occur with stimuli such as caries, bruxism, or after placing a restoration. In order to access the root canal as minimally invasive as possible in case of a necessary root canal treatment, dynamic navigation has recently been introduced in endodontics in addition to static navigation. The use of a dynamic navigation system (DNS) requires pre-operative cone-beam computed tomography (CBCT) imaging and a digital surface scan. If necessary, reference markers must be placed on the teeth before the CBCT scan; with some systems, these can also be planned and created digitally afterward. By means of a stereo camera connected to the planning software, the drill can now be coordinated with the help of reference markers and virtual planning. As a result, the position of the drill can be displayed on the monitor in real-time during preparation in different planes. In addition, the spatial displacement, the angular deviation, and the depth position are also displayed separately. The few commercially available DNS mostly consist of relatively large camera-marker-systems. Here, the DNS contains miniaturized components: a low-weight camera (97 g) mounted on the micromotor of the electric handpiece utilizing a manufacturer-specific connecting mechanism and a small marker (10 mm x 15 mm), which can be easily attached to an individually manufactured intraoral tray. For research purposes, a post-operative CBCT scan can be matched with the pre-operative one, and the volume of tooth structure removed can be calculated by the software. This work aims to present the technique of guided access cavity preparation by means of a miniaturized navigation system from imaging to clinical implementation.

Dynamic navigation systems (DNS) provide real-time visualization and guidance to the operator during endodontic access cavities preparation. The planning of the procedure requires three-dimensional imaging utilizing cone beam computed tomography and surface scans. After the export of the planning data to the DNS, access cavities can be prepared with minimal invasion.

In the case of teeth with pulp canal calcification (PCC) and apical pathology or pulpitis, root canal treatment can be very challenging. PCC are common ...

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Pulp canal obliterations (PCO) are often a consequence of dental trauma, such as luxation injuries. Even though dentin apposition is a sign of vital pulp, pulpitis or apical periodontitis may develop in the long term. Root canal treatment of teeth with severe PCO and pulpal or periapical pathosis is challenging for general practitioners and even for well-equipped endodontic specialists. To ensure detection of the calcified root canal and avoid excessive loss of tooth structure or root perforation, static navigation using templates ("Guided Endodontics") was introduced a few years ago. The general workflow includes three-dimensional imaging using cone-beam computed tomography (CBCT), a digital surface scan, and superimposition of both in a planning software. This is followed by virtual planning of the access cavity and the design of a template that will guide the drill to the desired target point. To do this, a true-to-scale virtual image of the drill must be placed in a way that the tip of the drill reaches the orifice of the calcified root canal. Once the template has been fabricated using computer-aided design and computer-aided manufacturing (CAD/CAM) or a 3D printer, guided preparation of the access cavity can be performed clinically. For research purposes, a postoperative CBCT image can be used to quantify the accuracy of the access cavity performed. This work aims to present the technique of static guided endodontics from imaging to clinical implementation.

Guided endodontics describes a template-aided approach for access cavity preparation. The procedure requires cone-beam computed tomography and a surface scan to produce a template. An incorporated sleeve guides the drill to the target point. This allows the preparation of minimally invasive endodontic access cavities in calcified teeth.

Pulp canal obliterations (PCO) are often a consequence of dental trauma, such as luxation injuries. Even though dentin apposition is a sign of vital pulp, ...

3D Cephalometric Landmark Annotation Demonstration on Human CBCT Scans

Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Craniofacial cephalometric analysis is a diagnostic tool used for the assessment of the relationship of various bones and soft tissues in the head and face. Cephalometric analysis has been traditionally conducted with the use of 2D radiographs and landmark sets and restricted to size, linear and angular measurements, and 2D relationships. The increasing use of 3D cone beam computed tomography (CBCT) scans in the dental field dictates the need for the evolution to 3D cephalometric analysis, which incorporates shape and a more realistic analysis of longitudinal development in all three planes. This study is a demonstration of 3D cephalometric analysis with the use of a validated set of skeletal tissue landmarks on human CBCT scans. Detailed instructions for the annotation of each landmark on a 3D volume are provided as part of a step-by-step protocol. The generated measurements and 3D coordinates of the landmarks can be exported and used both for clinical and research purposes. The introduction of 3D cephalometric analysis in basic and clinical craniofacial studies will lead to future advancements in the field of craniofacial growth and development.

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans  

Presented here is a detailed protocol for the conduction of three-dimensional cephalometric analysis with the use of human cone beam computed tomography scans.

Craniofacial cephalometric analysis is a diagnostic tool used for the assessment of the relationship of various bones and soft tissues in the head and ...