Artificial intelligence and augmented reality for guided implant surgery planning: A proof of concept
Francesco Guido Mangano a b, Oleg Admakin a, Henriette Lerner c, Carlo Mangano
daDepartment of Pediatric, Preventive Dentistry and Orthodontics, Sechenov First State Medical University, Moscow, Russian Federation
bHonorary Professor in Restorative Dental Sciences, Faculty of Dentistry, The University of Hong Kong, China
cAcademic Teaching and Research Institution of Johann Wolfgang Goethe University, Frankfurt, Germany
dPrivate Practice, (CO), Gravedona, Italy
To present a novel protocol for authentic three-dimensional (3D) planning of dental implants, using artificial intelligence (AI) and augmented reality (AR).
The novel protocol consists of (1) 3D data acquisition, with an intraoral scanner (IOS) and cone-beam computed tomography (CBCT); (2) application of AI for CBCT segmentation to obtain standard tessellation language (STL) models and automatic alignment with IOS models; (3) loading of selected STL models within the AR system and surgical planning with holograms; (4) surgical guide design with open-source computer-assisted-design (CAD) software; and (5) surgery on the patient.
This novel protocol is effective and time-efficient when used for planning simple cases of static guided implant surgery in the partially edentulous patient. The clinician can plan the implants in an authentic 3D environment, without using any radiological guided surgery software. The precision of implant placement looks clinically acceptable, with minor deviations.
AI and AR technologies can be successfully used in guided implant surgery for authentic 3D planning that may replace conventional software. However, further clinical studies are needed to validate this protocol.
Statement of clinical relevance
The combined use of AI and AR may change the perspectives of modern guided implant surgery for authentic 3D planning that may replace conventional software.
The digital revolution has transformed dentistry . Intraoral scanners (IOSs) [2,3] and cone-beam computed tomography (CBCT) , together with computer-assisted-design (CAD) software , have changed diagnostic precision, treatment plans, and workflows .
Recently, two disruptive technologies have promised an equally radical impact on modern dentistry: artificial intelligence (AI) [7,8] and augmented reality (AR) . AI refers to computer systems that can perform tasks normally requiring human cognition [7,8]. In dentistry, AI is currently used for the automatic detection and diagnosis of caries [10,11] and endodontic or periodontal lesions  on two-dimensional (2D) radiographs (endoral and panoramic), as well as for the detection and automatic segmentation of anatomical structures in three dimensions (3D) with CBCT , , , . These functions are enabled by machine learning (ML), through which computers learn rules from data, capturing their intrinsic statistical patterns and structures [7,8].
AR is a technology that superimposes computer-generated virtual content (high-definition holograms) atop the existing environment, enhancing the user's perception of reality [9,17,18]. A hologram is a 3D model created with photographic projection. With AR, the user wears a headset with see-through lenses that puts virtual objects into the real world, augmenting it; therefore, they continue to be in touch with the real world while interacting with virtual objects (holograms) [17,18].
To date, AR has been used for guided implant surgery applications in a few in vitro studies , ,  and in vivo reports [22,23]. In one recent in vitro study, AI was employed for assisted implant planning . No studies currently exist in the literature on the combined use of AI and AR in dentistry. However, in guided implant surgery, this approach could revolutionize workflows, allowing authentic and accurate 3D planning of dental implants in a holographic environment, without the use of any guided surgery software [7,9]. This is possible using the complete set of standard tessellation language (STL) models derived from automatic CBCT segmentation and alignment with IOS, implemented by modern AI systems . These models, loaded into specific applications designed for AR systems, can be used for 3D planning of dental implants, thanks to modern holographic systems . The 3D planning of the implants can therefore be intuitively realized in a holographic environment, using hand and finger gestures and movements. The implant files, correctly planned in the ideal position, inclination, and depth, can be saved in STL format, together with other holographic models, and used to design surgical templates. These surgical templates can be 3D printed in resin  or metal  and used to prepare the implant beds and/or insert the fixtures, in a static guided surgery workflow . Alternatively, dynamic guided surgery can be used .
This work aims to present a new protocol for 3D planning dental implants in a holographic environment, using AI and AR technologies, without the use of any guided surgery software.
Materials and methods
The protocol consists of (1) 3D data acquisition, with IOS and CBCT scans; (2) application of AI for automatic alignment of IOS and CBCT models, with CBCT segmentation; (3) loading of STL models within the AR system and surgical planning with the holographic system; (4) quality control of the project; (5) surgical guide design within open-source CAD software; and (6) surgery on the patient.
Patients with good systemic health, with single or partial edentulism, in the presence of sufficient bone
The complete documentation of three implants planned in the mandible of the same patient (left mandible, two implants placed in position #36 and #37; right mandible, one implant placed in position #46) with AI and AR is provided here (left mandible, Fig. 1, Fig. 2, Fig. 3, Fig. 4, Fig. 5, Fig. 6, Fig. 7, Fig. 8, Fig. 9, Video 1, Video 2; right mandible, Fig. 10, Fig. 11, Fig. 12, Fig. 13, Fig. 14, Fig. 15, Fig. 16, Fig. 17, Video 3, Video 4). This experimental clinical protocol based on the
Static guided implant surgery is a technique that allows, through the use of surgical templates, the preparation of implant sites and the consequent insertion of dental implants in the desired position, inclination, and depth, following a plan created on the computer , , . This planning is carried out through dedicated software, in which the clinician uploads the DICOM files coming from the CBCT, along with the meshes captured with IOS and any virtual diagnostic waxing. The first
In this short communication, we have presented a novel protocol for 3D planning dental implants in a holographic environment, using AI and AR technologies, without the use of any guided surgery software. This protocol consists of 3D data acquisition, AI application for automatic CBCT segmentation and alignment with IOS models, surgical planning with a holographic system, guide design within open-source CAD software, and surgery on the patient. Based on the results obtained, this novel protocol
Credit authorship contribution statement
Francesco Guido Mangano: Methodology, Software, Visualization, Investigation, Formal analysis, Writing – original draft, Writing – review & editing. Oleg Admakin: Supervision, Writing – review & editing. Henriette Lerner: Visualization, Investigation, Formal analysis. Carlo Mangano: Conceptualization, Investigation, Supervision, Writing – review & editing.
Declaration of Competing Interest
The authors report no conflict of interest related to the present study. The materials belong to the authors who have not received any grant, material, or financial support for the preparation of the present research.
- F. Mangano Digital dentistry J. Dent. (2021)
- T. Kaasalainen et al. Dental cone beam CT: an updated review Phys. Med. (2021)
- J. Conejo et al.The digital clone: intraoral scanning, face scans and cone beam computed tomography integration for diagnosis and treatment planning Dent. Clin. N. Am. (2021)
- J. Grischke et al .Dentronics: towards robotics and artificial intelligence in dentistry Dent. Mater. (2020)
- H. Mohammad-Rahimi et al.Deep learning for caries detection: a systematic review J. Dent. (2022)
- F. Schwendicke et al. IADR e-oral health network and the ITU WHO focus group AI for health, artificial intelligence in dental research: checklist for authors, reviewers, readers J. Dent. (2021)
- S. Li et al.Artificial intelligence for caries and periapical periodontitis detection J. Dent. (2022)
- P.J. Verhelst et al.Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography J. Dent. (2021)
- E. Shaheen et al.A novel deep learning system for multi-class tooth segmentation and classification on cone beam computed tomography. A validation study J. Dent. (2021)
- P. Lahoud et al.Development and validation of a novel artificial intelligence driven tool for accurate mandibular canal segmentation on CBCT J. Dent. (2022)