Artificial Intelligence Supported Intraoral Scanning.

Summary

Digitization (automation) of production stages with Computer-Aided Design and Computer-Aided Manufacturing (CAD/CAM) technologies has led to a digital revolution in dentistry, as in many other fields of the industry. In current dentistry, the digitalization process can be defined as direct and indirect workflow. The clinical reliability and success of the indirect digital workflow made possible by these technologies have been proven by scientific studies. With the development of intraoral scanners (IOS), a virtual model is obtained by direct digitalization. This method eliminated the conventıonale impression and dental cast model steps required for indirect digitalization. Intraoral scanners are used as an alternative to convantıonal impressions in single and short edentulous cases. It has already been emphasized that direct digitalization is a reliable alternative to the conventional impression method, as the clinical applicability, accuracy, and precision of the manufactured restorations have been scientifically verified. Therefore, the clinical use of direct digitalization is increasing (exponentially) day by day, and new upgraded versions of software, along with various modifications for the hardware equipment, are being developed. Integrating artificial intelligence (AI) supported software into the intraoral scanning process can be seen as the beginning of a new era for direct digitalization. Therefore the aim of this study is to evaluate the effect of artificial intelligence on the scanning time, the amount of data collected, and the image accuracy obtained.

Conditions

• Impression Technic, Dental

Interventions

DEVICE

AI on algorithm

The mandibles of the participants were scanned with ''AI on'' scanning in line with the recommended scanning protocol. All scans were performed by the same operator.

DEVICE

AI off algorithm

The mandibles of the participants were scanned with ''AI off'' scanning in line with the recommended scanning protocol. All scans were performed by the same operator.

Sponsors & Collaborators

• Hacettepe University

  collaborator OTHER

• Kıvanç Akça

  lead OTHER

Principal Investigators

• Kivanc Akca, Professor · Study Director

Study Design

Allocation

NON_RANDOMIZED

Purpose

BASIC_SCIENCE

Masking

TRIPLE

Model

PARALLEL

Eligibility

Min Age

18 Years

Max Age

44 Years

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2021-09-01

Primary Completion

2021-10-10

Completion

2021-12-05

Countries

• Turkey (Türkiye)

Study Locations