Close this panel

Design Optimization of Reduced-Diameter Implants by Artificial Neural Network

Jason Griggs, PhD – Associate Dean for Research, University of Mississippi School of Dentistry


Purpose of the Study: The objective was to train an artificial neural network (ANN) to predict the fatigue limits of dental implants.

Methods: Four commercially available reduced-diameter implant systems (RDIS) were investigated: Straumann Narrow Neck, Biomet 3i Osseotite MicroMiniplant, Nobel Biocare NobelReplace, and Biomet 3i Osseotite Certain. Step-stress accelerated lifetime testing was performed on the RDIS to determine the fatigue limit for each design. MicroCT images (Skyscan1172, Microphotonics) of the four RDIS were analyzed. Twenty-four design parameters were identified, and measurements were made using Mimics interactive image processing software (Materialise, 9-micron resolution). Linear stepwise regression was used to identify the seven most significant design parameters, and these were used as the input vector to predict the fatigue limit in a feedforward error-backpropagation ANN having one hidden node. The learning ratio was decreased from 1 to 0 over 1,500 iterations.

Results: The ANN achieved a notable prediction accuracy (R-squared=0.99995). The effects of implant body inner diameter, abutment screw thread height, and abutment screw head diameter were non-linear and could account for most of the variation in fatigue limit between implant systems.

Conclusion: The ANN was successfully trained on the commercially available implant systems and may be a useful tool in predicting the implant design that corresponds to maximum possible fatigue limit. However, some of the design parameters are confounded in the current commercially available systems, so future studies should train an ANN on the fatigue lifetime predictions from finite element models of hypothetical implant systems in which the factors are not confounded.

Articles: None cited.

Primary Author:

Close this panel
Browse By Track
Browse By Poster Author
Browse By Title
Close this panel

Rate This Poster

Stuff for notes
Stuff for Message board

Share Poster


Technical Support

(877) 426-6323


SUBMIT FEEDBACKfeedback icon

We really appreciate your feedback on the eventScribe website. We use the data to improve the experience and simplify the process for users like you.


Log In / Sign Up

Already have an Event Scheduler or mobile app login? Login with those details. If not, create a login.

Log In   Sign Up
Access your bookmarked poster and notes by logging in ...   Sign up to take notes on poster, bookmark poster, and submit feedback.
  Lost your access key?      
You need to be logged in to bookmark posters, save notes, or rate posters.