Prediction of the facial growth direction with Machine Learning methods

TL;DR

This paper introduces the first machine learning approach to predict facial growth direction from 2D X-ray images, achieving around 71-75% accuracy, highlighting the problem's complexity.

Contribution

It is the first to apply machine learning methods to predict facial growth direction, exploring various algorithms and problem formulations.

Findings

Classification accuracy between 71% and 75%.

The problem's inherent complexity affects prediction performance.

Different algorithms yield similar accuracy levels.

Abstract

First attempts of prediction of the facial growth (FG) direction were made over half of a century ago. Despite numerous attempts and elapsed time, a satisfactory method has not been established yet and the problem still poses a challenge for medical experts. To our knowledge, this paper is the first Machine Learning approach to the prediction of FG direction. Conducted data analysis reveals the inherent complexity of the problem and explains the reasons of difficulty in FG direction prediction based on 2D X-ray images. To perform growth forecasting, we employ a wide range of algorithms, from logistic regression, through tree ensembles to neural networks and consider three, slightly different, problem formulations. The resulting classification accuracy varies between 71% and 75%.