Uso de redes neuronales artificiales en predicción de morfología mandibular a través de variables craneomaxilares en una vista posteroanterior / Use of Artificial Neural Networks for Mandibular Morphology Prediction through Craniomaxillar Variables...

Abstract

<p><em><strong><span>Background:</span></strong></em><span class="apple-converted-space"><span> </span></span><span>Predicting mandibular morphology is important in facial reconstruction for forensic purposes as in orthodontics and maxillofacial surgery. This process has been performed through parametric and linear methods based on Caucasian populations. Also, these analyzes are performed on lateral cephalograms, but a prediction from a posteroanterior view is not taken into account.<span class="apple-converted-space"> </span><em><strong>Purpose:</strong></em><span class="apple-converted-space"> </span>To predict through artificial neural networks the mandibular morphology using craniomaxillary measures in posteroanterior radiographs.<span class="apple-converted-space"> </span><em><strong>Methods:</strong></em><span class="apple-converted-space"> </span>229 standardized posteroanterior radiographs from Colombian young adults of both sexes were collected. Coordinates of craniofacial skeletal landmarks were used to create mandibular and craniomaxillary measures. 17 predictor craniomaxillary input variables were selected, measuring widths, heights, and angles. Similarly, 13 mandibular measures were selected to be predicted, considering both the right and left sides. Artificial neural networks were used for the prediction process and it was evaluated by a correlation coefficient using a ridge regression between real value and the predicted value.<span class="apple-converted-space"> </span><em><strong>Results:</strong></em><span class="apple-converted-space"> </span>The results found in the model were significant especially for 5 variables of morphological importance in the forensic field: right mandibular ramus (Cdd-God), bigonial width (Goi-God), bicondylar width (Cdi-Cdd), and distance between the condyles to the menton (Cdd-Me and Cdi-Me).<span class="apple-converted-space"> </span><em><strong>Conclusions:</strong></em><span class="apple-converted-space"> </span>An important prediction capacity in 5 measures of forensic importance in patients with skeletal Class I, Class II and Class III was found in both sexes.</span></p>

Evaluation of natural mandibular shape asymmetry: an approach by using elliptical Fourier analysis

“…17 However, this situation is complicated when the mandibular defects affect almost the entire hemimandibular segment. The results of this work helps to improve aspects considered in previous researches about mandibular prediction, 8 and it can be established that the asymmetry is not only a property determined by the Mandibular shape asymmetry by EFA Niño-Sandoval et al size, but also the mandibular right curve is significantly dissimilar to the mandibular left curve. Taking this in to account to achieve a real mandibular prediction, asymmetry is a factor that must be considered in further studies.…”

“…In order to carry out a system accessible to the low-income Latin American population, that also has a proper mandibular morphology to the actual craniofacial conformation of the patient, it is proposed to employ two-dimensional elements such as analysis in panoramic radiographs to be extrapolated in a three-dimensional view. Approaches in prediction in other types of radiographs have been made in terms of size and position; 1,[4][5][6][7] however from a posteroanterior view according to a previous study, 8 a discrepancy could be observed between the left and right side prediction coefficients, with an important influence of the mandibular shape.…”