Kök Hatice, İzgi Mehmet Said, Acılar Ayşe Merve
Department of Orthodontics, Selçuk University, Faculty of Dentistry, Konya, Turkey.
Private Practice, İstanbul, Turkey.
Turk J Orthod. 2020 Dec 2;34(1):2-9. doi: 10.5152/TurkJOrthod.2020.20059. eCollection 2021.
This study aimed to evaluate the success rates of the artificial neural network models (NNMs) and naive Bayes models (NBMs) trained with various cervical vertebra ratios in cephalometric radiographs for determining growth and development.
Our retrospective study was performed on 360 individuals between the ages of 8 and 17 years, whose cephalometric radiographs were taken. According to the evaluation of cephalometric radiographs, growth and development periods were divided into 6 vertebral stages. Each stage was considered as a group, each group had 30 girls and 30 boys. Twenty-eight cervical vertebral ratios were obtained by using 10 horizontal and 13 vertical measurements. These 28 vertebral ratios were combined in 4 different combinations, leading to 4 different datasets. Each dataset was split into 2 parts as training and testing. To prevent the overfitting, a 5-cross fold validation technique was also used in the training phase. The experiments were conducted on 2 different train/test ratios as 80%-20% and 70%-30% for both NNMs and NBMs.
The highest determination success rate was obtained in NNM 3 (0.95) and the lowest in NBM 4 (0.50). The determination success of NBM 1 and NBM 3 was almost similar (0.60). The success of NNM 2 did not differ much from that of NNM 1 (0.94). The determination success of stage 5 was relatively lower than the others in NNM 1 and NNM 2 (0.83).
The NNMs were more successful than the NBMs in our developed models. It is important to determine the effective ratio and/or measurements that will be useful for differentiation.
本研究旨在评估利用头颅侧位片中各种颈椎比例训练的人工神经网络模型（NNMs）和朴素贝叶斯模型（NBMs）在确定生长发育方面的成功率。
我们对360名8至17岁拍摄了头颅侧位片的个体进行了回顾性研究。根据头颅侧位片评估，将生长发育期分为6个椎体阶段。每个阶段视为一组，每组有30名女孩和30名男孩。通过10项水平测量和13项垂直测量获得了28个颈椎比例。这28个椎体比例以4种不同组合进行合并，从而得到4个不同的数据集。每个数据集分为训练和测试两部分。为防止过拟合，在训练阶段还使用了5折交叉验证技术。对NNMs和NBMs均以80%-20%和70%-30%这两种不同的训练/测试比例进行实验。
NNM 3的最高判定成功率为0.95，NBM 4的最低，为0.50。NBM 1和NBM 3的判定成功率几乎相似（0.60）。NNM 2的成功率与NNM 1的相差不大（0.94）。在NNM 1和NNM 2中，第5阶段的判定成功率相对低于其他阶段（0.83）。
在我们开发的模型中，NNMs比NBMs更成功。确定对鉴别有用的有效比例和/或测量值很重要。
