Artificial intelligence‐based algorithm for cervical vertebrae maturation stage assessment

Abstract

Objective:The aim of this study was to develop an artificial intelligence (AI) algorithm to automatically and accurately determine the stage of cervical vertebra maturation (CVM) with the main purpose being to eliminate the human error factor. Setting and Sample Population:Archives of the cephalometric images were reviewed and the data of 1501 subjects with fully visible cervical vertebras were included in this retrospective study. Materials and Methods:Lateral cephalometric (LC) that met the inclusion criteria were used in the training process, labeling was carried out using a computer vision annotation tool (CVAT), tracing was done by an experienced orthodontist as a gold standard and, in order to limit the effect of the uneven distribution of the training data set, maturation stage was classified with a modified Bachetti method by the operator who labelled them. The labelled data were split randomly into a training set (80%), a testing set (10%) and an validation set (10%), to measure intra-observer, inter-observer reliability, intraclass correlation coefficient (ICC) and weighted Cohen's kappa test was carried out. Results:The ICC was valued at 0.973, weighted Cohen's kappa standard error was 0.870 ± 0.027 which shows high reliability of the observers and excellent level of agreement between them, the segmentation network achieved a global accuracy of 0.99 and the average dice score overall images was 0.93. The classification network achieved an accuracy of 0.802, class sensitivity of (pre-pubertal 0.78; pubertal 0.45; post-pubertal 0.98), respectively, per class specificity of (pre-pubertal 0.94; pubertal 0.94; post-pubertal 0.75), respectively. Conclusion:The developed algorithm showed the ability to determine the cervical vertebrae maturation stage which might aid in a faster diagnosis process by eliminating human intervention, which might lead to wrong decision-making procedures that might affect the outcome of the treatment plan. The developed algorithm proved reliable in determining the pre-pubertal and post-pubertal growth stages with high accuracy.

Improving cervical maturation degree classification accuracy using a multi-stage deep learning approach

“…It is especially useful when there is an uneven distribution of false positives and false negatives. In accordance with the results of the current study, Radwan et al, 12 found the lowest F1-score (57%) in C3, and C4 stages. Also, Zhou et al, 11 proved that C3 had the lowest F1-score (31%).…”

“…This is due to the fact that in many cases, cervical vertebrae maturity encompasses a period between the previous and next stage of development. this might explain the reason why more accurate classi cation results were obtained by Radwan et al, 12 by merging each two subsequent stages into a single class. Similarly, our previously developed three-class classi cation model, which categorized the CVM stages into three classes of pre-pubertal (C1, C2), growth spurt (C3, C4), and post-pubertal (C5, C6), achieved a higher accuracy than our six-class CVM diagnosis model (82.83% V.S.…”

Mapping an intelligent algorithm for predicting female adolescents’ cervical vertebrae maturation stage with high recall and accuracy

“…Recent progress in artificial intelligence (AI) has empowered the execution of tasks such as recognition, segmenting, and classifying in cephalometric radiograph analysis, with the benefit of minimizing interobserver differences [ 29 , 30 ]. AI-assisted algorithms can perform feature extraction in an automated manner, which allows clinicians to extract confused features with minimal domain knowledge and effort [ 31 ]. Kök H et al trained the artificial neural networks (ANN) model with 300 individuals aged between 8 and 17 years and proposed the ANN algorithm was stable in determining the CVM classes with a 2.17 average rank [ 32 ].…”

AI in Orthodontics: Revolutionizing Diagnostics and Treatment Planning

“…The last few years have seen a rise in scientific evidence supporting the diagnostic accuracy and effectiveness of AI in skeletal age assessment, based on both wrist X-rays [83,84] and CVM [85][86][87][88]. Although AI has already proven its diagnostic accuracy in skeletal age assessment, exceeding that of experienced readers in wrist X-rays [83,84] and even index finger X-rays [89], the accuracy of CVMbased models remains a concern [90,91].…”