摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-关于人工智能的详细数据已经呈现出来。根据来自土耳其梅尔辛的新sRx记者的新闻报道，研究称，"本研究旨在建立一种人工智能(AI)算法,自动、准确地确定颈椎成熟度(CVM)的阶段,主要目的是消除人为误差因素,回顾分析颈椎成熟度图像的设置和样本人群档案,并收集1501例全视野颈椎患者的数据."我们的新闻编辑引用了近东大学的研究，“在训练过程中使用符合纳入标准的侧位头影测量学(LC)，使用计算机视觉注释工具(CVAT)进行标记，由经验丰富的正畸医生进行跟踪作为金标准，并且为了限制训练数据集分布不均匀的影响，”用改良的Bachetti法对成熟阶段进行分类，由标记者进行分类。将标记数据随机分为训练集（80%）、测试集（10%）和验证集（10%），进行观察者内、观察者间可靠性、类内相关系数(ICC)和加权Cohen's kappa检验。ICC值为0.973,加权Cohen's Kappa标准差为0.870+/-0.027,表明观察者的可靠性高,两者之间的一致性好,分割网络的整体精度为0.99,平均骰子得分为0.93.。分类网络的准确率为0.802，分类敏感性分别为(青春期前0.78；青春期后0.45；青春期后0.98)，每个分类特异性分别为(青春期前0.94；Pubert AL 0.94；青春期后0.75)。开发的算法显示了确定颈椎成熟阶段的能力，这可能有助于更快的诊断过程，因为人类干预可能导致错误的决策程序，可能影响治疗计划的结果。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Data detailed on Artificial Intelligence have bee n presented. According to news reporting originating from Mersin, Turkey, by New sRx correspondents, research stated, "The aim of this study was to develop an ar tificial intelligence (AI) algorithm to automatically and accurately determine t he stage of cervical vertebra maturation (CVM) with the main purpose being to el iminate the human error factor. Setting and Sample Population Archives of the ce phalometric images were reviewed and the data of 1501 subjects with fully visibl e cervical vertebras were included in this retrospective study." Our news editors obtained a quote from the research from Near East University, " Lateral cephalometric (LC) that met the inclusion criteria were used in the trai ning process, labeling was carried out using a computer vision annotation tool ( CVAT), tracing was done by an experienced orthodontist as a gold standard and, i n 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 (8 0%), 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. 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 betwee n them, the segmentation network achieved a global accuracy of 0.99 and the aver age dice score overall images was 0.93. The classification network achieved an a ccuracy of 0.802, class sensitivity of (pre-pubertal 0.78; pubertal 0.45; post-p ubertal 0.98), respectively, per class specificity of (pre-pubertal 0.94; pubert al 0.94; post-pubertal 0.75), respectively. The developed algorithm showed the a bility 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."
NETL
NSTL