基于卷积神经网络的头影测量标志点自动识别与定位
研究开发了基于卷积神经网络的CephaNET模型,用于头颅侧位X线片缺失标志点的自动识别与定位。使用481张头颅侧位X线片建立数据集,模型可识别61个常用标志点,平均耗时0.13秒,缺失标志点识别平均准确率93.5%,测试集平均径向误差(1.19±0.91)mm。
要点
- CephaNET可在0.13秒内自动定位61个常用头影测量标志点。
- 缺失标志点识别平均准确率93.5%,Cv点92.7%,Bolton点94.3%。
- 测试集平均径向误差(1.19±0.91)mm,2.0 mm内成功检测率85.4%。
核心结论
- CephaNET模型可适应头颅侧位X线片标志点缺失情况,并高精度定位61个常用标志点,满足不同头影测量分析要求。
研究设计与样本
- 收集2015年1月至2021年1月首都医科大学口腔医学院正畸科481张头颅侧位X线片,男240张、女241张,年龄(24.5±5.6)岁。
- 5名正畸专业研究生手动定位61个标志点,2名主治医师审核校准,2名主任医师仲裁决策。
- 研发基于CNN的CephaNET模型,包含特征提取模块和卷积姿态机模块,采用深监督技术训练。
主要发现
- 模型平均在0.13秒内识别并定位61个常用标志点。
- 缺失标志点识别平均准确率93.5%,Cv点识别成功率92.7%(38/41),Bolton点94.3%(50/53)。
- 测试集平均径向误差(MRE)为(1.19±0.91)mm。
- 2.0、2.5、3.0、3.5、4.0 mm范围内成功检测率(SDR)分别为85.4%、90.2%、93.5%、95.4%、97.0%。
关键数值与推荐
- 评价标准包括缺失标志点(Cv点和Bolton点)识别成功率、平均径向误差(MRE)及2.0至4.0 mm范围内成功检测率(SDR)。
临床怎么用
- 该模型可用于头颅侧位X线片标志点缺失情况下的自动定点,辅助正畸头影测量分析。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Objective: To develop an automated landmark location system applicable to the case of landmark missing. Methods: Four and eighty-one lateral cephalograms, which contained 240 males and 241 females, with an average age of (24.5±5.6) years, taken from January 2015 to January 2021 in the Department of Orthodontics, Capital Medical University School of Stomatology, and met the inclusion criteria were collected. Five postgraduate orthodontic students were the annotators to manually locate 61 possible landmarks in 481 lateral cephalograms. Two assistant professors in the department as reviewers performed calibration. Two professors as arbitrators, made final decision. Data sets were established (341 were used as training set, 40 as validation set, and 100 as test set). In this paper, an automatic landmarks identification and location model based on convolutional neural networks (CNN), CephaNET, was developed. The model was trained by feeding the original image into the feature extraction module and convolutional pose machine (CPM) module to locate landmarks with high accuracy using deep supervision. Training set was enhanced to 1 684 images by histogram equalization, cropping, and adjustment of brightness. The model was trained to compare the Gaussian heat maps output from the network with the set threshold to identify landmark missing cases. Test set of 100 lateral cephalograms was used to test the accuracy of the model. The evaluation criteria used were success detection rate of missing landmark, mean radial error (MRE) and success detection rate (SDR) in the range of 2.0, 2.5, 3.0, 3.5 and 4.0 mm. Results: The model identified and located 61 commonly used landmarks in 0.13 seconds on average. It had an average accuracy of 93.5% in identifying missing landmarks. The MRE of our testing set was (1.19±0.91) mm. SDR of 2.0, 2.5, 3.0, 3.5 and 4.0 mm were 85.4%, 90.2%, 93.5%, 95.4%, 97.0% respectively. Conclusions: The model proposed in this paper could adapt to the absence of landmark in lateral cephalograms and locate 61 commonly used landmarks with high accuracy to meet the requirements of different cephalometric analysis methods. 目的: 基于卷积神经网络开发头影测量自动定点模型,以期为智能识别头颅侧位X线片上缺失的标志点并高精度实现头影测量自动定点提供参考。 方法: 收集2015年1月至2021年1月于首都医科大学口腔医学院正畸科就诊的错(牙合)畸形患者的481张头颅侧位X线片,其中男性240张,女性241张,年龄(24.5±5.6)岁。以5名正畸专业研究生为标注人员,手动定位481张头颅侧位X线片中的61个头影测量标志点;以2名正畸主治医师为审核人员,进行定点校准;以2名正畸主任医师为仲裁人员,作出最终决策。建立数据集:其中341张作为训练集,40张作为验证集,100张作为测试集。研发一种基于卷积神经网络(CNN)的自动定点模型CephaNET,通过将原始图像输入特征提取模块和卷积姿态机模块,使用深监督技术,训练CephaNET模型高精度定位标志点;将训练集通过直方图均衡化、裁剪、调节亮度,增强为1 684张,训练模型对比网络输出的高斯热力图与设置的阈值,以识别标志点缺失情况。测试集100张头颅侧位X线片用于检测模型的准确性。评价标准使用缺失标志点[颈点(Cv点)和Bolton点]识别成功率、平均径向误差(MRE)以及2.0、2.5、3.0、3.5和4.0 mm范围内成功检测率(SDR)。 结果: 针对1张头影测量X线片,CephaNET模型平均在0.13 s内识别并定位61个常用标志点;Cv点识别成功率为92.7%(38/41),Bolton点识别成功率为94.3%(50/53),平均为93.5%。测试集MRE为(1.19±0.91)mm,2.0、2.5、3.0、3.5和4.0 mm范围内SDR分别为85.4%、90.2%、93.5%、95.4%、97.0%。 结论: 本项研究研发的自动定点模型可适应头颅侧位X线片标志点缺失的情况,并高精度定位61个常用的头影测量标志点,满足不同头影测量分析要求。.
引用
- Gong BW, Chang S, Zuo FF, et al. [Automated cephalometric landmark identification and location based on convolutional neural network]. Zhonghua Kou Qiang Yi Xue Za Zhi. 2023. PMID: 38061867. doi:10.3760/cma.j.cn112144-20230829-00118
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。