[论文解读] Automatic Three-Dimensional Cephalometric Annotation System Using Three-Dimensional Convolutional Neural Networks

Sung Ho Kang, Kiwan Jeon+3 more|arXiv (Cornell University)|Nov 19, 2018

Dental Radiography and Imaging参考文献 27被引用 6

一句话总结

本文提出一种用于CT扫描自动三维头影测量标志点标注的3D卷积神经网络（3D-CNN）系统，通过图像重采样提升空间精度。系统在x、y和z轴上的平均预测误差分别为3.26 mm、3.18 mm和4.81 mm，三维距离误差为7.61 mm，表明在不同解剖区域间具有高度一致性。

ABSTRACT

Background: Three-dimensional (3D) cephalometric analysis using computerized tomography data has been rapidly adopted for dysmorphosis and anthropometry. Several different approaches to automatic 3D annotation have been proposed to overcome the limitations of traditional cephalometry. The purpose of this study was to evaluate the accuracy of our newly-developed system using a deep learning algorithm for automatic 3D cephalometric annotation. Methods: To overcome current technical limitations, some measures were developed to directly annotate 3D human skull data. Our deep learning-based model system mainly consisted of a 3D convolutional neural network and image data resampling. Results: The discrepancies between the referenced and predicted coordinate values in three axes and in 3D distance were calculated to evaluate system accuracy. Our new model system yielded prediction errors of 3.26, 3.18, and 4.81 mm (for three axes) and 7.61 mm (for 3D). Moreover, there was no difference among the landmarks of the three groups, including the midsagittal plane, horizontal plane, and mandible (p>0.05). Conclusion: A new 3D convolutional neural network-based automatic annotation system for 3D cephalometry was developed. The strategies used to implement the system were detailed and measurement results were evaluated for accuracy. Further development of this system is planned for full clinical application of automatic 3D cephalometric annotation.

研究动机与目标

• 为克服人工及传统2D头影测量分析在3D颅面评估中的局限性。
• 开发一种基于深度学习的系统，能够高精度地自动标注CT数据中的三维颅骨标志点。
• 评估系统在不同解剖区域（包括矢状中平面、横平面和下颌）的性能表现。
• 建立一个稳健的自动化流程，适用于临床集成的3D头影测量标注。

提出的方法

• 训练3D卷积神经网络（3D-CNN）以直接预测颅骨CT容积中解剖标志点的3D坐标。
• 应用图像重采样技术以提升空间分辨率，并改善3D特征空间中的定位精度。
• 采用回归损失函数优化网络，以最小化预测坐标与真实坐标之间的差异。
• 系统处理全头CT扫描，输出每个目标标志点的3D坐标。
• 使用各轴上的平均绝对误差（MAE）和三维欧几里得距离评估性能。

实验结果

研究问题

• RQ1 3D-CNN模型能否在CT扫描上实现准确且一致的自动三维头影测量标志点标注？
• RQ2 该系统在不同解剖区域（如矢状中平面、横平面和下颌）的表现如何？
• RQ3 图像重采样在多大程度上提升了3D深度学习模型中的标志点定位精度？
• RQ4 预测误差在所有标志点组之间是否分布均匀？

主要发现

• 系统在x轴上的平均预测误差为3.26 mm，y轴为3.18 mm，z轴为4.81 mm。
• 预测标志点与参考标志点之间的平均三维欧几里得距离误差为7.61 mm。
• 在三个解剖组之间未发现误差的统计学显著差异（p > 0.05），表明性能一致。
• 所提出的方法在利用深度学习实现自动化3D头影测量标注方面具有可行性。