使用基于补丁的深度神经网络的自动三维地标模型用于口腔颌面外科CT图像
Automatic 3D landmarking model using patch-based deep neural networks for CT image of oral and maxillofacial surgery.
作者信息
Ma Qingchuan, Kobayashi Etsuko, Fan Bowen, Nakagawa Keiichi, Sakuma Ichiro, Masamune Ken, Suenaga Hideyuki
机构信息
Department of Oral-Maxillofacial Surgery and Orthodontics, The University of Tokyo Hospital, Tokyo, Japan.
Institute of Advanced BioMedical Engineering and Science, Tokyo Women's Medical University, Tokyo, Japan.
出版信息
Int J Med Robot. 2020 Jun;16(3):e2093. doi: 10.1002/rcs.2093. Epub 2020 Mar 20.
BACKGROUND
Manual landmarking is a time consuming and highly professional work. Although some algorithm-based landmarking methods have been proposed, they lack flexibility and may be susceptible to data diversity.
METHODS
The CT images from 66 patients who underwent oral and maxillofacial surgery (OMS) were landmarked manually in MIMICS. Then the CT slices were exported as images for recreating the 3D volume. The coordinate data of landmarks were further processed in Matlab using a principal component analysis (PCA) method. A patch-based deep neural network model with a three-layer convolutional neural network (CNN) was trained to obtain landmarks from CT images.
RESULTS
The evaluating experiment showed that this CNN model could automatically finish landmarking in an average processing time of 37.871 seconds with an average accuracy of 5.785 mm.
CONCLUSION
This study shows a promising potential to relieve the workload of the surgeon and reduces the dependence on human experience for OMS landmarking.
背景
手动标注界标是一项耗时且专业性很强的工作。尽管已经提出了一些基于算法的界标标注方法，但它们缺乏灵活性，并且可能易受数据多样性的影响。
方法
对66例接受口腔颌面外科手术（OMS）的患者的CT图像在MIMICS中进行手动界标标注。然后将CT切片导出为图像以重建三维体积。使用主成分分析（PCA）方法在Matlab中进一步处理界标坐标数据。训练一个具有三层卷积神经网络（CNN）的基于补丁的深度神经网络模型，以从CT图像中获取界标。
结果
评估实验表明，该CNN模型能够在平均37.871秒的处理时间内自动完成界标标注，平均精度为5.785毫米。
结论
本研究显示出减轻外科医生工作量并减少口腔颌面外科手术界标标注对人类经验依赖的潜在前景。
Zotero 插件