Leclercq Mathieu, Ruellas Antonio, Gurgel Marcela, Yatabe Marilia, Bianchi Jonas, Cevidanes Lucia, Styner Martin, Paniagua Beatriz, Prieto Juan Carlos
University of North Carolina, Chapel Hill, United States.
University of Michigan, Ann Arbor, United States.
Proc IEEE Int Symp Biomed Imaging. 2023 Apr;2023. doi: 10.1109/isbi53787.2023.10230397. Epub 2023 Sep 1.
In this paper, we present a deep learning-based method for surface segmentation. This technique consists of acquiring 2D views and extracting features from the surface such as the normal vectors. The rendered images are analyzed with a 2D convolutional neural network, such as a UNET. We test our method in a dental application for the segmentation of dental crowns. The neural network is trained for multi-class segmentation, using image labels as ground truth. A 5-fold cross-validation was performed, and the segmentation task achieved an average Dice of 0.97, sensitivity of 0.98 and precision of 0.98. Our method and algorithms are available as a 3DSlicer extension.
在本文中，我们提出了一种基于深度学习的表面分割方法。该技术包括获取二维视图并从表面提取诸如法向量等特征。使用二维卷积神经网络（如UNET）对渲染图像进行分析。我们在牙科应用中测试了我们的方法，用于牙冠分割。使用图像标签作为真实值对神经网络进行多类分割训练。进行了五折交叉验证，分割任务的平均骰子系数为0.97，灵敏度为0.98，精度为0.98。我们的方法和算法可作为3DSlicer扩展使用。
