Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity of CMF bony structures, it is difficult to localize landmarks efficiently and accurately. In this paper, we propose a deep learning framework to tackle this challenge by jointly digitalizing 105 CMF landmarks on CBCT images. By explicitly learning the local geometrical relationships between the landmarks, our approach extends Mask R-CNN for end-to-end prediction of landmark locations. Specifically, we first apply a detection network on a down-sampled 3D image to leverage global contextual information to predict the approximate locations of the landmarks. We subsequently leverage local information provided by higher-resolution image patches to refine the landmark locations. On patients with varying non-syndromic jaw deformities, our method achieves an average detection accuracy of 1.38± 0.95mm, outperforming a related state-of-the-art method.

中文翻译：

---

使用 3D Mask R-CNN 和局部依赖学习对 CBCT 图像上的颅颌面标志进行定位

头影测量分析依赖于锥束计算机断层扫描 (CBCT) 图像中颅颌面 (CMF) 标志的准确检测。然而，由于CMF骨结构的复杂性，很难有效、准确地定位标志。在本文中，我们提出了一个深度学习框架，通过联合数字化 CBCT 图像上的 105 个 CMF 地标来应对这一挑战。通过显式学习地标之间的局部几何关系，我们的方法扩展了 Mask R-CNN，用于地标位置的端到端预测。具体来说，我们首先在下采样的 3D 图像上应用检测网络，以利用全局上下文信息来预测地标的大致位置。随后，我们利用更高分辨率图像块提供的局部信息来细化地标位置。对于患有不同非综合征性颌畸形的患者，我们的方法实现了 1.38±0.95mm 的平均检测精度，优于相关的最先进方法。