Torosdagli Neslisah, Anwar Syed, Verma Payal, Liberton Denise K, Lee Janice S, Han Wade W, Bagci Ulas
University of Central Florida, Orlando, Florida, United States.
Children's National Hospital, Sheikh Zayed Institute, Washington, District of Columbia, United States.
J Med Imaging (Bellingham). 2023 Mar;10(2):024002. doi: 10.1117/1.JMI.10.2.024002. Epub 2023 Mar 6.
We perform anatomical landmarking for craniomaxillofacial (CMF) bones without explicitly segmenting them. Toward this, we propose a simple, yet efficient, deep network architecture, called relational reasoning network (RRN), to accurately learn the local and the global relations among the landmarks in CMF bones; specifically, mandible, maxilla, and nasal bones.
The proposed RRN works in an end-to-end manner, utilizing learned relations of the landmarks based on dense-block units. For a given few landmarks as input, RRN treats the landmarking process similar to a data imputation problem where predicted landmarks are considered missing.
We applied RRN to cone-beam computed tomography scans obtained from 250 patients. With a fourfold cross-validation technique, we obtained an average root mean squared error of per landmark. Our proposed RRN has revealed unique relationships among the landmarks that help us in inferring informativeness of the landmark points. The proposed system identifies the missing landmark locations accurately even when severe pathology or deformations are present in the bones.
Accurately identifying anatomical landmarks is a crucial step in deformation analysis and surgical planning for CMF surgeries. Achieving this goal without the need for explicit bone segmentation addresses a major limitation of segmentation-based approaches, where segmentation failure (as often is the case in bones with severe pathology or deformation) could easily lead to incorrect landmarking. To the best of our knowledge, this is the first-of-its-kind algorithm finding anatomical relations of the objects using deep learning.
我们在不进行颅颌面（CMF）骨骼明确分割的情况下对其进行解剖定位。为此，我们提出了一种简单而高效的深度网络架构，称为关系推理网络（RRN），以准确学习CMF骨骼（具体为下颌骨、上颌骨和鼻骨）中各标志点之间的局部和全局关系。
所提出的RRN以端到端的方式工作，利用基于密集块单元学习到的标志点关系。对于给定的少数几个标志点作为输入，RRN将定位过程视为类似于数据插补问题，其中预测的标志点被视为缺失值。
我们将RRN应用于从250名患者获得的锥束计算机断层扫描。通过四倍交叉验证技术，我们获得了每个标志点平均均方根误差为 。我们提出的RRN揭示了标志点之间独特的关系，这有助于我们推断标志点的信息性。即使骨骼中存在严重病变或变形，所提出的系统也能准确识别缺失的标志点位置。
准确识别解剖标志点是CMF手术变形分析和手术规划中的关键步骤。在无需进行明确骨骼分割的情况下实现这一目标解决了基于分割方法的一个主要局限性，即分割失败（在有严重病变或变形的骨骼中经常出现这种情况）很容易导致错误的定位。据我们所知，这是同类算法中首个使用深度学习来发现物体解剖关系的算法。
