After nasal bone fractures, fractures of the mandible are the most frequently encountered injuries of the facial skeleton. Accurate identification of fracture locations is critical for effectively managing these injuries. To address this need, JawFracNet, an innovative artificial intelligence method, has been developed to enable automated detection of mandibular fractures in cone-beam computed tomography (CBCT) scans. JawFracNet employs a 3-stage neural network model that processes 3-dimensional patches from a CBCT scan. Stage 1 predicts a segmentation mask of the mandible in a patch, which is subsequently used in stage 2 to predict a segmentation of the fractures and in stage 3 to classify whether the patch contains any fracture. The final output of JawFracNet is the fracture segmentation of the entire scan, obtained by aggregating and unifying voxel-level and patch-level predictions. A total of 164 CBCT scans without mandibular fractures and 171 CBCT scans with mandibular fractures were included in this study. Evaluation of JawFracNet demonstrated a precision of 0.978 and a sensitivity of 0.956 in detecting mandibular fractures. The current study proposes the first benchmark for mandibular fracture detection in CBCT scans. Straightforward replication is promoted by publicly sharing the code and providing access to JawFracNet on grand-challenge.org.

中文翻译：

---

使用 3 阶段神经网络在 CBCT 扫描中检测下颌骨骨折


鼻骨骨折后，下颌骨骨折是面部骨骼最常见的损伤。准确识别骨折位置对于有效管理这些损伤至关重要。为了满足这一需求，JawFracNet 是一种创新的人工智能方法，可在锥形束计算机断层扫描 （CBCT） 扫描中自动检测下颌骨骨折。JawFracNet 采用 3 阶段神经网络模型来处理来自 CBCT 扫描的 3D 补丁。第 1 阶段预测补片中下颌骨的分割掩码，随后在第 2 阶段用于预测骨折的分割，在第 3 阶段用于分类补片是否包含任何骨折。JawFracNet 的最终输出是整个扫描的断裂分割，通过聚合和统一体素级和补丁级预测获得。本研究共纳入 164 例无下颌骨骨折的 CBCT 扫描和 171 例有下颌骨骨折的 CBCT 扫描。对 JawFracNet 的评估表明，检测下颌骨骨折的精度为 0.978，灵敏度为 0.956。目前的研究提出了 CBCT 扫描中下颌骨骨折检测的第一个基准。通过在 grand-challenge.org 上公开共享代码并提供对 JawFracNet 的访问，促进了直接复制。