Humbert-Vidan Laia, Castelo Austin H, He Renjie, van Dijk Lisanne V, Rhee Dong Joo, Wang Congjun, Wang He C, Wahid Kareem A, Joshi Sonali, Gerafian Parshan, West Natalie, Kaffey Zaphanlene, Mirbahaeddin Sarah, Curiel Jaqueline, Acharya Samrina, Shekha Amal, Oderinde Praise, Ali Alaa M S, Hope Andrew, Watson Erin, Wesson-Aponte Ruth, Frank Steven J, Barbon Carly E A, Brock Kristy K, Chambers Mark S, Walji Muhammad, Hutcheson Katherine A, Lai Stephen Y, Fuller Clifton D, Naser Mohamed A, Moreno Amy C
Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Phys Imaging Radiat Oncol. 2025 Jul 25;35:100817. doi: 10.1016/j.phro.2025.100817. eCollection 2025 Jul.
Accurate delineation of orodental structures on radiotherapy computed tomography (CT) images is essential for dosimetric assessment and dental decisions. We propose a deep-learning (DL) auto-segmentation framework for individual teeth and mandible/maxilla sub-volumes aligned with the ClinRad osteoradionecrosis staging system.
Mandible and maxilla sub-volumes were manually defined on simulation CT images from 60 clinical cases, differentiating alveolar from basal regions; teeth were labelled individually. For each task, a DL segmentation model was independently trained. A Swin UNETR-based model was used for mandible sub-volumes. For smaller structures (e.g., teeth and maxilla sub-volumes) a two-stage model first used the ResUNet to segment the entire teeth and maxilla regions as a single ROI used to crop the image input for Swin UNETR. In addition to segmentation accuracy and geometric precision, a dose-volume comparison was made between manual and model-predicted segmentations.
Segmentation performance varied across sub-volumes - mean Dice values of 0.85 (mandible basal), 0.82 (mandible alveolar), 0.78 (maxilla alveolar), 0.80 (upper central teeth), 0.69 (upper premolars), 0.76 (upper molars), 0.76 (lower central teeth), 0.70 (lower premolars), 0.71 (lower molars) - with limited applicability in segmenting sub-volumes absent in the data. The maxilla alveolar central sub-volume showed a statistically significant dose-volume difference in both D and D.
We present a novel DL-based auto-segmentation framework of orodental structures, enabling spatial localization of dose-related differences. This tool may enhance image-based bone injury detection and improve clinical decision-making in radiation oncology and dental care for head and neck cancer patients.
在放射治疗计算机断层扫描（CT）图像上准确描绘口腔颌面部结构对于剂量评估和牙科决策至关重要。我们提出了一种深度学习（DL）自动分割框架，用于与临床放射性骨坏死分期系统对齐的单个牙齿以及下颌骨/上颌骨子体积。
在60例临床病例的模拟CT图像上手动定义下颌骨和上颌骨子体积，区分牙槽区域和基底区域；对牙齿进行单独标记。对于每个任务，独立训练一个DL分割模型。基于Swin UNETR的模型用于下颌骨子体积。对于较小的结构（例如牙齿和上颌骨子体积），一个两阶段模型首先使用ResUNet将整个牙齿和上颌骨区域分割为单个感兴趣区域（ROI），用于裁剪输入到Swin UNETR的图像。除了分割准确性和几何精度外，还对手动分割和模型预测分割之间进行了剂量体积比较。
不同子体积的分割性能各不相同——平均骰子系数值分别为0.85（下颌骨基底）、0.82（下颌骨牙槽）、0.78（上颌骨牙槽）、0.80（上颌中切牙）、0.69（上颌前磨牙）、0.76（上颌磨牙）、0.76（下颌中切牙）、0.70（下颌前磨牙）、0.71（下颌磨牙）——在分割数据中不存在的子体积时适用性有限。上颌骨牙槽中央子体积在D和D方面均显示出统计学上显著的剂量体积差异。
我们提出了一种基于DL的口腔颌面部结构自动分割新框架，能够对与剂量相关的差异进行空间定位。该工具可能会增强基于图像的骨损伤检测，并改善头颈癌患者放射肿瘤学和牙科护理中的临床决策。
Zotero 插件
