基于三维U-Net的上颌骨与下颌骨亚结构深度学习自动分割的设计与评估
本研究将上颌骨和下颌骨划分为12个亚结构,利用82例头颈部肿瘤患者CT扫描训练三维U-Net模型,并在20例独立CT扫描上与手动分割对比。自动分割中位耗时86秒,手动分割中位耗时53.5分钟;各亚结构中位DSC为0.81–0.91,中位HD95为1.61–4.22,上颌骨亚结构指标低于下颌骨亚结构。
要点
- 自动分割中位耗时86秒,手动分割中位耗时53.5分钟。
- 各亚结构中位DSC为0.81–0.91,中位HD95为1.61–4.22。
- 伪影数量未影响上述评分,上颌骨亚结构指标低于下颌骨亚结构。
核心结论
- 颌骨亚结构分割在含金属伪影与不含金属伪影的CT扫描中均表现出高准确度、时间效率和良好结果。
- 该新模型有望进一步研究剂量与放射性骨坏死或牙种植失败的关系,用于正常组织并发症预测模型。
研究设计与样本
- 将下颌骨和上颌骨划分为12个亚结构。
- 模型基于82例头颈部肿瘤患者的CT扫描开发,采用编码器-解码器三维U-Net结构。
- 在另外20例独立CT扫描上,将自动分割与手动分割进行效率与准确度对比。
- 评估指标为Dice相似系数(DSC)、95%豪斯多夫距离(HD95)和表面DSC(sDSC)。
主要发现
- 自动分割中位耗时86秒,手动分割中位耗时53.5分钟。
- 各亚结构中位DSC为0.81–0.91,中位HD95为1.61–4.22。
- 伪影数量未影响上述评分。
- 上颌骨亚结构的指标低于下颌骨亚结构。
关键数值与推荐
- 各亚结构中位DSC为0.81–0.91。
- 各亚结构中位HD95为1.61–4.22。
- 自动分割中位耗时86秒,手动分割中位耗时53.5分钟。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Current segmentation approaches for radiation treatment planning in head and neck cancer patients (HNCP) typically consider the entire mandible as an organ at risk, whereas segmentation of the maxilla remains uncommon. Accurate risk assessment for osteoradionecrosis (ORN) or implant-based dental rehabilitation after radiation therapy may require a nuanced analysis of dose distribution in specific mandibular and maxillary segments. Manual segmentation is time-consuming and inconsistent, and there is no definition of jaw subsections. MATERIALS AND METHODS: The mandible and maxilla were divided into 12 substructures. The model was developed from 82 computed tomography (CT) scans of HNCP and adopts an encoder-decoder three-dimensional (3D) U-Net structure. The efficiency and accuracy of the automated method were compared against manual segmentation on an additional set of 20 independent CT scans. The evaluation metrics used were the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and surface DSC (sDSC). RESULTS: Automated segmentations were performed in a median of 86 s, compared to manual segmentations, which took a median of 53.5 min. The median DSC per substructure ranged from 0.81 to 0.91, and the median HD95 ranged from 1.61 to 4.22. The number of artifacts did not affect these scores. The maxillary substructures showed lower metrics than the mandibular substructures. CONCLUSIONS: The jaw substructure segmentation demonstrated high accuracy, time efficiency, and promising results in CT scans with and without metal artifacts. This novel model could provide further investigation into dose relationships with ORN or dental implant failure in normal tissue complication prediction models.
引用
- Melerowitz L, Sreenivasa S, Nachbar M, et al. Design and evaluation of a deep learning-based automatic segmentation of maxillary and mandibular substructures using a 3D U-Net. Clin Transl Radiat Oncol. 2024. PMID: 38712013. doi:10.1016/j.ctro.2024.100780
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。