文献速递头颈技术与安全CT

对比剂对基于深度学习软件「Ai-Seg」头颈癌分割的影响

Impact of contrast-enhanced agent on segmentation using a deep learning-based software "Ai-Seg" for head and neck cancer.
PubMed 文献 · Br J Radiol · 2025-01-01

该回顾性研究纳入321例头颈癌患者,用增强CT训练Ai-Seg分割模型(CE模型),并在另外25例患者的增强与非增强CT上评估。CE模型在增强CT上对腮腺和下颌下腺的DSC显著高于现有模型;在非增强CT上除下颌下腺外其余OAR性能与增强CT相当。

要点

  • CE模型在增强CT上对腮腺和下颌下腺的DSC显著高于现有模型。
  • CE模型用于非增强CT时,除下颌下腺外其他OAR性能与增强CT无显著差异。
  • 非增强CT上颌下腺的DSC显著低于增强CT、AHD显著高于增强CT。

核心结论

  • CE模型性能显著优于现有模型,且除下颌下腺外可用于非增强CT而无显著性能差异,结果可能促进分割工具在临床实践中的应用。

研究设计与样本

  • 回顾性研究,纳入321例头颈癌患者,使用增强CT训练专用分割模型(CE模型)并装入Ai-Seg。

诊断标准与关键数值

  • 以Dice相似系数(DSC)和平均Hausdorff距离(AHD)评估脑、脑干、视交叉、视神经、耳蜗、口腔、腮腺、咽缩肌和下颌下腺的分割精度。
  • CE模型在增强CT上对腮腺和下颌下腺的DSC显著高于现有非增强CT训练模型。
  • CE模型在非增强CT上对下颌下腺的DSC显著低于增强CT、AHD显著高于增强CT,其余OAR两者相当。

临床应用与阅片要点

  • CE模型可用于增强CT头颈OAR分割,在非增强CT上除下颌下腺外性能无显著差异。
  • 使用非增强CT时需注意下颌下腺分割精度可能下降。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: In radiotherapy, auto-segmentation tools using deep learning assist in contouring organs-at-risk (OARs). We developed a segmentation model for head and neck (HN) OARs dedicated to contrast-enhanced (CE) computed tomography (CT) using the segmentation software, Ai-Seg, and compared the performance between CE and non-CE (nCE) CT.

METHODS: The retrospective study recruited 321 patients with HN cancers and trained a segmentation model using CE CT (CE model). The CE model was installed in Ai-Seg and applied to additional 25 patients with CE and nCE CT. The Dice similarity coefficient (DSC) and average Hausdorff distance (AHD) were calculated between the ground truth and Ai-Seg contours for brain, brainstem, chiasm, optic nerves, cochleae, oral cavity, parotid glands, pharyngeal constrictor muscle, and submandibular glands (SMGs). We compared the CE model and the existing model trained with nCE CT available in Ai-Seg for 6 OARs.

RESULTS: The CE model obtained significantly higher DSCs on CE CT for parotid and SMGs compared to the existing model. The CE model provided significantly lower DSC values and higher AHD values on nCE CT for SMGs than on CE CT, but comparable values for other OARs.

CONCLUSIONS: The CE model achieved significantly better performance than the existing model and can be used on nCE CT images without significant performance difference, except SMGs. Our results may facilitate the adoption of segmentation tools in clinical practice.

ADVANCES IN KNOWLEDGE: We developed a segmentation model for HN OARs dedicated to CE CT using Ai-Seg and evaluated its usability on nCE CT.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Kihara S, Ueda Y, Harada S, et al. Impact of contrast-enhanced agent on segmentation using a deep learning-based software "Ai-Seg" for head and neck cancer. Br J Radiol. 2025. PMID: 40419459. doi:10.1093/bjr/tqaf108

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。