AI肿瘤勾画用于早期NSCLC所有呼吸时相
本研究基于214例接受SBRT的早期NSCLC患者4D-CT数据,训练深度学习算法在所有呼吸时相自动勾画GTV。Swin+Dyn混合模型表现最佳,生成的ITV与真实值表面DSC为0.79±0.16(10时相)和0.77±0.14(2时相),有望减少勾画时间和观察者间变异。
要点
- Swin+Dyn混合模型在GTV 50%的表面DSC达0.79±0.14。
- 基于10个呼吸时相生成的ITV表面DSC为0.79±0.16。
- 仅用最大吸气/呼气2个时相生成的ITV表面DSC为0.77±0.14。
核心结论
- Swin+Dyn Net算法在最大呼气CT上训练后能有效勾画所有呼吸时相的GTV,生成的ITV与真实值一致性良好。
研究设计与样本
- 回顾性研究,使用214例接受SBRT的早期NSCLC患者4D-CT数据,每例含10个重建呼吸时相,按75%训练集和25%测试集划分。
- 训练并评估SwinUNetR、Dynamic UNet及两者混合模型(Swin+Dyn),以DSC、3 mm SDSC和HD95为评价指标。
主要发现
- Swin+Dyn模型性能最高,测试集GTV 50%的SDSC为0.79±0.14。
- ITV的SDSC在使用全部10个呼吸时相时为0.79±0.16,使用2个呼吸时相时为0.77±0.14。
- 体素水平上,Swin+DynNet对2呼吸时相ITV的敏感度为0.75±0.14、精确度为0.84±0.10。
- 体素水平上,Swin+DynNet对10呼吸时相ITV的敏感度为0.79±0.12、精确度为0.80±0.11。
临床怎么用
- 该算法可在NSCLC SBRT流程中辅助自动勾画所有呼吸时相的GTV并生成ITV,有望减少勾画时间和勾画者间变异。
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 AND PURPOSE: Accurate delineation of the Gross Tumor Volume (GTV) and the Internal Target Volume (ITV) in early-stage lung tumors is crucial in Stereotactic Body Radiation Therapy (SBRT). Traditionally, the ITVs, which account for breathing motion, are generated by manually contouring GTVs across all breathing phases (BPs), a time-consuming process. This research aims to streamline this workflow by developing a deep learning algorithm to automatically delineate GTVs in all four-dimensional computed tomography (4D-CT) BPs for early-stage Non-Small Cell Lung Cancer Patients (NSCLC). METHODS: A dataset of 214 early-stage NSCLC patients treated with SBRT was used. Each patient had a 4D-CT scan containing ten reconstructed BPs. The data were divided into a training set (75 %) and a testing set (25 %). Three models SwinUNetR and Dynamic UNet (DynUnet), and a hybrid model combining both (Swin + Dyn)were trained and evaluated using the Dice Similarity Coefficient (DSC), 3 mm Surface Dice Similarity Coefficient (SDSC), and the 95th percentile Hausdorff distance (HD95). The best performing model was used to delineate GTVs in all test set BPs, creating the ITVs using two methods: all 10 phases and the maximum inspiration/expiration phases. The ITVs were compared to the ground truth ITVs. RESULTS: The Swin + Dyn model achieved the highest performance, with a test set SDSC of 0.79 ± 0.14 for GTV 50 %. For the ITVs, the SDSC was 0.79 ± 0.16 using all 10 BPs and 0.77 ± 0.14 using 2 BPs. At the voxel level, the Swin + DynNet network achieved a sensitivity of 0.75 ± 0.14 and precision of 0.84 ± 0.10 for the ITV 2 breathing phases, and a sensitivity of 0.79 ± 0.12 and precision of 0.80 ± 0.11 for the 10 breathing phases. CONCLUSION: The Swin + Dyn Net algorithm, trained on the maximum expiration CT-scan effectively delineated gross tumor volumes in all breathing phases and the resulting ITV showed a good agreement with the ground truth (surface DSC = 0.79 ± 0.16 using all 10 BPs and 0.77 ± 0.14 using 2 BPs.). The proposed approach could reduce delineation time and inter-performer variability in the tumor contouring process for NSCLC SBRT workflows.
引用
- DelaO-Arevalo LR, Sijtsema NM, van Dijk LV, et al. "AI tumor delineation for all breathing phases in early-stage NSCLC". Radiother Oncol. 2025. PMID: 40789427. doi:10.1016/j.radonc.2025.111095
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。