深度学习在危及器官分割中的泛化能力:宫颈近距离放疗中的迁移学习研究
该研究基于120例在3T磁共振扫描仪上使用环形与串联施源器的扫描图像构建预训练模型,分割并评估4个危及器官,并在三个分布外目标组上进行微调。迁移学习提升了各目标组的分割精度,前5例微调扫描带来最明显改善,且混合模型在未见数据上表现更优。
要点
- 迁移学习可提升宫颈近距离放疗磁共振引导下危及器官自动分割的泛化能力。
- 前5例微调扫描带来的改善最明显,继续增加数据后性能趋于平台。
- 相同训练数据下,迁移学习优于从头训练;混合模型在未见数据上表现更优。
核心结论
- 迁移学习可提升模型在磁共振引导宫颈近距离放疗危及器官分割中的泛化能力,且所需微调数据更少、训练时间更短。
研究设计与样本
- 使用120例在3T磁共振扫描仪(RT3)上采用环形与串联施源器的扫描图像构建预训练模型,分割并评估4个危及器官。
- 分割性能采用体积Dice相似系数(vDSC)、95%豪斯多夫距离(HD95)、表面DSC和附加路径长度(APL)评估。
- 模型在三个分布外目标组上进行微调,比较迁移学习前后结果及微调扫描数量的影响。
- 比较仅用一组训练的模型(Single)与用全部四组训练的模型(Mixed)在已见和未见数据分布上的表现。
主要发现
- 迁移学习提升了各目标组的分割精度,达到与预训练模型相当的性能。
- 前5例微调扫描带来最明显的改善,更多数据后性能趋于平台。
- 相同训练数据下,迁移学习优于从头训练。
- 在RT3扫描上,混合模型与单组模型表现相似,但在未见数据上混合模型表现更优。
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
PURPOSE: Deep learning can automate delineation in radiation therapy, reducing time and variability. Yet, its efficacy varies across different institutions, scanners, or settings, emphasizing the need for adaptable and robust models in clinical environments. Our study demonstrates the effectiveness of the transfer learning (TL) approach in enhancing the generalizability of deep learning models for auto-segmentation of organs-at-risk (OARs) in cervical brachytherapy. METHODS: A pre-trained model was developed using 120 scans with ring and tandem applicator on a 3T magnetic resonance (MR) scanner (RT3). Four OARs were segmented and evaluated. Segmentation performance was evaluated by Volumetric Dice Similarity Coefficient (vDSC), 95 % Hausdorff Distance (HD95), surface DSC, and Added Path Length (APL). The model was fine-tuned on three out-of-distribution target groups. Pre- and post-TL outcomes, and influence of number of fine-tuning scans, were compared. A model trained with one group (Single) and a model trained with all four groups (Mixed) were evaluated on both seen and unseen data distributions. RESULTS: TL enhanced segmentation accuracy across target groups, matching the pre-trained model's performance. The first five fine-tuning scans led to the most noticeable improvements, with performance plateauing with more data. TL outperformed training-from-scratch given the same training data. The Mixed model performed similarly to the Single model on RT3 scans but demonstrated superior performance on unseen data. CONCLUSIONS: TL can improve a model's generalizability for OAR segmentation in MR-guided cervical brachytherapy, requiring less fine-tuning data and reduced training time. These results provide a foundation for developing adaptable models to accommodate clinical settings.
引用
- Ni R, Han K, Haibe-Kains B, et al. Generalizability of deep learning in organ-at-risk segmentation: A transfer learning study in cervical brachytherapy. Radiother Oncol. 2024. PMID: 38763356. doi:10.1016/j.radonc.2024.110332
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。