基于深度学习的自动分割模型用于直肠癌放疗临床靶区与危及器官的局部微调及临床评估
本研究回顾性纳入120例II/III期中低位直肠癌患者,分为训练集60例、外部验证集30例和泛化性评估集30例,对商业深度学习自动分割软件进行局部微调,并与供应商预训练模型比较。局部微调显著提高了临床靶区勾画准确性(p<0.05),在靶区体积、DSC、95HD和特异性上优于预训练模型,在小肠分割上也有显著提升,且在不同CT模拟机采集的泛化性评估集中未出现性能下降。
要点
- 局部微调显著改善临床靶区勾画准确性(p<0.05),靶区体积、DSC、95HD和特异性均优于预训练模型。
- 两种模型对膀胱和股骨头分割准确性均足够,局部微调在小肠分割上有显著提升。
- 在泛化性评估数据集中未发现局部微调模型与预训练模型的性能下降。
核心结论
- 局部微调对深度学习自动分割模型实现机构特异性适配的必要性和潜在获益得到强调。
- 商业深度学习自动分割软件经局部微调后准确性更优,且对成像设备变化具有高度稳健性。
研究设计与样本
- 回顾性纳入120例II/III期中低位直肠癌患者,分为训练集60例、外部验证集30例和泛化性评估集30例。
- 训练集和外部验证集患者图像采集自同一台CT模拟机,泛化性评估集采集自另一台CT模拟机。
- 使用训练数据对商业深度学习自动分割软件进行局部微调,然后在外部验证集和泛化性评估集上分别验证。
- 性能评估将局部微调模型与供应商预训练模型分别与真实轮廓比较,采用Dice相似系数、第95百分位Hausdorff距离、灵敏度和特异性等指标。
主要发现
- 局部微调显著提高了临床靶区勾画准确性(p<0.05),局部微调模型在靶区体积、DSC、95HD和特异性上优于预训练模型。
- 两种模型对膀胱和股骨头均表现出足够的准确性,局部微调在分割更复杂的小肠上有显著提升。
- 局部微调模型和预训练模型应用于泛化性评估数据集时未发现性能下降。
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)。
原文
BACKGROUND AND PURPOSE: Various deep learning auto-segmentation (DLAS) models have been proposed, some of which have been commercialized. However, the issue of performance degradation is notable when pretrained models are deployed in the clinic. This study aims to enhance precision of a popular commercial DLAS product in rectal cancer radiotherapy by localized fine-tuning, addressing challenges in practicality and generalizability in real-world clinical settings. MATERIALS AND METHODS: A total of 120 Stage II/III mid-low rectal cancer patients were retrospectively enrolled and divided into three datasets: training (n = 60), external validation (ExVal, n = 30), and generalizability evaluation (GenEva, n = 30) datasets respectively. The patients in the training and ExVal dataset were acquired on the same CT simulator, while those in GenEva were on a different CT simulator. The commercial DLAS software was first localized fine-tuned (LFT) for clinical target volume (CTV) and organs-at-risk (OAR) using the training data, and then validated on ExVal and GenEva respectively. Performance evaluation involved comparing the LFT model with the vendor-provided pretrained model (VPM) against ground truth contours, using metrics like Dice similarity coefficient (DSC), 95th Hausdorff distance (95HD), sensitivity and specificity. RESULTS: LFT significantly improved CTV delineation accuracy (p < 0.05) with LFT outperforming VPM in target volume, DSC, 95HD and specificity. Both models exhibited adequate accuracy for bladder and femoral heads, and LFT demonstrated significant enhancement in segmenting the more complex small intestine. We did not identify performance degradation when LFT and VPM models were applied in the GenEva dataset. CONCLUSIONS: The necessity and potential benefits of LFT DLAS towards institution-specific model adaption is underscored. The commercial DLAS software exhibits superior accuracy once localized fine-tuned, and is highly robust to imaging equipment changes.
引用
- Geng J, Sui X, Du R, et al. Localized fine-tuning and clinical evaluation of deep-learning based auto-segmentation (DLAS) model for clinical target volume (CTV) and organs-at-risk (OAR) in rectal cancer radiotherapy. Radiat Oncol. 2024. PMID: 38956690. doi:10.1186/s13014-024-02463-0
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。