文献速递头颈部肿瘤放疗放疗物理与技术

三维深度学习正常组织并发症概率模型预测头颈癌患者晚期口干症

Three-Dimensional Deep Learning Normal Tissue Complication Probability Model to Predict Late Xerostomia in Patients With Head and Neck Cancer.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2024-08-13

研究基于2个机构1208例头颈癌患者,训练并两次验证深度学习模型(输入三维剂量分布、CT、危及器官分割及临床变量),预测放疗后12个月中重度口干症。所有深度学习模型在独立测试中AUC为0.78-0.79,优于参考模型AUC 0.74;外部验证AUC为0.63,低于参考模型AUC 0.66,迁移学习后深度学习模型AUC为0.66,优于参考模型AUC 0.64。

要点

  • 深度学习NTCP模型在同机构独立测试中AUC 0.78-0.79,优于参考模型AUC 0.74。
  • 外部验证中深度学习模型AUC 0.63,低于参考模型AUC 0.66。
  • 迁移学习后深度学习模型外部AUC 0.66,优于参考模型AUC 0.64。

核心结论

  • 深度学习NTCP模型在同机构数据验证中表现优于参考模型。
  • 通过迁移学习可提升外部数据集性能,表明需要多中心训练数据以实现可泛化的深度学习NTCP模型。

研究设计与样本

  • 国际多中心队列研究,纳入2个机构共1208例头颈癌患者,用于训练并两次验证深度学习模型。
  • 深度学习模型包括深度卷积神经网络、EfficientNet-v2和ResNet,输入为三维剂量分布、CT扫描、危及器官分割、基线口干症评分、性别和年龄。
  • NTCP终点为放疗后12个月中重度口干症。
  • 参考模型为近期发表的口干症NTCP模型,输入基线口干症评分和唾液腺平均剂量。
  • 进行了迁移学习以提升深度学习模型在外部验证集上的性能。

主要发现

  • 所有深度学习NTCP模型在独立测试中AUC为0.78-0.79,优于参考模型AUC 0.74。
  • 注意力图显示深度学习模型关注主要唾液腺,尤其是腮腺富含干细胞的区域。
  • 深度学习模型外部验证AUC为0.63,低于参考模型AUC 0.66。
  • 在小型外部子集上进行迁移学习后,深度学习模型外部AUC为0.66,优于参考模型AUC 0.64。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文指出需要多中心训练数据以实现可泛化的深度学习NTCP模型。

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: Conventional normal tissue complication probability (NTCP) models for patients with head and neck cancer are typically based on single-value variables, which, for radiation-induced xerostomia, are baseline xerostomia and mean salivary gland doses. This study aimed to improve the prediction of late xerostomia by using 3-dimensional information from radiation dose distributions, computed tomography imaging, organ-at-risk segmentations, and clinical variables with deep learning (DL). METHODS AND MATERIALS: An international cohort of 1208 patients with head and neck cancer from 2 institutes was used to train and twice validate DL models (deep convolutional neural network, EfficientNet-v2, and ResNet) with 3-dimensional dose distribution, computed tomography scan, organ-at-risk segmentations, baseline xerostomia score, sex, and age as input. The NTCP endpoint was moderate-to-severe xerostomia 12 months postradiation therapy. The DL models' prediction performance was compared with a reference model: a recently published xerostomia NTCP model that used baseline xerostomia score and mean salivary gland doses as input. Attention maps were created to visualize the focus regions of the DL predictions. Transfer learning was conducted to improve the DL model performance on the external validation set. RESULTS: All DL-based NTCP models showed better performance (area under the receiver operating characteristic curve [AUC]test, 0.78-0.79) than the reference NTCP model (AUCtest, 0.74) in the independent test. Attention maps showed that the DL model focused on the major salivary glands, particularly the stem cell-rich region of the parotid glands. DL models obtained lower external validation performance (AUCexternal, 0.63) than the reference model (AUCexternal, 0.66). After transfer learning on a small external subset, the DL model (AUCtl, external, 0.66) performed better than the reference model (AUCtl, external, 0.64). CONCLUSION: DL-based NTCP models performed better than the reference model when validated in data from the same institute. Improved performance in the external data set was achieved with transfer learning, demonstrating the need for multicenter training data to realize generalizable DL-based NTCP models.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Chu H, de Vette SPM, Neh H, et al. Three-Dimensional Deep Learning Normal Tissue Complication Probability Model to Predict Late Xerostomia in Patients With Head and Neck Cancer. Int J Radiat Oncol Biol Phys. 2024. PMID: 39147208. doi:10.1016/j.ijrobp.2024.07.2334

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。