文献速递头颈部肿瘤放疗放疗物理与技术

机器学习与深度学习方法预测头颈癌放疗所致放射性骨坏死(ORN)的比较

Comparison of Machine-Learning and Deep-Learning Methods for the Prediction of Osteoradionecrosis Resulting From Head and Neck Cancer Radiation Therapy.
PubMed 文献 · Adv Radiat Oncol · 2022-12-27

本研究回顾性比较了机器学习(ML)与深度学习(DL)方法在头颈癌(HNC)放疗后下颌骨放射性骨坏死(ORN)二分类预测中的表现,纳入2005至2015年在MD安德森癌症中心接受HNC放疗的患者。ML模型使用剂量体积直方图参数,DL模型使用裁剪至下颌骨的剂量图像;表现最佳的ML模型逻辑回归F1分数为0.3,优于表现最佳的DL模型自编码器架构的0.23。增加DL模型训练数据量未观察到性能提升。

要点

  • 表现最佳的ML模型逻辑回归F1分数为0.3,优于表现最佳的DL模型自编码器架构的0.23。
  • 随机分类器的F1分数为0.17,ResNet与DenseNet模型的F1分数分别为0.07和0.14。
  • 增加DL模型训练数据量未观察到性能提升。

核心结论

  • ML模型的表现优于DL模型。
  • 增加训练数据后DL模型性能未见提升,作者认为可能是构建合适的DL模型需要更多数据,或DL模型所用的图像特征不适合该任务。

研究设计与样本

  • 回顾性比较研究,纳入2005至2015年在德克萨斯大学MD安德森癌症中心接受HNC放疗的患者,ML研究n=1259,DL研究n=1236。
  • 受试者随访ORN发生至少12个月,其中173例发生ORN,1086例无ORN证据。
  • ML模型使用剂量体积直方图参数,包括逻辑回归、随机森林、支持向量机和随机分类器参考。
  • DL模型基于ResNet、DenseNet和自编码器架构,使用每位受试者裁剪至下颌骨的剂量。
  • 通过使用递增比例的原始训练数据训练DL模型,评估增加可用训练数据量对DL模型预测性能的影响。

主要发现

  • 表现最佳的ML模型逻辑回归F1分数为0.3。
  • 表现最佳的ResNet、DenseNet和自编码器模型的F1分数分别为0.07、0.14和0.23,随机分类器的F1分数为0.17。
  • 增加DL模型训练数据量后未观察到明显的性能提升。

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 (DL) techniques have been successful in disease-prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine-learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of patients with HNC. METHODS AND MATERIALS: Patients who received HNC radiation therapy at the University of Texas MD Anderson Cancer Center from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. The ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. The DL models were based on ResNet, DenseNet, and autoencoder-based architectures. The DL models used each participant's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models' prediction performance was evaluated by training the DL models using increasing ratios of the original training data. RESULTS: The F1 score for the logistic regression model, the best-performing ML model, was 0.3. The best-performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training. CONCLUSIONS: The ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data are needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task.

来源:Adv Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Reber B, Van Dijk L, Anderson B, et al. Comparison of Machine-Learning and Deep-Learning Methods for the Prediction of Osteoradionecrosis Resulting From Head and Neck Cancer Radiation Therapy. Adv Radiat Oncol. 2022. PMID: 36798732. doi:10.1016/j.adro.2022.101163

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。