人工智能用于宫颈癌在线自适应放疗决策的可行性研究
本研究纳入24例宫颈癌患者的671次每日FBCT引导在线自适应放疗分次,以计划剂量偏差超预设标准定义触发。机器学习与深度学习模型在独立数据集上表现稳健,加权模型预测准确率显著优于医师共识。
要点
- 基于剂量学标签,671次分次中492次为触发、179次为非触发。
- ML模型AUC 0.884,DL_C模型AUC 0.917,DL_D加入剂量学数据后性能略降。
- 独立数据集上加权模型准确率0.855 vs 医师共识0.795,召回率0.887 vs 0.790。
核心结论
- 研究提出机器学习和深度学习模型可识别宫颈癌根治性放疗中可能受益于自适应再计划的分次,作为辅助临床决策工具。
研究设计与样本
- 纳入24例宫颈癌患者共671次每日FBCT引导oART分次,每次分次含FBCT图像及计划与自适应计划对。
- 以计划剂量偏差超预设标准标注触发,588次分次(21例)用于模型开发,83次分次(3例)为独立评估集。
- 机器学习提取101个形态学、灰度及剂量学特征,经LASSO选择、SVM分类;深度学习采用Siamese网络,DL_C仅用影像与轮廓,DL_D加入剂量学数据。
- 采用5折交叉验证训练与测试,以AUC、准确率、精确率、召回率评估,并与3名有经验放疗肿瘤学家的触发标签比较。
主要发现
- 基于剂量学标签,671次分次分为492次触发和179次非触发。
- ML模型选择39个关键特征,主要反映子宫CTV(CTV_U)、宫颈阴道及宫旁组织CTV(CTV_C)和小肠的形态与灰度变化,AUC 0.884,准确率0.825,精确率0.824,召回率0.827。
- DL_C模型AUC 0.917,准确率0.869,精确率0.860,召回率0.881;DL_D模型加入剂量学数据后性能较DL_C略有下降。
- 热图分析显示,触发分次中深度学习模型关注参考CT的CTV_U未完全包涵每日FBCT的CTV_U的区域。
- 独立数据集评估中,加权模型预测准确率显著优于医师共识(0.855 vs 0.795),精确率相当(0.917 vs 0.925),召回率更高(0.887 vs 0.790)。
关键数值与推荐
- 剂量偏差预设标准:原文未报告具体阈值。
- ML模型参数:LASSO特征选择,SVM分类,39个关键特征。
- 深度学习模型:Siamese网络,DL_C仅影像与轮廓,DL_D加入剂量学数据,5折交叉验证。
- 评估指标:AUC、准确率、精确率、召回率,独立数据集与3名医师标签比较。
临床怎么用
- 模型可作为决策支持工具,辅助临床医生判断宫颈癌根治性放疗中何时触发oART工作流程。
- 深度学习模型基于影像和轮廓即可获得较高预测性能,加入剂量学数据未提升性能。
局限性
- 原文未述局限性
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: Interfraction variations during radiation therapy pose a challenge for patients with cervical cancer, highlighting the benefits of online adaptive radiation therapy (oART). However, adaptation decisions rely on subjective image reviews by physicians, leading to high interobserver variability and inefficiency. This study explores the feasibility of using artificial intelligence for decision-making in oART. METHODS AND MATERIALS: A total of 24 patients with cervical cancer who underwent 671 fractions of daily fan-beam computed tomography (FBCT) guided oART were included in this study, with each fraction consisting of a daily FBCT image series and a pair of scheduled and adaptive plans. Dose deviations of scheduled plans exceeding predefined criteria were labeled as "trigger," otherwise as "nontrigger." A data set comprising 588 fractions from 21 patients was used for model development. For the machine learning model (ML), 101 morphologic, gray-level, and dosimetric features were extracted, with feature selection by the least absolute shrinkage and selection operator (LASSO) and classification by support vector machine (SVM). For deep learning, a Siamese network approach was used: the deep learning model of contour (DL_C) used only imaging data and contours, whereas a deep learning model of contour and dose (DL_D) also incorporated dosimetric data. A 5-fold cross-validation strategy was employed for model training and testing, and model performance was evaluated using the area under the curve (AUC), accuracy, precision, and recall. An independent data set comprising 83 fractions from 3 patients was used for model evaluation, with predictions compared against trigger labels assigned by 3 experienced radiation oncologists. RESULTS: Based on dosimetric labels, the 671 fractions were classified into 492 trigger and 179 nontrigger cases. The ML model selected 39 key features, primarily reflecting morphologic and gray-level changes in the clinical target volume (CTV) of the uterus (CTV_U), the CTV of the cervix, vagina, and parametrial tissues (CTV_C), and the small intestine. It achieved an AUC of 0.884, with accuracy, precision, and recall of 0.825, 0.824, and 0.827, respectively. The DL_C model demonstrated superior performance with an AUC of 0.917, accuracy of 0.869, precision of 0.860, and recall of 0.881. The DL_D model, which incorporated additional dosimetric data, exhibited a slight decline in performance compared with DL_C. Heatmap analyses indicated that for trigger fractions, the deep learning models focused on regions where the reference CT's CTV_U did not fully encompass the daily FBCT's CTV_U. Evaluation on an independent data set confirmed the robustness of all models. The weighted model's prediction accuracy significantly outperformed the physician consensus (0.855 vs 0.795), with comparable precision (0.917 vs 0.925) but substantially higher recall (0.887 vs 0.790). CONCLUSION: This study proposes machine learning and deep learning models to identify treatment fractions that may benefit from adaptive replanning in radical radiation therapy for cervical cancer, providing a promising decision-support tool to assist clinicians in determining when to trigger the oART workflow during treatment.
引用
- Sun S, Gong X, Cheng S, et al. Fully Automated Online Adaptive Radiation Therapy Decision-Making for Cervical Cancer Using Artificial Intelligence. Int J Radiat Oncol Biol Phys. 2025. PMID: 40252932. doi:10.1016/j.ijrobp.2025.04.012
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。