机器学习用于接受177Lu-PSMA I&T治疗的晚期前列腺癌患者治疗前剂量学估算
该回顾性研究纳入23例接受177Lu-PSMA I&T放射配体治疗的转移性去势抵抗性前列腺癌患者,共43个治疗周期,利用治疗前68Ga-PSMA-HEBD-CC PET/CT的器官SUV和实验室指标,通过机器学习预测肾脏、肝脏、脾脏和唾液腺的剂量学。最优机器学习方法的剂量预测平均绝对百分比误差(MAPE)在肾脏为15.8±13.2%、肝脏为29.6%±13.7%、唾液腺为23.8%±13.1%、脾脏为32.1±31.4%。结论认为治疗前剂量学估算可行,且优于基于人群均值的经验性估算。
要点
- 机器学习基于治疗前PET/CT器官SUV和实验室指标可预测177Lu-PSMA I&T的器官剂量。
- 最优模型肾脏MAPE为15.8±13.2%,脾脏MAPE最高为32.1±31.4%。
- 基于文献人群均值的预测MAPE显著更大(p<0.01),如肝脏为139.1%±111.5%。
核心结论
- 初步结果证实了治疗前剂量学估算的可行性及其相对于经验性人群估算的附加价值。
- 剂量预测的探索可能支持放射配体治疗中治疗计划的实施。
研究设计与样本
- 回顾性纳入23例接受177Lu-PSMA I&T放射配体治疗的转移性去势抵抗性前列腺癌患者。
- 患者具有治疗前68Ga-PSMA-HEBD-CC PET/CT及至少3次平面显像和1次SPECT/CT用于剂量学。
- 共应用43个周期的177Lu-PSMA I&T放射配体治疗。
- 从治疗前PET/CT获取器官标准摄取值(SUV),使用Hermes Hybrid Dosimetry 4.0从平面和SPECT/CT图像计算肾脏、肝脏、脾脏和唾液腺的患者剂量学。
- 探索机器学习方法从器官SUV和实验室测量值预测剂量,并与基于人群的剂量学估算比较不确定性,采用平均绝对百分比误差(MAPE)评估预测不确定性。
主要发现
- 最优机器学习方法对肾脏的剂量预测MAPE为15.8±13.2%。
- 最优机器学习方法对肝脏的剂量预测MAPE为29.6%±13.7%。
- 最优机器学习方法对唾液腺的剂量预测MAPE为23.8%±13.1%。
- 最优机器学习方法对脾脏的剂量预测MAPE为32.1±31.4%。
- 基于文献人群均值的预测MAPE显著更大(p<0.01):肾脏25.5±17.3%、肝脏139.1%±111.5%、唾液腺67.0±58.3%、脾脏54.1±215.3%。
关键数值与推荐
- 机器学习模型预测肾脏剂量的MAPE为15.8±13.2%,基于文献人群均值的MAPE为25.5±17.3%(p<0.01)。
- 机器学习模型预测肝脏剂量的MAPE为29.6%±13.7%,基于文献人群均值的MAPE为139.1%±111.5%(p<0.01)。
- 机器学习模型预测唾液腺剂量的MAPE为23.8%±13.1%,基于文献人群均值的MAPE为67.0±58.3%(p<0.01)。
- 机器学习模型预测脾脏剂量的MAPE为32.1±31.4%,基于文献人群均值的MAPE为54.1±215.3%(p<0.01)。
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: Although treatment planning and individualized dose application for emerging prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) are generally recommended, it is still difficult to implement in practice at the moment. In this study, we aimed to prove the concept of pretherapeutic prediction of dosimetry based on imaging and laboratory measurements before the RLT treatment. METHODS: Twenty-three patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177Lu-PSMA I&T RLT were included retrospectively. They had available pre-therapy 68 Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT imaging for dosimetry. Overall, 43 cycles of 177Lu-PSMA I&T RLT were applied. Organ-based standard uptake values (SUVs) were obtained from pre-therapy PET/CT scans. Patient dosimetry was calculated for the kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the planar and SPECT/CT images. Machine learning methods were explored for dose prediction from organ SUVs and laboratory measurements. The uncertainty of these dose predictions was compared with the population-based dosimetry estimates. Mean absolute percentage error (MAPE) was used to assess the prediction uncertainty of estimated dosimetry. RESULTS: An optimal machine learning method achieved a dosimetry prediction MAPE of 15.8 ± 13.2% for the kidney, 29.6% ± 13.7% for the liver, 23.8% ± 13.1% for the salivary glands, and 32.1 ± 31.4% for the spleen. In contrast, the prediction based on literature population mean has significantly larger MAPE (p < 0.01), 25.5 ± 17.3% for the kidney, 139.1% ± 111.5% for the liver, 67.0 ± 58.3% for the salivary glands, and 54.1 ± 215.3% for the spleen. CONCLUSION: The preliminary results confirmed the feasibility of pretherapeutic estimation of treatment dosimetry and its added value to empirical population-based estimation. The exploration of dose prediction may support the implementation of treatment planning for RLT.
引用
- Xue S, Gafita A, Dong C, et al. Application of machine learning to pretherapeutically estimate dosimetry in men with advanced prostate cancer treated with 177Lu-PSMA I&T therapy. Eur J Nucl Med Mol Imaging. 2022. PMID: 35771265. doi:10.1007/s00259-022-05883-w
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。