机器学习利用前列腺特异性膜抗原PET影像组学预测寡转移性去势敏感性前列腺癌的常规影像无转移生存
研究纳入117例接受立体定向消融放疗转移灶定向治疗的寡转移性去势敏感性前列腺癌患者,提取治疗前后PSMA-PET影像组学特征并结合临床参数构建机器学习模型预测2年无转移生存。随机森林在留一法测试中准确率80%、AUC 0.82,跨机构验证中约翰霍普金斯医院患者准确率75%、AUC 0.77,巴什肯特大学患者准确率78%、AUC 0.80。
要点
- 治疗前后PSMA-PET影像组学联合临床参数可用于预测2年无转移生存。
- 随机森林模型留一法测试准确率80%、AUC 0.82。
- 跨机构验证中约翰霍普金斯医院患者准确率75%、AUC 0.77,巴什肯特大学患者准确率78%、AUC 0.80。
核心结论
- 研究显示利用转移灶定向治疗前后PSMA-PET影像生物标志物预测寡转移性去势敏感性前列腺癌无转移生存具有前景。
研究设计与样本
- 国际队列纳入117例寡转移性去势敏感性前列腺癌患者,其中约翰霍普金斯医院34例、巴什肯特大学83例,均接受立体定向消融放疗转移灶定向治疗并采集治疗前后PSMA-PET/CT。
- 从CT-PET融合定义的大体肿瘤体积(zone 1)及其外5 mm扩展环区域(zone 2)提取1748个PET影像组学特征。
- 采用卡方方法选取6个最显著特征,联合5个临床参数(年龄、Gleason评分、总病灶数、未治疗病灶数、治疗前前列腺特异性抗原)作为模型输入。
- 使用随机森林、决策树、支持向量机和朴素贝叶斯等多种机器学习模型预测2年无转移生存,并采用留一法和跨机构验证进行测试。
主要发现
- 选入预测2年无转移生存的6个影像组学特征包括治疗前PSMA-PET zone 1的总能量、熵和标准差,治疗后PSMA-PET zone 1的总能量和对比度,以及治疗前PSMA-PET zone 2的熵。
- 在全部患者的留一法测试中,随机森林预测2年无转移生存的准确率为80%,AUC为0.82。
- 跨机构验证中,模型对约翰霍普金斯医院患者预测2年无转移生存事件的准确率为75%,AUC为0.77。
- 跨机构验证中,模型对巴什肯特大学患者预测2年无转移生存事件的准确率为78%,AUC为0.80。
临床怎么用
- 原文未据此给出推荐。
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: This study investigated imaging biomarkers derived from PSMA-PET acquired pre- and post-metastasis-directed therapy (MDT) to predict 2-year metastasis-free survival (MFS), which provides valuable early response assessment to improve patient outcomes. MATERIALS/METHODS: An international cohort of 117 oligometastatic castration-sensitive prostate cancer (omCSPC) patients, comprising 34 from John Hopkins Hospital (JHH) and 83 from Baskent University (BU), were treated with stereotactic ablative radiation therapy (SABR) MDT with both pre- and post-MDT PSMA-PET/CT scans acquired. PET radiomic features were analyzed from a CT-PET fusion defined gross tumor volume ((GTV) or zone 1), and a 5 mm expansion ring area outside the GTV (zone 2). A total of 1748 PET radiomic features were extracted from these zones. The six most significant features selected using the Chi2 method, along with five clinical parameters (age, Gleason score, number of total lesions, untreated lesions, and pre-MDT prostate-specific antigen (PSA)) were extracted as inputs to the models. Various machine learning models, including Random Forest, Decision Tree, Support Vector Machine, and Naïve Bayesian, were employed for 2-year MFS prediction and tested using leave-one-out and cross-institution validation. RESULTS: Six radiomic features, including Total Energy, Entropy, and Standard Deviation from pre-PSMA-PET zone 1, Total Energy and Contrast from post-PSMA-PET zone 1, and Entropy from pre-PSMA-PET zone 2, along with five clinical parameters were selected for predicting 2-year MFS. In a leave-one-out test with all the patients, random forest achieved an accuracy of 80 % and an AUC of 0.82 in predicting 2-year MFS. In cross-institution validation, the model correctly predicted 2-year MFS events with an accuracy of 75 % and an AUC of 0.77 for patients from JHH, and an accuracy of 78 % and an AUC of 0.80 for BU patients, respectively. CONCLUSION: Our study demonstrated the promise of using pre- and post-MDT PSMA-PET-based imaging biomarkers for MFS prediction for omCSPC patients.
引用
- Cao Y, Sutera P, Silva Mendes W, et al. Machine learning predicts conventional imaging metastasis-free survival (MFS) for oligometastatic castration-sensitive prostate cancer (omCSPC) using prostate-specific membrane antigen (PSMA) PET radiomics. Radiother Oncol. 2024. PMID: 39094629. doi:10.1016/j.radonc.2024.110443
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。