文献速递泌尿生殖技术与安全PET

基于机器学习的18F-PSMA-1007 PET影像组学预测多原发性前列腺癌生物学特征:不同体积分割阈值的比较

Machine learning-based radiomics for multiple primary prostate cancer biological characteristics prediction with 18F-PSMA-1007 PET: comparison among different volume segmentation thresholds.
PubMed 文献 · Radiol Med · 2022-08-26

结果显示预测Gleason评分和血管侵犯时50% SUVmax模型性能最佳,预测包膜外侵犯时40% SUVmax模型最佳,40-50% SUVmax阈值下的影像组学特征对多种生物学特征预测性能最好。

要点

  • 预测Gleason评分和血管侵犯时,50% SUVmax阈值勾画的影像组学模型性能最佳。
  • 预测包膜外侵犯时,40% SUVmax阈值勾画的影像组学模型性能最佳。
  • 40-50% SUVmax阈值下的18F-PSMA-1007 PET影像组学特征对多种前列腺癌生物学特征预测性能最好。

核心结论

  • 18F-1007-PSMA PET影像组学特征在40-50% SUVmax阈值下对多种前列腺癌生物学特征评估表现出最佳预测性能。
  • 与单一PSA模型相比,影像组学特征可能为预测前列腺癌生物学特征提供额外获益。

研究设计与样本

  • 以前列腺病灶30%、40%、50%、60% SUVmax为阈值半自动勾画感兴趣体积并分别提取影像组学特征。
  • 采用支持向量机建立Gleason评分、包膜外侵犯和血管侵犯的预测模型。
  • 使用受试者工作特征曲线及混淆矩阵衍生指标评估不同阈值区域模型的性能。

诊断标准与关键数值

  • 预测Gleason评分:50% SUVmax模型在训练队列AUC为0.82(95%CI 0.74-0.88),测试队列AUC为0.80(95%CI 0.66-0.90)。
  • 预测包膜外侵犯:40% SUVmax模型在训练队列AUC为0.77(95%CI 0.68-0.84),测试队列AUC为0.77(95%CI 0.63-0.88)。
  • 预测血管侵犯:50% SUVmax模型在训练队列AUC为0.74(95%CI 0.65-0.82),测试队列AUC为0.74(95%CI 0.56-0.82)。

临床应用与阅片要点

  • 在基于18F-PSMA-1007 PET影像组学预测前列腺癌生物学特征时,可优先考虑40-50% SUVmax阈值进行病灶分割。
  • 不同预测目标对应不同最佳阈值:Gleason评分和血管侵犯用50% SUVmax,包膜外侵犯用40% SUVmax。
  • 影像组学特征可作为单一PSA模型的补充,用于前列腺癌生物学特征的无创评估。

局限性

  • 本研究为单中心回顾性研究。
  • 最优阈值仅在30%、40%、50%、60% SUVmax四个离散水平中比较,未探索其他阈值。
  • 预测模型仅在训练和测试队列中评估,缺乏外部验证。

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)。

英文原文(摘要)· 点击展开

BACKGROUND: PET-based radiomics features could predict the biological characteristics of primary prostate cancer (PCa). However, the optimal thresholds to predict the biological characteristics of PCa are unknown. This study aimed to compare the predictive power of 18F-PSMA-1007 PET radiomics features at different thresholds for predicting multiple biological characteristics.

METHODS: One hundred and seventy-three PCa patients with complete preoperative 18F-PSMA-1007 PET examination and clinical data before surgery were collected. The prostate lesions' volumes of interest were semi-automatically sketched with thresholds of 30%, 40%, 50%, and 60% maximum standardized uptake value (SUVmax). The radiomics features were respectively extracted. The prediction models of Gleason score (GS), extracapsular extension (ECE), and vascular invasion (VI) were established using the support vector machine. The performance of models from different thresholding regions was assessed using receiver operating characteristic curve and confusion matrix-derived indexes.

RESULTS: For predicting GS, the 50% SUVmax model showed the best predictive performance in training (AUC, 0.82 [95%CI 0.74-0.88]) and testing cohorts (AUC, 0.80 [95%CI 0.66-0.90]). For predicting ECE, the 40% SUVmax model exhibit the best predictive performance (AUC, 0.77 [95%CI 0.68-0.84] and 0.77 [95%CI 0.63-0.88]). As for VI, the 50% SUVmax model had the best predictive performance (AUC, 0.74 [95%CI 0.65-0.82] and 0.74 [95%CI 0.56-0.82]).

CONCLUSION: The 18F-1007-PSMA PET-based radiomics features at 40-50% SUVmax showed the best predictive performance for multiple PCa biological characteristics evaluation. Compared to the single PSA model, radiomics features may provide additional benefits in predicting the biological characteristics of PCa.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Yao, Bian, Zhu, et al. Machine learning-based radiomics for multiple primary prostate cancer biological characteristics prediction with 18F-PSMA-1007 PET: comparison among different volume segmentation thresholds. Radiol Med. 2022. PMID: 36018488. doi:10.1007/s11547-022-01541-1

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。