文献速递泌尿生殖与妇科肿瘤放疗放疗物理与技术

人工智能勾画的前列腺体积与肿瘤体积对放疗预后的评估

Evaluating the prognostic significance of artificial intelligence-delineated gross tumor volume and prostate volume measurements for prostate radiotherapy.
PubMed 文献 · Radiother Oncol · 2025-03-22

该回顾性研究纳入2010–2017年接受放疗的187例前列腺癌患者,训练AI分割算法从前列腺MRI勾画前列腺和GTV,并应用于近距离放疗患者。结果显示AI GTV体积与生化失败和转移相关,AI前列腺体积在单药治疗亚组与急性和晚期2级以上泌尿生殖毒性相关,但在联合治疗亚组仅与IPSS缓解相关。AI衍生体积可能对放疗后毒性和肿瘤学结局具有预后价值。

要点

  • AI GTV体积与生化失败(HR 1.28)和转移(HR 1.34)相关。
  • 单药近距离放疗亚组中,AI前列腺体积与急性(aOR 1.16)和晚期(aHR 1.04)2级以上泌尿毒性相关。
  • 联合治疗亚组中,AI前列腺体积与IPSS缓解相关(OR 0.96),与泌尿毒性无关。

核心结论

  • AI导出的前列腺和GTV体积可能对放疗后毒性和肿瘤学结局具有预后价值。
  • 考虑到不同放疗模式间结局的差异,此类信息可能有助于治疗决策。

研究设计与样本

  • 回顾性研究,纳入2010–2017年接受放疗的患者。
  • 训练AI分割算法从外照射放疗患者勾画前列腺和GTV,并应用于近距离放疗患者。
  • 共识别187例接受近距离放疗的患者(单药治疗N=154,联合治疗N=33)。

主要发现

  • AI GTV体积与生化失败相关(HR 1.28[1.14,1.44];p<0.001)。
  • AI GTV体积与转移相关(HR 1.34[1.18,1.53];p<0.001)。
  • 单药治疗亚组中,AI前列腺体积与急性2级以上泌尿生殖毒性相关(校正OR 1.16[1.07,1.25];p<0.001),与晚期2级以上泌尿生殖毒性相关(校正HR 1.04[1.01,1.07];p=0.01),与IPSS缓解无关(0.99[0.97,1.00];p=0.13)。
  • 联合治疗亚组中,AI前列腺体积与急性2级以上泌尿毒性无关(p=0.72),与晚期2级以上泌尿毒性无关(p=0.75),但与IPSS缓解相关(0.96[0.93,0.99];p=0.01)。

临床怎么用

  • AI导出的前列腺和GTV体积可能为放疗后毒性和肿瘤学结局提供预后信息,可能辅助治疗决策。

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 AND PURPOSE: Artificial intelligence (AI) may extract prognostic information from MRI for localized prostate cancer. We evaluate whether AI-derived prostate and gross tumor volume (GTV) are associated with toxicity and oncologic outcomes after radiotherapy. MATERIALS AND METHODS: We conducted a retrospective study of patients, who underwent radiotherapy between 2010 and 2017. We trained an AI segmentation algorithm to contour the prostate and GTV from patients treated with external-beam RT, and applied the algorithm to those treated with brachytherapy. AI prostate and GTV volumes were calculated from segmentation results. We evaluated whether AI GTV volume was associated with biochemical failure (BF) and metastasis. We evaluated whether AI prostate volume was associated with acute and late grade 2+ genitourinary toxicity, and International Prostate Symptom Score (IPSS) resolution for monotherapy and combination sets, separately. RESULTS: We identified 187 patients who received brachytherapy (monotherapy (N = 154) or combination therapy (N = 33)). AI GTV volume was associated with BF (hazard ratio (HR):1.28[1.14,1.44];p < 0.001) and metastasis (HR:1.34[1.18,1.53;p < 0.001). For the monotherapy subset, AI prostate volume was associated with both acute (adjusted odds ratio:1.16[1.07,1.25];p < 0.001) and late grade 2 + genitourinary toxicity (adjusted HR:1.04[1.01,1.07];p = 0.01), but not IPSS resolution (0.99[0.97,1.00];p = 0.13). For the combination therapy subset, AI prostate volume was not associated with either acute (p = 0.72) or late (p = 0.75) grade 2 + urinary toxicity. However, AI prostate volume was associated with IPSS resolution (0.96[0.93, 0.99];p = 0.01). CONCLUSION: AI-derived prostate and GTV volumes may be prognostic for toxicity and oncologic outcomes after RT. Such information may aid in treatment decision-making, given differences in outcomes among RT treatment modalities.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Adleman J, McLaughlin PY, Tsui JMG, et al. Evaluating the prognostic significance of artificial intelligence-delineated gross tumor volume and prostate volume measurements for prostate radiotherapy. Radiother Oncol. 2025. PMID: 40127722. doi:10.1016/j.radonc.2025.110866

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。