文献速递胸部CT

基于CT的深度学习形态学与组织病理学特征对肺腺癌的预后预测:一项回顾性双中心研究

Prognostication of lung adenocarcinomas using CT-based deep learning of morphological and histopathological features: a retrospective dual-institutional study.
PubMed 文献 · Eur Radiol · 2023-10-20

该回顾性双中心研究训练并验证了基于术前胸部CT的深度学习模型,同时预测五种形态学和组织病理学特征以构建预后评分,并在时间验证集和外部验证集中评估其预测无复发生存和总生存的能力,结果显示该评分具有独立预后价值,外部验证集中5年OS的TD-AUC与病理分期相当(0.71 vs 0.71,p=0.74)。

要点

  • 基于术前CT的深度学习预后评分在外部验证集中5年OS的TD-AUC为0.71,与病理分期相当(0.71 vs 0.71,p=0.74)。
  • 该评分对FFR和OS的预后价值独立于临床因素,时间验证集中FFR每增加1%的校正HR为1.02(95%CI 1.01-1.03,p<0.001)。
  • 该模型TD-AUC高于直接生存预测模型但无统计学显著差异(2.5年OS:0.73 vs 0.68,p=0.13)。

核心结论

  • 基于CT的深度学习预后评分通过联合学习形态学和组织病理学特征,在预测肺腺癌生存方面显示出潜力。

研究设计与样本

  • 回顾性双中心研究,训练集来自3181例接受手术切除的肺腺癌患者的术前胸部CT,模型同时预测五种形态学和组织病理学特征,并在时间验证集(640例,中位年龄64岁)和外部验证集(846例,中位年龄65岁)中验证,结局为无复发生存和总生存,并与既往开发的深度学习离散时间生存模型比较。

诊断标准与关键数值

  • 时间验证集(640例)中,基于CT的深度学习评分预测5年FFR的TD-AUC为0.79,预测5年OS的TD-AUC为0.73。
  • 外部验证集(846例)中,该评分预测5年OS的TD-AUC为0.71,与病理分期相当(0.71 vs 0.71,p=0.74)。
  • 时间验证集中,校正临床因素后每增加1%的FFR的HR为1.02(95%CI 1.01-1.03,p<0.001),OS的HR为1.01(95%CI 1.002-1.02,p=0.01)。
  • 外部验证集中,校正临床因素后每增加1%的OS的HR为1.01(95%CI 1.005-1.02,p<0.001)。
  • 该模型预测2.5年OS的TD-AUC高于深度学习离散时间生存模型但无统计学显著差异(0.73 vs 0.68,p=0.13)。

临床应用与阅片要点

  • 作者认为,基于CT联合深度学习形态学和组织病理学特征有望增强肺腺癌的预后预测并优化围手术期管理。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: To develop and validate CT-based deep learning (DL) models that learn morphological and histopathological features for lung adenocarcinoma prognostication, and to compare them with a previously developed DL discrete-time survival model.

METHODS: DL models were trained to simultaneously predict five morphological and histopathological features using preoperative chest CT scans from patients with resected lung adenocarcinomas. The DL score was validated in temporal and external test sets, with freedom from recurrence (FFR) and overall survival (OS) as outcomes. Discrimination was evaluated using the time-dependent area under the receiver operating characteristic curve (TD-AUC) and compared with the DL discrete-time survival model. Additionally, we performed multivariable Cox regression analysis.

RESULTS: In the temporal test set (640 patients; median age, 64 years), the TD-AUC was 0.79 for 5-year FFR and 0.73 for 5-year OS. In the external test set (846 patients; median age, 65 years), the TD-AUC was 0.71 for 5-year OS, equivalent to the pathologic stage (0.71 vs. 0.71 [p = 0.74]). The prognostic value of the DL score was independent of clinical factors (adjusted per-percentage hazard ratio for FFR (temporal test), 1.02 [95% CI: 1.01-1.03; p < 0.001]; OS (temporal test), 1.01 [95% CI: 1.002-1.02; p = 0.01]; OS (external test), 1.01 [95% CI: 1.005-1.02; p < 0.001]). Our model showed a higher TD-AUC than the DL discrete-time survival model, but without statistical significance (2.5-year OS: 0.73 vs. 0.68; p = 0.13).

CONCLUSION: The CT-based prognostic score from collective deep learning of morphological and histopathological features showed potential in predicting survival in lung adenocarcinomas.

CLINICAL RELEVANCE STATEMENT: Collective CT-based deep learning of morphological and histopathological features presents potential for enhancing lung adenocarcinoma prognostication and optimizing pre-/postoperative management.

KEY POINTS: • A CT-based prognostic model was developed using collective deep learning of morphological and histopathological features from preoperative CT scans of 3181 patients with resected lung adenocarcinoma. • The prognostic performance of the model was comparable-to-higher performance than the pathologic T category or stage. • Our approach yielded a higher discrimination performance than the direct survival prediction model, but without statistical significance (0.73 vs. 0.68; p=0.13).

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Lee T, Lee KH, Lee JH, et al. Prognostication of lung adenocarcinomas using CT-based deep learning of morphological and histopathological features: a retrospective dual-institutional study. Eur Radiol. 2023. PMID: 37861801. doi:10.1007/s00330-023-10306-x

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。