文献速递胸部CT

基于平扫CT的深度学习模型鉴别肺腺癌与结核球:一项多中心诊断研究

Non-enhanced CT deep learning model for differentiating lung adenocarcinoma from tuberculoma: a multicenter diagnostic study.
PubMed 文献 · Eur Radiol · 2025-06-11

该多中心诊断研究纳入三家医院的1160例患者,构建基于三维特征的视觉Transformer深度学习模型(DL_3D),用于在平扫CT上鉴别肺腺癌与结核球。外部测试集中DL_3D的AUC为0.913,优于DL_2D(AUC 0.804)、影像组学模型(AUC 0.676)及六位放射科医师(AUC 0.692–0.810)。

要点

  • 平扫CT三维深度学习模型DL_3D在外部测试集鉴别肺腺癌与结核球的AUC达0.913。
  • DL_3D在测试集的AUC 0.913高于六位放射科医师的0.692–0.810(p值范围<0.001–0.035)。
  • DL_3D优于DL_2D(AUC 0.804)与影像组学模型(AUC 0.676),差异均有统计学意义(p<0.001)。

核心结论

  • DL_3D模型在平扫CT上鉴别肺腺癌与结核球的诊断性能优于专家放射科医师。

研究设计与样本

  • 多中心诊断研究,共纳入三家医院的1160例患者,训练集840例(平均年龄54.8岁,范围19–86岁;男性514例),验证集210例(平均年龄54.3岁,范围18–86岁;男性128例),外部测试集110例(平均年龄54.7岁,范围22–88岁;男性51例)。

诊断标准与关键数值

  • DL_3D在验证集AUC为0.895、外部测试集AUC为0.913;测试集中DL_3D的AUC为0.913(95%CI 0.854–0.973),DL_2D为0.804(95%CI 0.722–0.886,p<0.001),影像组学为0.676(95%CI 0.574–0.777,p<0.001),六位放射科医师AUC为0.692–0.810(p值范围<0.001–0.035)。

临床应用与阅片要点

  • 原文结论指出DL_3D模型可准确鉴别肺腺癌与结核球,有助于临床医师制定个体化治疗方案。

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 a deep learning model based on three-dimensional features (DL_3D) for distinguishing lung adenocarcinoma (LUAD) from tuberculoma (TBM).

MATERIALS AND METHODS: A total of 1160 patients were collected from three hospitals. A vision transformer network-based DL_3D model was trained, and its performance in differentiating LUAD from TBM was evaluated using validation and external test sets. The performance of the DL_3D model was compared with that of two-dimensional features (DL_2D), radiomics, and six radiologists. Diagnostic performance was assessed using the area under the receiver operating characteristic curves (AUCs) analysis.

RESULTS: The study included 840 patients in the training set (mean age, 54.8 years [range, 19-86 years]; 514 men), 210 patients in the validation set (mean age, 54.3 years [range, 18-86 years]; 128 men), and 110 patients in the external test set (mean age, 54.7 years [range, 22-88 years]; 51 men). In both the validation and external test sets, DL_3D exhibited excellent diagnostic performance (AUCs, 0.895 and 0.913, respectively). In the test set, the DL_3D model showed better performance (AUC, 0.913; 95% CI: 0.854, 0.973) than the DL_2D (AUC, 0.804, 95% CI: 0.722, 0.886; p < 0.001), radiomics (AUC, 0.676, 95% CI: 0.574, 0.777; p < 0.001), and six radiologists (AUCs, 0.692 to 0.810; p value range < 0.001-0.035).

CONCLUSION: The DL_3D model outperforms expert radiologists in distinguishing LUAD from TBM.

KEY POINTS: Question Can a deep learning model perform in differentiating LUAD from TBM on non-enhanced CT images? Findings The DL_3D model demonstrated higher diagnostic performance than the DL_2D model, radiomics model, and six radiologists in differentiating LUAD and TBM. Clinical relevance The DL_3D model could accurately differentiate between LUAD and TBM, which can help clinicians make personalized treatment plans.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang G, Shang L, Li S, et al. Non-enhanced CT deep learning model for differentiating lung adenocarcinoma from tuberculoma: a multicenter diagnostic study. Eur Radiol. 2025. PMID: 40500528. doi:10.1007/s00330-025-11721-y

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。