融合临床与影像组学评分的多模态深度学习预测早期肺腺癌淋巴结转移
回顾性纳入两个中心724例经病理证实的早期浸润性肺腺癌患者,基于非增强CT图像提取3D影像组学特征,构建融合临床知识与影像组学评分的多模态深度学习网络(CS-RS-DL)预测淋巴结转移。该模型在内部验证集AUC为0.877、独立测试集AUC为0.906,均高于其他模型(Delong检验独立测试集均P<0.05),敏感度最高为0.941,平均精度为0.642。
要点
- CS-RS-DL融合模型在独立测试集AUC为0.906,优于临床模型(0.844)、影像组学模型(0.850)等。
- CS-RS-DL模型敏感度最高为0.941,平均精度为0.642。
- 模型融合了性别、CEA、CYFRA21-1、NSE、肿瘤大小、位置、密度及中心性8个临床与影像特征。
核心结论
- 来自临床、影像组学和深度学习的知识在预测肺腺癌淋巴结转移方面具有互补性。
- 通过深度学习整合临床评分与影像组学评分可显著提高淋巴结状态评估的准确性。
研究设计与样本
- 回顾性纳入两个中心共724例经病理证实的早期浸润性肺腺癌患者。
- 中心1的524例患者按4:1随机分为训练集(n=418)和内部验证集(n=106),中心2的200例患者作为独立测试集。
- 收集临床与CT语义特征,从非增强CT图像提取3D影像组学特征。
- 提出基于InceptionResNetV2架构的多模态特征融合深度学习网络(CS-RS-DL)。
诊断标准与关键数值
- 从16个临床与影像特征中选取8个:性别、血清癌胚抗原、细胞角蛋白19片段抗原21-1、神经元特异性烯醇化酶、肿瘤大小、位置、密度和中心性。
- 从1595个影像组学特征中识别出6个关键特征。
- CS-RS-DL融合模型内部验证集AUC为0.877,独立测试集AUC为0.906。
- 独立测试集Delong检验:CS-RS-DL模型显著优于临床模型(0.844)、影像组学模型(0.850)、CS-RS模型(0.872)、单一DL模型(0.848)和CS-DL模型(0.875),均P<0.05。
- CS-RS-DL模型敏感度最高为0.941,平均精度为0.642。
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
RATIONALE AND OBJECTIVES: To develop and validate a multimodal deep learning (DL) model based on computed tomography (CT) images and clinical knowledge to predict lymph node metastasis (LNM) in early lung adenocarcinoma.
MATERIALS AND METHODS: A total of 724 pathologically confirmed early invasive lung adenocarcinoma patients were retrospectively included from two centers. Clinical and CT semantic features of the patients were collected, and 3D radiomics features were extracted from nonenhanced CT images. We proposed a multimodal feature fusion DL network based on the InceptionResNetV2 architecture, which can effectively extract and integrate image and clinical knowledge to predict LNM.
RESULTS: A total of 524 lung adenocarcinoma patients from Center 1 were randomly divided into training (n=418) and internal validation (n=106) sets in a 4:1 ratio, while 200 lung adenocarcinoma patients from Center 2 served as the independent test set. Among the 16 collected clinical and imaging features, 8 were selected: gender, serum carcinoembryonic antigen, cytokeratin 19 fragment antigen 21-1, neuron-specific enolase, tumor size, location, density, and centrality. From the 1595 extracted radiomics features, six key features were identified. The CS-RS-DL fusion model achieved the highest area under the receiver operating characteristic curve in both the internal validation set (0.877) and the independent test set (0.906) compared to other models. The Delong test results for the independent test set indicated that the CS-RS-DL model significantly outperformed the clinical model (0.844), radiomics model (0.850), CS-RS model (0.872), single DL model (0.848), and the CS-DL model (0.875) (all P<0.05). Additionally, the CS-RS-DL model exhibited the highest sensitivity (0.941) and average precision (0.642).
CONCLUSION: The knowledge derived from clinical, radiomics, and DL is complementary in predicting LNM in lung adenocarcinoma. The integration of clinical and radiomics scores through DL can significantly improve the accuracy of lymph node status assessment.
引用
- Xia C, Zuo M, Lin Z, et al. Multimodal Deep Learning Fusing Clinical and Radiomics Scores for Prediction of Early-Stage Lung Adenocarcinoma Lymph Node Metastasis. Acad Radiol. 2024. PMID: 39730249. doi:10.1016/j.acra.2024.12.018
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。