深度学习模型整合正电子发射断层扫描和临床数据，用于非小细胞肺癌患者的预后预测。
Deep learning model integrating positron emission tomography and clinical data for prognosis prediction in non-small cell lung cancer patients.
机构信息
Department of Mathematics and Statistics, Chonnam National University, Gwangju, Republic of Korea.
Department of Nuclear Medicine, Chonnam National University Medical School and Hwasun Hospital, Hwasun, Jeonnam, Republic of Korea.
出版信息
BMC Bioinformatics. 2023 Feb 6;24(1):39. doi: 10.1186/s12859-023-05160-z.
BACKGROUND
Lung cancer is the leading cause of cancer-related deaths worldwide. The majority of lung cancers are non-small cell lung cancer (NSCLC), accounting for approximately 85% of all lung cancer types. The Cox proportional hazards model (CPH), which is the standard method for survival analysis, has several limitations. The purpose of our study was to improve survival prediction in patients with NSCLC by incorporating prognostic information from F-18 fluorodeoxyglucose positron emission tomography (FDG PET) images into a traditional survival prediction model using clinical data.
RESULTS
The multimodal deep learning model showed the best performance, with a C-index and mean absolute error of 0.756 and 399 days under a five-fold cross-validation, respectively, followed by ResNet3D for PET (0.749 and 405 days) and CPH for clinical data (0.747 and 583 days).
CONCLUSION
The proposed deep learning-based integrative model combining the two modalities improved the survival prediction in patients with NSCLC.
背景
肺癌是全球癌症相关死亡的主要原因。大多数肺癌是非小细胞肺癌（NSCLC），约占所有肺癌类型的 85%。Cox 比例风险模型（CPH）是生存分析的标准方法，但存在一些局限性。我们的研究旨在通过将 F-18 氟脱氧葡萄糖正电子发射断层扫描（FDG PET）图像中的预后信息纳入使用临床数据的传统生存预测模型，来改善 NSCLC 患者的生存预测。
结果
多模态深度学习模型表现最佳，在五折交叉验证下的 C 指数和平均绝对误差分别为 0.756 和 399 天，其次是用于 PET 的 ResNet3D（0.749 和 405 天）和用于临床数据的 CPH（0.747 和 583 天）。
结论
提出的结合两种模态的基于深度学习的综合模型提高了 NSCLC 患者的生存预测。
Zotero 插件