基于多任务深度学习的影像组学列线图用于局部晚期鼻咽癌预后预测
本研究纳入两个医疗中心的886例局部晚期鼻咽癌患者,利用[18F]FDG PET/CT图像和临床数据,构建整合DeepMTS-Score、AutoRadio-Score和临床数据的多任务深度学习影像组学列线图,用于无进展生存期预测和风险分层。该列线图在训练、内部验证和外部验证队列中C指数分别为0.818、0.752和0.717,AUC分别为0.859、0.769和0.730,较传统影像组学列线图有统计学显著改善,并能将患者分为高低风险组。
要点
- 多任务深度学习影像组学列线图在局部晚期鼻咽癌中实现可靠的PFS预测和风险分层。
- 外部验证队列C指数0.717(95%CI 0.641-0.793),AUC 0.730(95%CI 0.634-0.826)。
- 列线图预测能力较传统影像组学列线图有统计学显著改善。
核心结论
- 多任务深度学习影像组学列线图可对局部晚期鼻咽癌患者进行可靠且准确的预后预测,并实现更好的患者分层,有助于个体化治疗规划。
研究设计与样本
- 回顾性纳入两个医疗中心的886例局部晚期鼻咽癌患者,含临床数据、[18F]FDG PET/CT图像和无进展生存期随访。
- 采用深度多任务生存模型(DeepMTS)联合进行预后预测(DeepMTS-Score)和FDG-PET/CT图像肿瘤分割。
- 利用DeepMTS分割掩膜提取手工影像组学特征用于预后预测(AutoRadio-Score),并整合DeepMTS-Score、AutoRadio-Score和临床数据构建多任务深度学习影像组学列线图。
主要发现
- 列线图在训练队列C指数0.818(95%CI 0.785-0.851),内部验证队列0.752(95%CI 0.638-0.865),外部验证队列0.717(95%CI 0.641-0.793)。
- 列线图在训练队列AUC 0.859(95%CI 0.822-0.895),内部验证队列0.769(95%CI 0.642-0.896),外部验证队列0.730(95%CI 0.634-0.826)。
- 列线图预测能力较传统影像组学列线图有统计学显著改善。
- 列线图可将患者分为高风险和低风险组,两组间差异显著。
关键数值与推荐
- 训练队列C指数0.818(95%CI 0.785-0.851),AUC 0.859(95%CI 0.822-0.895)。
- 内部验证队列C指数0.752(95%CI 0.638-0.865),AUC 0.769(95%CI 0.642-0.896)。
- 外部验证队列C指数0.717(95%CI 0.641-0.793),AUC 0.730(95%CI 0.634-0.826)。
临床怎么用
- 原文未据此给出推荐。
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)。
原文
PURPOSE: Prognostic prediction is crucial to guide individual treatment for locoregionally advanced nasopharyngeal carcinoma (LA-NPC) patients. Recently, multi-task deep learning was explored for joint prognostic prediction and tumor segmentation in various cancers, resulting in promising performance. This study aims to evaluate the clinical value of multi-task deep learning for prognostic prediction in LA-NPC patients. METHODS: A total of 886 LA-NPC patients acquired from two medical centers were enrolled including clinical data, [18F]FDG PET/CT images, and follow-up of progression-free survival (PFS). We adopted a deep multi-task survival model (DeepMTS) to jointly perform prognostic prediction (DeepMTS-Score) and tumor segmentation from FDG-PET/CT images. The DeepMTS-derived segmentation masks were leveraged to extract handcrafted radiomics features, which were also used for prognostic prediction (AutoRadio-Score). Finally, we developed a multi-task deep learning-based radiomic (MTDLR) nomogram by integrating DeepMTS-Score, AutoRadio-Score, and clinical data. Harrell's concordance indices (C-index) and time-independent receiver operating characteristic (ROC) analysis were used to evaluate the discriminative ability of the proposed MTDLR nomogram. For patient stratification, the PFS rates of high- and low-risk patients were calculated using Kaplan-Meier method and compared with the observed PFS probability. RESULTS: Our MTDLR nomogram achieved C-index of 0.818 (95% confidence interval (CI): 0.785-0.851), 0.752 (95% CI: 0.638-0.865), and 0.717 (95% CI: 0.641-0.793) and area under curve (AUC) of 0.859 (95% CI: 0.822-0.895), 0.769 (95% CI: 0.642-0.896), and 0.730 (95% CI: 0.634-0.826) in the training, internal validation, and external validation cohorts, which showed a statistically significant improvement over conventional radiomic nomograms. Our nomogram also divided patients into significantly different high- and low-risk groups. CONCLUSION: Our study demonstrated that MTDLR nomogram can perform reliable and accurate prognostic prediction in LA-NPC patients, and also enabled better patient stratification, which could facilitate personalized treatment planning.
引用
- Gu B, Meng M, Xu M, et al. Multi-task deep learning-based radiomic nomogram for prognostic prediction in locoregionally advanced nasopharyngeal carcinoma. Eur J Nucl Med Mol Imaging. 2023. PMID: 37596343. doi:10.1007/s00259-023-06399-7
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。