AI 中文总结
该研究针对NSCLC生存分层难题，用模拟衍生的6种结构化代理特征扩充多模态数据，结合TMAE模型，在Lung1队列取得优于现有方法的预测性能，验证了代理特征的互补价值。
AI 中文摘要
肺癌每年在全球造成约180万人死亡，其中非小细胞肺癌（NSCLC）占大多数病例。尽管治疗取得了进展，但由于常规描述符无法充分捕捉肿瘤内异质性，生存分层仍然具有挑战性。标准的放射组学和深度学习技术将影像特征视为独立的量，忽略了肿瘤特征之间的结构化相互作用。本研究评估结构化代理特征是否可通过扩充治疗前计算机断层扫描（CT）表征、放射组学和临床变量来增强多模态NSCLC生存预测，这些特征包含6个模拟衍生特征，旨在捕捉异质性与形态之间的相互作用。放射组学参数化的细胞自动机通过使用熵和球形度计算低维代理参数，从基线CT生成生长速率和坏死率代理特征。影像主干为基于Transformer的掩码自编码器（TMAE），该模型在同一流程内与其他编码器进行系统评估后被选定，它能提供基于注意力的可视化，突出显示模型关注度较高的肿瘤区域。在公共Lung1队列（n=390）中，主要的四模态融合取得了0.641的C指数（iAUC为0.731，对数秩检验p值<0.001）。在可比的评估方案下，该主要结果优于Lung1上先前的多模态结果（C指数0.631；iAUC 0.592 [15]），而单独的探索性系数优化分析取得了观察到的最佳C指数0.662（iAUC 0.748）。这些结果表明，在Lung1基准内，除了常规的放射组学、深度学习和临床表征外，模拟衍生的代理特征可能提供互补的预测信息。
英文摘要
Lung cancer results in roughly 1.8 million fatalities annually worldwide, with non-small cell lung cancer (NSCLC) comprising the majority of cases. Despite advancements in treatment, survival stratification remains challenging due to intratumoral heterogeneity inadequately captured by conventional descriptors. Standard radiomic and deep learning techniques regard imaging features as independent quantities, overlooking structured interactions between tumor characteristics. We evaluate whether structured proxy features can enhance multimodal NSCLC survival prediction by augmenting pretreatment computed tomography (CT) representations, radiomics, and clinical variables with six simulation-derived features designed to capture interactions between heterogeneity and morphology. A radiomic-parameterized cellular automaton generates growth-rate and necrosis-ratio proxy features from baseline CT by using entropy and sphericity to compute low-dimensional proxy parameters. The imaging backbone is a Transformer-based Masked Autoencoder (TMAE), which was chosen after a systematic evaluation with alternative encoders within the same pipeline and provides attention-based visualizations that highlight tumor regions receiving higher model attention. On the public Lung1 cohort (n = 390), the primary four-modality fusion attained a C-index of 0.641 (iAUC 0.731, log-rank p < 0.001). The primary result compares favorably with prior multimodal results on Lung1 (C-index 0.631; iAUC 0.592 [15]) under a comparable evaluation protocol, while a separate exploratory coefficient-optimization analysis achieved a best observed C-index of 0.662 (iAUC 0.748). These results indicate that, in addition to conventional radiomic, deep, and clinical representations within the Lung1 benchmark, simulation-derived proxy features may provide complementary predictive information within this fixed Lung1 benchmark.
Comments33
