发表机构
Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出MM-DiT框架，通过多模态预训练整合CT图像与放射剂量分布，可联合估计RP风险并量化三类不确定性，在独立队列中验证了其预测准确性与不确定性量化能力。
AI 中文摘要
放射性肺炎（RP）是胸部放射治疗常见且具有临床意义的毒性反应，可导致肺部发病并损害生活质量。尽管基于传统剂量体积直方图的指标和正常组织并发症概率模型被广泛用于RP风险评估，但它们无法充分捕捉放射诱导肺损伤背后复杂的空间、解剖及患者特异性因素。近期机器学习方法通过整合多模态临床与影像信息提升了RP风险预测效果，但大多数仅提供点风险估计，未量化单个预测的可靠性，限制了其临床应用潜力。我们提出一种多模态贝叶斯扩散Transformer（MM-DiT）框架，可联合估计RP风险并表征预测不确定性的来源。MM-DiT通过自监督多模态预训练整合计划计算机断层扫描（CT）图像与三维放射剂量分布，减少对有限且可能含噪声的毒性标签的依赖。所得表示进一步通过潜在扩散Transformer优化，并迁移至贝叶斯预测框架以实现概率性RP风险估计。我们纳入可学习的标签噪声模型，明确处理不完美毒性注释引发的不确定性，从而提供个体化RP风险估计，同时附带偶然不确定性、认知不确定性及标签不确定性的互补度量，支持在患者个体层面评估预测可靠性。我们在两个独立队列中评估MM-DiT，采用预测判别力、校准度及不确定性的互补评估方式。结果表明，该框架具备提供准确RP风险估计的潜力，同时可量化具有临床意义的预测不确定性来源。
英文摘要
Radiation pneumonitis (RP) is a common and clinically significant toxicity of thoracic radiation therapy that can cause pulmonary morbidity and impair quality of life. Although conventional dose-volume histogram-based metrics and normal tissue complication probability models are widely used for RP risk assessment, they inadequately capture the complex spatial, anatomical, and patient-specific factors underlying radiation-induced lung injury. Recent machine learning approaches have improved RP risk prediction by integrating multimodal clinical and imaging information; however, most provide a point risk estimate without quantifying the reliability of individual predictions, limiting their potential clinical utility. We propose a Multimodal Bayesian Diffusion Transformer (MM-DiT) framework that jointly estimates RP risk and characterizes the sources of predictive uncertainty. MM-DiT integrates planning computed tomography (CT) images and three-dimensional radiation dose distributions through self-supervised multimodal pre-training, reducing reliance on limited and potentially noisy toxicity labels. The resulting representations are further refined using a latent diffusion transformer and transferred to a Bayesian prediction framework for probabilistic RP risk estimation. A learnable label-noise model is incorporated to explicitly account for uncertainty arising from imperfect toxicity annotations. Therefore, it provides individualized RP risk estimates with complementary measures of aleatoric, epistemic, and label uncertainty, enabling assessment of prediction reliability at the individual-patient level. We evaluated MM-DiT in two independent cohorts using complementary assessments of predictive discrimination, calibration, and uncertainty. The results demonstrate its potential to provide accurate RP risk estimates while quantifying clinically relevant sources of predictive uncertainty.
Comments30 pages, 7 figures, 4 tables
