用于多模态纵向图像插补与插值的隐式神经表示

中文摘要 AI 辅助

纵向多参数MRI是肿瘤随访成像的核心，但真实临床数据存在序列缺失、采集协议异质性、不同时间点空间分辨率不一等问题。我们提出一种患者特异性条件隐式神经表示（INR），将多模态纵向MRI建模为世界坐标、时间和模态条件的连续函数。该模型通过随机模态丢弃训练以处理不完整数据，其连续坐标空间公式无需重采样到固定体素网格即可实现空间与时间插值。推理时，从跨模态重建性能推导出自一致性置信度估计器。我们在儿科脑肿瘤患者的纵向MRI上评估该框架，结果显示其对T1CE和FLAIR的线性插值有统计学显著改进（p < 0.05），T1CE的平均MS-SSIM为0.95 ± 0.02；预测置信度与真实重建质量强相关（皮尔逊相关系数r最高达0.996），表明其在异质性临床环境中具备可靠部署潜力。

英文摘要

Longitudinal multiparametric MRI is central to follow-up imaging in oncology, yet real-world clinical data are characterised by missing sequences, heterogeneous acquisition protocols, and varying spatial resolutions across time points. We propose a patient-specific conditional implicit neural representation (INR) that models multimodal longitudinal MRI as a continuous function of world coordinates, time, and modality conditioning. The model is trained with stochastic modality dropout to handle incomplete data, and its continuous coordinate-space formulation enables both spatial and temporal interpolation without resampling to a fixed voxel grid. A self-consistency-based confidence estimator is derived from cross-modal reconstruction performance at inference time. We evaluate the framework on longitudinal MRI from paediatric brain tumour patients, demonstrating statistically significant improvements over linear interpolation for T1CE and FLAIR (p < 0.05), with mean MS-SSIM of 0.95 $\pm$ 0.02 for T1CE. Predicted confidence correlates strongly with true reconstruction quality (Pearson r up to 0.996), suggesting reliable deployment potential in heterogeneous clinical settings.

发表机构

• University Hospital Augsburg（奥格斯堡大学医院）
• University of Augsburg（奥格斯堡大学）
• Technical University of Munich（慕尼黑工业大学）
• Bavarian Cancer Research Center (BZKF)（巴伐利亚癌症研究中心）
• Swabian Children’s Cancer Center（施瓦本儿童癌症中心）

机构由 AI 辅助整理，请以论文原文为准。