摘要：当仅有少量既往观测时，稀疏的纵向 CT 随访会限制病灶尺寸预测。我们基于 DeepLesion 和 Deep Lesion Tracker（DLT）构建了一个包含五次随访的、由 DLT 衍生的同一病灶轨迹基准数据集，涵盖 129 名患者的 205 条轨迹。我们比较了一项探索性的传统“稀疏观测至最终结果”分析，以及一项主要的固定访视索引预测跨度设计：该设计在逐步加入更早期观测的同时，预测从 T3 到 T4 的共同对数变化；并评估预测准确性、不确定性可靠性、事后保形区间校准、亚组表现以及 Gompertz 启发式轨迹正则化。所评估方法的点预测准确性存在部分重叠，但其不确定性行为不同。在 10 个训练随机种子的平均留出集结果中，m = 1、2、3、4 时的 RMSE 分别为 0.4726、0.4305、0.4499 和 0.4513，表明 m = 2 时平均 RMSE 最低；增加更多历史观测并未改善 RMSE。在 m = 4 时，原始 Cohort-Level Feature GP 的覆盖率接近 95% 的标称水平，而 MC Dropout、Deep Ensemble 和基于残差尺度的区间则较为保守。患者级保形校准通常以更宽的区间为代价，实现接近标称水平或更保守的覆盖率。按患者分组的开发集交叉验证为 Gompertz 启发式项选择了 lambda* = 0。全局人群参考值经常与病灶级变化方向相反，且不同解剖学亚组之间的预测难度存在差异。总体而言，一旦控制预测时间跨度，额外的历史观测带来的预测收益有限；预测准确性、不确定性可靠性与轨迹一致性也不一定会同步改善，因此应在稀疏纵向医学影像任务中对其进行联合评估。

Abstract:Sparse longitudinal CT follow-up limits lesion-size forecasting when only a few prior observations are available. We constructed a five-visit DLT-derived same-lesion trajectory benchmark from DeepLesion and Deep Lesion Tracker (DLT), yielding 205 trajectories from 129 patients. We compared an exploratory conventional sparse-to-final analysis with a primary fixed visit-index horizon design predicting the common log change from T3 to T4 while progressively adding earlier observations, evaluating predictive accuracy, uncertainty reliability, post-hoc conformal interval calibration, subgroup performance, and Gompertz-inspired trajectory regularization. The evaluated methods showed partially overlapping point-prediction accuracy but distinct uncertainty behavior. Mean held-out RMSE across ten training seeds was 0.4726, 0.4305, 0.4499, and 0.4513 for m = 1, 2, 3, 4, indicating the lowest mean RMSE at m = 2; additional history did not improve RMSE. At m = 4, raw Cohort-Level Feature GP coverage was near the 95% nominal level, whereas MC Dropout, Deep Ensemble, and residual-scale intervals were conservative. Patient-level conformal calibration generally produced near-nominal or conservative coverage at the cost of wider intervals. Patient-grouped development cross-validation selected lambda* = 0 for the Gompertz-inspired term. A global population reference frequently opposed lesion-level change directions, and prediction difficulty varied across anatomical subgroups. Overall, additional historical observations provided limited predictive benefit once the prediction horizon was controlled, while predictive accuracy, uncertainty reliability, and trajectory consistency did not necessarily improve together, and should be evaluated jointly in sparse longitudinal imaging.