基于图像的不确定性感知剩余寿命预测

摘要

通过图像预测与死亡率相关的指标，为可及、无创且可扩展的健康筛查提供了前景。我们提出了一种方法，利用预训练的视觉Transformer基础模型，从面部和全身图像中估算剩余寿命，并辅以稳健的不确定性量化。研究表明，预测不确定性会随真实剩余寿命呈现系统性变化，且通过为每个样本学习高斯分布，可有效建模这种不确定性。我们的方法在已建立的数据集上实现了7.48年的平均绝对误差（MAE），达到当前最优水平；在本研究整理并发布的两个更高质量新数据集上，MAE进一步降至4.79年和5.07年。尤为重要的是，我们的模型提供了校准良好的不确定性估计，其分桶预期校准误差仅为0.62年。尽管这些成果并非为临床部署设计，但它们凸显了从图像中提取医学相关信号的潜力。我们公开了所有代码和数据集，以促进进一步研究。

English

Predicting mortality-related outcomes from images offers the prospect of accessible, noninvasive, and scalable health screening. We present a method that leverages pretrained vision transformer foundation models to estimate remaining lifespan from facial and whole-body images, alongside robust uncertainty quantification. We show that predictive uncertainty varies systematically with the true remaining lifespan, and that this uncertainty can be effectively modeled by learning a Gaussian distribution for each sample. Our approach achieves state-of-the-art mean absolute error (MAE) of 7.48 years on an established Dataset, and further improves to 4.79 and 5.07 years MAE on two new, higher-quality datasets curated and published in this work. Importantly, our models provide well-calibrated uncertainty estimates, as demonstrated by a bucketed expected calibration error of 0.62 years. While not intended for clinical deployment, these results highlight the potential of extracting medically relevant signals from images. We make all code and datasets available to facilitate further research.

基于图像的不确定性感知剩余寿命预测

Uncertainty-Aware Remaining Lifespan Prediction from Images

摘要

Support