Interdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing, Newcastle University, Newcastle upon Tyne, UK.
Department of Dermatology, Erasmus MC University Medical Center Rotterdam, Rotterdam, The Netherlands.
J Eur Acad Dermatol Venereol. 2024 Dec;38(12):2295-2302. doi: 10.1111/jdv.20365. Epub 2024 Oct 3.
Perceived age (PA) has been associated with mortality, genetic variants linked to ageing and several age-related morbidities. However, estimating PA in large datasets is laborious and costly to generate, limiting its practical applicability.
To determine if estimating PA using deep learning-based algorithms results in the same associations with morbidities and genetic variants as human-estimated perceived age.
Self-supervised learning (SSL) and deep feature transfer (DFT) deep learning (DL) approaches were trained and tested on human-estimated PAs and their corresponding frontal face images of middle-aged to elderly Dutch participants (n = 2679) from a population-based study in the Netherlands. We compared the DL-estimated PAs with morbidities previously associated with human-estimated PA as well as genetic variants in the gene MC1R; we additionally tested the PA associations with MC1R in a new validation cohort (n = 1158).
The DL approaches predicted PA in this population with a mean absolute error of 2.84 years (DFT) and 2.39 years (SSL). In the training-test dataset, we found the same significant (p < 0.05) associations for DL PA with osteoporosis, ARHL, cognition, COPD and cataracts and MC1R, as with human PA. We also found a similar but less significant association for SSL and DFT PAs (0.69 and 0.71 years per allele, p = 0.008 and 0.011, respectively) with MC1R variants in the validation dataset as that found with human, SSL and DFT PAs in the training-test dataset (0.79, 0.78 and 0.71 years per allele respectively; all p < 0.0001).
Deep learning methods can automatically estimate PA from facial images with enough accuracy to replicate known links between human-estimated perceived age and several age-related morbidities. Furthermore, DL predicted perceived age associated with MC1R gene variants in a validation cohort. Hence, such DL PA techniques may be used instead of human estimations in perceived age studies thereby reducing time and costs.
感知年龄 (PA) 与死亡率、与衰老相关的遗传变异以及多种与年龄相关的疾病有关。然而，在大型数据集中国估计 PA 既费力又昂贵，限制了其实际应用。
确定使用基于深度学习的算法估计 PA 是否会产生与人类估计的感知年龄相同的与发病率和遗传变异的关联。
自监督学习 (SSL) 和深度特征转移 (DFT) 深度学习 (DL) 方法在来自荷兰一项基于人群的研究中的中年至老年荷兰参与者的人类估计的 PA 及其相应的正面面部图像 (n=2679) 上进行了训练和测试。我们比较了 DL 估计的 PA 与以前与人类估计的 PA 相关的发病率以及基因 MC1R 中的遗传变异；我们还在新的验证队列 (n=1158) 中测试了 PA 与 MC1R 的关联。
该方法在该人群中以 2.84 年（DFT）和 2.39 年（SSL）的平均绝对误差预测 PA。在训练-测试数据集，我们发现 DL PA 与骨质疏松症、ARHL、认知、COPD 和白内障以及 MC1R 之间存在相同的显著关联（p<0.05），与人类 PA 相同。我们还发现 SSL 和 DFT PA 与 MC1R 变异体的关联较弱但更显著（分别为每个等位基因 0.69 和 0.71 年，p=0.008 和 0.011），与在训练-测试数据集中发现的人类、SSL 和 DFT PA 与 MC1R 变异体的关联（分别为每个等位基因 0.79、0.78 和 0.71 年；所有 p<0.0001）。
深度学习方法可以从面部图像中自动估计 PA，具有足够的准确性来复制人类估计的感知年龄与几种与年龄相关的疾病之间的已知联系。此外，DL 预测了感知年龄与 MC1R 基因变异体相关，这在验证队列中。因此，在感知年龄研究中，可以使用这种 DL PA 技术代替人类估计，从而减少时间和成本。
