Inter-individual variation in fat distribution is increasingly recognized as clinically important but is not routinely assessed in clinical practice, in part because medical imaging has not been practical to deploy at scale for this task. Here, we report a deep learning model trained on an individual’s body shape outline—or “silhouette” —that enables accurate estimation of specific fat depots of interest, including visceral (VAT), abdominal subcutaneous (ASAT), and gluteofemoral (GFAT) adipose tissue volumes, and VAT/ASAT ratio. Two-dimensional coronal and sagittal silhouettes are constructed from whole-body magnetic resonance images in 40,032 participants of the UK Biobank and used as inputs for a convolutional neural network to predict each of these quantities. Mean age of the study participants is 65 years and 51% are female. A cross-validated deep learning model trained on silhouettes enables accurate estimation of VAT, ASAT, and GFAT volumes (R²: 0.88, 0.93, and 0.93, respectively), outperforming a comparator model combining anthropometric and bioimpedance measures (ΔR² = 0.05–0.13). Next, we study VAT/ASAT ratio, a nearly body-mass index (BMI)—and waist circumference-independent marker of metabolically unhealthy fat distribution. While the comparator model poorly predicts VAT/ASAT ratio (R²: 0.17–0.26), a silhouette-based model enables significant improvement (R²: 0.50–0.55). Increased silhouette-predicted VAT/ASAT ratio is associated with increased risk of prevalent and incident type 2 diabetes and coronary artery disease independent of BMI and waist circumference. These results demonstrate that body silhouette images can estimate important measures of fat distribution, laying the scientific foundation for scalable population-based assessment.

脂肪分布的个体间差异越来越被认为具有临床重要性，但在临床实践中并未进行常规评估，部分原因是医学成像尚未在这项任务中大规模部署。在这里，我们报告了一种根据个人体型轮廓（或“轮廓”）进行训练的深度学习模型，该模型能够准确估计感兴趣的特定脂肪库，包括内脏 (VAT)、腹部皮下 (ASAT) 和臀股 (GFAT) 脂肪组织体积和 VAT/ASAT 比率。二维冠状和矢状轮廓是根据英国生物银行 40,032 名参与者的全身磁共振图像构建的，并用作卷积神经网络的输入来预测每个量。研究参与者的平均年龄为 65 岁，其中 51% 为女性。在轮廓上训练的交叉验证深度学习模型可以准确估计 VAT、ASAT 和 GFAT 体积（R ²分别为 0.88、0.93 和 0.93），优于结合人体测量和生物阻抗测量的比较器模型（Δ R ²  = 0.05） –0.13）。接下来，我们研究 VAT/ASAT 比率，这是一种与体重指数 (BMI) 和腰围无关的代谢不健康脂肪分布标记。虽然比较模型对 VAT/ASAT 比率的预测效果不佳 ( R ² : 0.17–0.26)，但基于轮廓的模型可以显着改善 ( R ² : 0.50–0.55)。轮廓预测的 VAT/ASAT 比率增加与 2 型糖尿病和冠状动脉疾病的流行和发病风险增加相关，与 BMI 和腰围无关。这些结果表明，身体轮廓图像可以估计脂肪分布的重要指标，为可扩展的基于人群的评估奠定了科学基础。