The aim of this study was to validate a previously developed deep learning model in 5 independent clinical trials. The predictive performance of this model was compared with the international prognostic index (IPI) and 2 models incorporating radiomic PET/CT features (clinical PET and PET models). Methods: In total, 1,132 diffuse large B-cell lymphoma patients were included: 296 for training and 836 for external validation. The primary outcome was 2-y time to progression. The deep learning model was trained on maximum-intensity projections from PET/CT scans. The clinical PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, SUV_peak, age, and performance status. The PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, and SUV_peak. Model performance was assessed using the area under the curve (AUC) and Kaplan–Meier curves. Results: The IPI yielded an AUC of 0.60 on all external data. The deep learning model yielded a significantly higher AUC of 0.66 (P < 0.01). For each individual clinical trial, the model was consistently better than IPI. Radiomic model AUCs remained higher for all clinical trials. The deep learning and clinical PET models showed equivalent performance (AUC, 0.69; P > 0.05). The PET model yielded the highest AUC of all models (AUC, 0.71; P < 0.05). Conclusion: The deep learning model predicted outcome in all trials with a higher performance than IPI and better survival curve separation. This model can predict treatment outcome in diffuse large B-cell lymphoma without tumor delineation but at the cost of a lower prognostic performance than with radiomics.

本研究的目的是在 5 项独立临床试验中验证先前开发的深度学习模型。将该模型的预测性能与国际预后指数 （IPI） 和 2 个结合放射组学 PET/CT 特征的模型 （临床 PET 和 PET 模型） 进行比较。方法：总共纳入了 1,132 名弥漫性大 B 细胞淋巴瘤患者：296 名用于训练，836 名用于外部验证。主要结局是 2 y 进展时间。深度学习模型是在 PET/CT 扫描的最大强度投影上训练的。临床 PET 模型包括代谢肿瘤体积、从最大病灶到另一个病灶的最大距离、SUV_峰值、年龄和体能状态。PET 模型包括代谢肿瘤体积、从最大病灶到另一个病灶的最大距离和 SUV_峰值。使用曲线下面积 （AUC） 和 Kaplan-Meier 曲线评估模型性能。结果：IPI 在所有外部数据上产生的 AUC 为 0.60。深度学习模型的 AUC 显着更高，为 0.66 （P < 0.01）。对于每项单独的临床试验，该模型始终优于 IPI。在所有临床试验中，放射组学模型 AUC 仍然较高。深度学习和临床 PET 模型显示出相同的性能 （AUC，0.69;P > 0.05）。PET 模型在所有模型中产生最高的 AUC（AUC，0.71;P < 0.05）。结论：深度学习模型预测了所有试验的结果，性能高于 IPI，生存曲线分离效果更好。该模型可以预测弥漫性大 B 细胞淋巴瘤的治疗结果，无需描绘肿瘤，但代价是预后表现低于放射组学。