从通过机器学习 (ML) 建模的前列腺特异性膜抗原 (PSMA)-PET 中提取的放射组学可用于预测疾病风险。然而，缺乏对先前提出的方法的验证。我们的目的是优化和验证基于 18F-DCFPyL-PET 放射组学的 ML 模型，用于预测原发性前列腺癌 (PCa) 患者的淋巴结受累 (LNI)、囊外扩展 (ECE) 和术后格里森评分 (GS)。对在根治性前列腺切除术和盆腔淋巴结清扫术之前接受 18F-DCFPyL-PET/CT 的中危至高危 PCa 患者进行评估。训练数据集包括 72 名患者，内部验证数据集包括 24 名患者，外部验证数据集包括 27 名患者。在 PET 上半自动描绘出富含 PSMA 的前列腺内病变，并提取了 480 个放射组学特征。传统的 PET 指标是为了进行比较分析而得出的。在训练数据集上重复进行 5 倍交叉验证 (CV) 来优化分割、预处理和 ML 方法。训练后的模型在组合验证数据集上进行了测试。战斗协调适用于外部放射组学数据。使用受试者工作特征曲线 (AUC) 评估模型性能。训练数据集中的 LNI、ECE 和 GS 的 CV-AUC 分别为 0.88、0.79 和 0.84。在组合验证数据集中，ML 模型可以显着预测 GS，AUC 为 0.78（p<0.05）。然而，LNI 和 ECE 预测的验证 AUC 并不显着（分别为 0.57 和 0.63）。传统的基于 PET 指标的模型的 LNI（0.59，p>0.05）和 ECE（0.66，p>0.05）的 AUC 相当，但 GS 的 AUC 较低（0.73，p<0.05）。一般来说，Combat 协调提高了外部验证 AUC（-0.03 至 0.18）。在内部和外部验证中，基于 18F-DCFPyL-PET 放射组学的 ML 模型预测中高危 PCa 术后高 GS，但不能预测 LNI 或 ECE。因此，临床获益似乎有限。这些结果强调需要对基于 PET 放射组学的 ML 模型分析进行外部和/或多中心验证，以评估其普遍性。版权所有：© 2023 Luining 等人。这是一篇根据知识共享署名许可条款分发的开放获取文章，允许在任何媒体上不受限制地使用、分发和复制，前提是注明原始作者和来源。

Radiomics extracted from prostate-specific membrane antigen (PSMA)-PET modeled with machine learning (ML) may be used for prediction of disease risk. However, validation of previously proposed approaches is lacking. We aimed to optimize and validate ML models based on 18F-DCFPyL-PET radiomics for the prediction of lymph-node involvement (LNI), extracapsular extension (ECE), and postoperative Gleason score (GS) in primary prostate cancer (PCa) patients.Patients with intermediate- to high-risk PCa who underwent 18F-DCFPyL-PET/CT before radical prostatectomy with pelvic lymph-node dissection were evaluated. The training dataset included 72 patients, the internal validation dataset 24 patients, and the external validation dataset 27 patients. PSMA-avid intra-prostatic lesions were delineated semi-automatically on PET and 480 radiomics features were extracted. Conventional PET-metrics were derived for comparative analysis. Segmentation, preprocessing, and ML methods were optimized in repeated 5-fold cross-validation (CV) on the training dataset. The trained models were tested on the combined validation dataset. Combat harmonization was applied to external radiomics data. Model performance was assessed using the receiver-operating-characteristics curve (AUC).The CV-AUCs in the training dataset were 0.88, 0.79 and 0.84 for LNI, ECE, and GS, respectively. In the combined validation dataset, the ML models could significantly predict GS with an AUC of 0.78 (p<0.05). However, validation AUCs for LNI and ECE prediction were not significant (0.57 and 0.63, respectively). Conventional PET metrics-based models had comparable AUCs for LNI (0.59, p>0.05) and ECE (0.66, p>0.05), but a lower AUC for GS (0.73, p<0.05). In general, Combat harmonization improved external validation AUCs (-0.03 to +0.18).In internal and external validation, 18F-DCFPyL-PET radiomics-based ML models predicted high postoperative GS but not LNI or ECE in intermediate- to high-risk PCa. Therefore, the clinical benefit seems to be limited. These results underline the need for external and/or multicenter validation of PET radiomics-based ML model analyses to assess their generalizability.Copyright: © 2023 Luining et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.