针对前列腺癌（APC）患者而言，根据METastasis Reporting and Data System for Prostate Cancer（MET-RADS-P）标准对治疗反应的评估是一项重要但耗时的任务。深度学习算法有潜力辅助进行评估。本研究旨在开发和评估一种基于深度学习的半自动化治疗反应算法，用于盆腔淋巴结的评估。纳入了至少进行了两次扫描以进行APC转移治疗后随访评估的162名患者。使用先前报道的深度学习模型自动分割盆腔淋巴结。使用Dice相似系数（DSC）和体积相似度（VS）评估深度学习算法的性能。使用Bland-Altman绘图评估短直径测量与放射科医师的一致性。根据淋巴结分割，使用基于规则的程序自动评估治疗效果，符合MET-RADS-P标准。使用Kappa统计方法评估深度学习模型和两位放射科医师（主治医师（R1）和住院医师（R2））的治疗效果评估的准确性和一致性。 盆腔淋巴结分割的平均DSC和VS分别为0.82±0.09和0.88±0.12。Bland-Altman绘图显示，大多数淋巴结测量值在协议的上界和下界之间。基于自动分割的评估的准确度为目标病变0.92（95％CI：0.85-0.96），非目标病变0.91（95％CI：0.86-0.95）和非病理性病变75％（95％CI：0.46-0.92）。基于自动分割和手动分割的治疗效果评估的一致性对于目标病变非常好[K值：0.92（0.86-0.98）]，对于非目标病变而言较好[0.82（0.74-0.90）]，对于非病理性病变而言中等[0.71（0.50-0.92）]。基于深度学习的半自动算法在盆腔淋巴结的治疗反应评估方面表现良好，与放射科医师具有可比性。©2023年，作者。

The evaluation of treatment response according to METastasis Reporting and Data System for Prostate Cancer (MET-RADS-P) criteria is an important but time-consuming task for patients with advanced prostate cancer (APC). A deep learning-based algorithm has the potential to assist with this assessment.To develop and evaluate a deep learning-based algorithm for semiautomated treatment response assessment of pelvic lymph nodes.A total of 162 patients who had undergone at least two scans for follow-up assessment after APC metastasis treatment were enrolled. A previously reported deep learning model was used to perform automated segmentation of pelvic lymph nodes. The performance of the deep learning algorithm was evaluated using the Dice similarity coefficient (DSC) and volumetric similarity (VS). The consistency of the short diameter measurement with the radiologist was evaluated using Bland-Altman plotting. Based on the segmentation of lymph nodes, the treatment response was assessed automatically with a rule-based program according to the MET-RADS-P criteria. Kappa statistics were used to assess the accuracy and consistency of the treatment response assessment by the deep learning model and two radiologists [attending radiologist (R1) and fellow radiologist (R2)].The mean DSC and VS of the pelvic lymph node segmentation were 0.82 ± 0.09 and 0.88 ± 0.12, respectively. Bland-Altman plotting showed that most of the lymph node measurements were within the upper and lower limits of agreement (LOA). The accuracies of automated segmentation-based assessment were 0.92 (95% CI: 0.85-0.96), 0.91 (95% CI: 0.86-0.95) and 75% (95% CI: 0.46-0.92) for target lesions, nontarget lesions and nonpathological lesions, respectively. The consistency of treatment response assessment based on automated segmentation and manual segmentation was excellent for target lesions [K value: 0.92 (0.86-0.98)], good for nontarget lesions [0.82 (0.74-0.90)] and moderate for nonpathological lesions [0.71 (0.50-0.92)].The deep learning-based semiautomated algorithm showed high accuracy for the treatment response assessment of pelvic lymph nodes and demonstrated comparable performance with radiologists.© 2023. The Author(s).