基于深度学习在前列腺切除术后复发患者中利用[68Ga]Ga-PSMA-11 PET/CT对前列腺癌病灶进行全身特征描述
本研究回顾性收集两个中心116例根治性前列腺切除术后复发转移性前列腺癌患者的[68Ga]Ga-PSMA-11 PET/CT图像,将PET与CT数据联合输入3D U-Net进行全身病灶分割与检测,内部测试集DSC为0.631、F1为0.824,外部测试集DSC为0.596、F1为0.837,深度学习与人工勾画计算的肿瘤负荷指标高度相关且一致。
要点
- 3D U-Net在内部测试集病灶检测精确率0.961、召回率0.721、F1值0.824。
- 外部测试集精确率0.888、召回率0.792、F1值0.837,DSC为0.596。
- 深度学习与人工勾画肿瘤负荷指标强相关(R²≥0.991,均P<0.05)且一致。
核心结论
- 3D卷积神经网络能准确描述复发前列腺癌患者的全身肿瘤,其结果与人工勾画高度一致。
- 作者认为该自动方法有望提高工作效率并辅助肿瘤负荷评估。
研究设计与样本
- 回顾性收集两个中心116例根治性前列腺切除术后复发转移性前列腺癌患者的[68Ga]Ga-PSMA-11 PET/CT图像。
- 中心1提供五折交叉验证(n=78)和内部测试(n=19)数据,中心2提供外部测试(n=19)数据。
- PET与CT数据联合输入3D U-Net实现全身病灶分割与检测,采用DSC评估分割,采用召回率、精确率、F1值评估检测。
- 通过线性回归和Bland-Altman图评估自动分割与人工参考标准计算的肿瘤负荷(PSMA-TV和TL-PSMA)的相关性与一致性。
主要发现
- 内部测试集DSC、精确率、召回率、F1值分别为0.631、0.961、0.721、0.824。
- 外部测试集DSC、精确率、召回率、F1值分别为0.596、0.888、0.792、0.837。
- 该方法在全身转移灶分割与检测上优于既往研究。
- 深度学习与人工参考标准计算的肿瘤负荷指标强相关(R²≥0.991,均P<0.05)且一致。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: The automatic segmentation and detection of prostate cancer (PC) lesions throughout the body are extremely challenging due to the lesions' complexity and variability in appearance, shape, and location. In this study, we investigated the performance of a three-dimensional (3D) convolutional neural network (CNN) to automatically characterize metastatic lesions throughout the body in a dataset of PC patients with recurrence after radical prostatectomy. METHODS: We retrospectively collected [68 Ga]Ga-PSMA-11 PET/CT images from 116 patients with metastatic PC at two centers: center 1 provided the data for fivefold cross validation (n = 78) and internal testing (n = 19), and center 2 provided the data for external testing (n = 19). PET and CT data were jointly input into a 3D U-Net to achieve whole-body segmentation and detection of PC lesions. The performance in both the segmentation and the detection of lesions throughout the body was evaluated using established metrics, including the Dice similarity coefficient (DSC) for segmentation and the recall, precision, and F1-score for detection. The correlation and consistency between tumor burdens (PSMA-TV and TL-PSMA) calculated from automatic segmentation and artificial ground truth were assessed by linear regression and Bland‒Altman plots. RESULTS: On the internal test set, the DSC, precision, recall, and F1-score values were 0.631, 0.961, 0.721, and 0.824, respectively. On the external test set, the corresponding values were 0.596, 0.888, 0.792, and 0.837, respectively. Our approach outperformed previous studies in segmenting and detecting metastatic lesions throughout the body. Tumor burden indicators derived from deep learning and ground truth showed strong correlation (R2 ≥ 0.991, all P < 0.05) and consistency. CONCLUSION: Our 3D CNN accurately characterizes whole-body tumors in relapsed PC patients; its results are highly consistent with those of manual contouring. This automatic method is expected to improve work efficiency and to aid in the assessment of tumor burden.
引用
- Huang B, Yang Q, Li X, et al. Deep learning-based whole-body characterization of prostate cancer lesions on [68Ga]Ga-PSMA-11 PET/CT in patients with post-prostatectomy recurrence. Eur J Nucl Med Mol Imaging. 2023. PMID: 38049657. doi:10.1007/s00259-023-06551-3
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。