深度神经网络自动表征68Ga-PSMA-11 PET/CT病灶
本研究基于三个医疗中心193例转移性前列腺癌患者的68Ga-PSMA-11 PET/CT图像,开发三重组合2.5D U-Net深度神经网络自动检测骨盆骨和淋巴结病灶。骨病灶检测精确率99%、召回率99%、F1分数99%;淋巴结病灶检测精确率94%、召回率89%、F1分数92%。分割准确率低于检测,网络性能与训练数据量相关。
要点
- 骨病灶检测精确率99%、召回率99%、F1分数99%
- 淋巴结病灶检测精确率94%、召回率89%、F1分数92%
- 分割准确率低于检测,性能与训练数据量相关
核心结论
- 开发的深度神经网络可自动表征68Ga-PSMA-11 PET/CT上前列腺癌病灶,骨盆区域初步测试证实深度学习方法潜力。
研究设计与样本
- 收集三个医疗中心193例转移性前列腺癌患者的68Ga-PSMA-11 PET/CT图像,聚焦骨盆骨和淋巴结病灶检测。
- 开发三重组合2.5D U-Net深度神经网络,同时从轴位、冠状位和矢状位提取特征。
主要发现
- 骨病灶检测精确率99%、召回率99%、F1分数99%。
- 淋巴结病灶检测精确率94%、召回率89%、F1分数92%。
- 分割准确率低于检测,网络性能与训练数据量相关。
关键数值与推荐
- 骨病灶检测:精确率99%、召回率99%、F1分数99%。
- 淋巴结病灶检测:精确率94%、召回率89%、F1分数92%。
临床怎么用
- 该方法可自动表征68Ga-PSMA-11 PET/CT骨盆区域病灶,有望辅助优化PSMA导向的放射性核素治疗。
局限性
- 初步测试仅限于骨盆区域,分割准确率低于检测,网络性能受训练数据量影响。
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: This study proposes an automated prostate cancer (PC) lesion characterization method based on the deep neural network to determine tumor burden on 68Ga-PSMA-11 PET/CT to potentially facilitate the optimization of PSMA-directed radionuclide therapy. METHODS: We collected 68Ga-PSMA-11 PET/CT images from 193 patients with metastatic PC at three medical centers. For proof-of-concept, we focused on the detection of pelvis bone and lymph node lesions. A deep neural network (triple-combining 2.5D U-Net) was developed for the automated characterization of these lesions. The proposed method simultaneously extracts features from axial, coronal, and sagittal planes, which mimics the workflow of physicians and reduces computational and memory requirements. RESULTS: Among all the labeled lesions, the network achieved 99% precision, 99% recall, and an F1 score of 99% on bone lesion detection and 94%, precision 89% recall, and an F1 score of 92% on lymph node lesion detection. The segmentation accuracy is lower than the detection. The performance of the network was correlated with the amount of training data. CONCLUSION: We developed a deep neural network to characterize automatically the PC lesions on 68Ga-PSMA-11 PET/CT. The preliminary test within the pelvic area confirms the potential of deep learning methods. Increasing the amount of training data should further enhance the performance of the proposed method and may ultimately allow whole-body assessments.
引用
- Zhao Y, Gafita A, Vollnberg B, et al. Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT. Eur J Nucl Med Mol Imaging. 2019. PMID: 31813050. doi:10.1007/s00259-019-04606-y
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。