文献速递肿瘤 PET/CT核素与放射性配体治疗

全身68Ga-DOTATATE PET/CT上嗜铬细胞瘤和副神经节瘤病灶自动分割人工智能模型

An automated pheochromocytoma and paraganglioma lesion segmentation AI-model at whole-body 68Ga- DOTATATE PET/CT.
PubMed 文献 · EJNMMI Res · 2024-11-05

本研究基于38例转移性及不可手术嗜铬细胞瘤和副神经节瘤(PPGL)患者的132次68Ga-DOTATATE PET/CT扫描,训练3D nnUNet模型实现全身病灶自动分割与肿瘤负荷计算。模型在PPGL测试集扫描水平DSC为0.88,病灶水平灵敏度86%、阳性预测值89%;在NET和ONB队列中病灶水平灵敏度分别为61.13%和61.64%。

要点

  • 模型在PPGL测试集扫描水平DSC为0.88,病灶水平灵敏度86%、阳性预测值89%。
  • PPGL队列中较小且低摄取的病灶被AI模型漏检(p < 0.001)。
  • 所有队列中假阴性和假阳性病灶多位于肝脏,主要因肝脏生理性高背景活动和图像噪声。

核心结论

  • 所开发的深度学习AI模型在全身68Ga-DOTATATE PET/CT图像上对转移性PPGL病灶的自动分割表现出可靠性能,可能有助于治疗随访期间客观评估肿瘤负荷。

研究设计与样本

  • 研究纳入38例转移性及不可手术PPGL患者的132次68Ga-DOTATATE PET/CT扫描,按70次扫描(20例患者)为训练集、62次扫描(18例患者)为测试集划分。
  • 训练集进一步按患者分层分为5折进行交叉验证,训练3D全分辨率nnUNet配置。
  • 模型在PPGL测试集以及NET(n = 9)和嗅神经母细胞瘤(ONB,n = 5)两个其他临床队列中评估扫描水平和病灶水平检测性能。
  • 对SUVmax、总病灶摄取(TLU)和总肿瘤体积(TTV)等PET参数进行定量统计分析。

主要发现

  • nnUNet AI模型在扫描水平获得平均5折验证Dice相似系数0.84。
  • 模型在PPGL测试集、NET队列和ONB队列的扫描水平DSC分别为0.88、0.6和0.67。
  • 模型在PPGL测试集、NET队列和ONB队列的病灶水平灵敏度分别为86%、61.13%和61.64%。
  • 模型在PPGL测试集、NET队列和ONB队列的病灶水平阳性预测值分别为89%、74%和86.54%。
  • PPGL队列中较小且低摄取的病灶被AI模型漏检(p < 0.001);所有队列中假阴性和假阳性病灶多位于肝脏,主要因肝脏生理性高背景活动和68Ga-DOTATATE PET图像噪声。

关键数值与推荐

  • 扫描水平平均5折验证Dice相似系数为0.84。
  • PPGL测试集扫描水平DSC为0.88,病灶水平灵敏度86%、阳性预测值89%。
  • NET队列扫描水平DSC为0.6,病灶水平灵敏度61.13%、阳性预测值74%。
  • ONB队列扫描水平DSC为0.67,病灶水平灵敏度61.64%、阳性预测值86.54%。
  • PPGL队列中小且低摄取病灶被漏检(p < 0.001)。

临床怎么用

  • 原文结论指出该AI模型可能有助于治疗随访期间客观评估肿瘤负荷。

局限性

  • PPGL队列中较小且低摄取的病灶被AI模型漏检(p < 0.001)。
  • 所有队列中假阴性和假阳性病灶多位于肝脏,主要因肝脏生理性高背景活动和68Ga-DOTATATE PET图像噪声。

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

BACKGROUND: Somatostatin receptor (SSR) targeting radiotracer 68Ga-DOTATATE is used for Positron Emission Tomography (PET)/Computed Tomography (CT) imaging to assess patients with Pheochromocytoma and paraganglioma (PPGL), rare types of Neuroendocrine tumor (NET) which can metastasize thereby becoming difficult to quantify. The goal of this study is to develop an artificial intelligence (AI) model for automated lesion segmentation on whole-body 3D DOTATATE-PET/CT and to automate the tumor burden calculation. 132 68Ga-DOTATATE PET/CT scans from 38 patients with metastatic and inoperable PPGL, were split into 70, and 62 scans, from 20, and 18 patients for training, and test sets, respectively. The training set was further divided into patient-stratified 5 folds for cross-validation. 3D-full resolution nnUNet configuration was trained with 5-fold cross-validation. The model's detection performance was evaluated at both scan and lesion levels for the PPGL test set and two other clinical cohorts with NET (n = 9) and olfactory neuroblastoma (ONB, n = 5). Additionally, quantitative statistical analysis of PET parameters including SUVmax, total lesion uptake (TLU), and total tumor volume (TTV), was conducted. RESULTS: The nnUNet AI model achieved an average 5-fold validation dice similarity coefficient of 0.84 at the scan level. The model achieved dice similarity coefficients (DSC) of 0.88, 0.6, and 0.67 at the scan level, the sensitivity of 86%, 61.13%, and 61.64%, and a positive predictive value of 89%, 74%, and 86.54% at the lesion level for the PPGL test, NET and ONB cohorts, respectively. For PPGL cohorts, smaller lesions with low uptake were missed by the AI model (p < 0.001). Anatomical region-based failure analysis showed most of the false negative and false positive lesions within the liver for all the cohorts, mainly due to the high physiologic liver background activity and image noise on 68Ga- DOTATATE PET scans. CONCLUSIONS: The developed deep learning-based AI model showed reliable performance for automated segmentation of metastatic PPGL lesions on whole-body 68Ga-DOTATATE-PET/CT images, which may be beneficial for tumor burden estimation for objective evaluation during therapy follow-up. https://www. CLINICALTRIALS: gov/study/NCT03206060 , https://www. CLINICALTRIALS: gov/study/NCT04086485 , https://www. CLINICALTRIALS: gov/study/NCT05012098 .

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Haque F, Carrasquillo JA, Turkbey EB, et al. An automated pheochromocytoma and paraganglioma lesion segmentation AI-model at whole-body 68Ga- DOTATATE PET/CT. EJNMMI Res. 2024. PMID: 39500789. doi:10.1186/s13550-024-01168-5

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。