文献速递神经核医学肿瘤 PET/CT

基于深度学习的平扫CT脑区划分实现免MRI的脑淀粉样蛋白PET定量

Deep Learning-Based Precontrast CT Parcellation for MRI-Free Brain Amyloid PET Quantification.
PubMed 文献 · Clin Nucl Med · 2025-01-29

本研究利用226例受试者的PET/CT与T1加权MRI配对数据,训练3个UNet在CT上进行脑区划分并集成,以在18F-FBB PET/CT中不依赖高分辨率MRI完成淀粉样蛋白定量。基于CT的深度学习划分与基于MRI的FreeSurfer方法高度一致,全局和区域SUVR的组内相关系数≥0.988。

要点

  • 基于CT的深度学习脑区划分在46个感兴趣区平均Dice系数为0.80。
  • 区域和全局SUVR比较的线性回归R²≥0.976,组内相关系数≥0.988。
  • 基于MRI和基于CT的全局SUVR均随临床痴呆评定量表评分增加而一致升高。

核心结论

  • 基于深度学习的CT脑区划分与基于MRI的方法在淀粉样蛋白PET定量上高度一致。

研究设计与样本

  • 回顾性数据集包含226例受试者的PET/CT与T1加权MRI配对数据,其中157例为轻度认知障碍或痴呆,69例为健康对照。
  • 数据集按60%训练/验证集和40%测试集划分,利用自动生成的分割标签独立训练3个UNet在CT上进行多平面脑区划分并集成。
  • 淀粉样蛋白负荷在源自Desikan-Killiany-Tourville图谱的46个感兴趣区中测量,计算所提出CT深度学习模型与基于MRI的FreeSurfer方法之间的Dice相似系数。

主要发现

  • 基于深度学习的CT划分在全部46个感兴趣区的平均Dice相似系数为0.80,16个皮层和边缘系统感兴趣区为0.72,30个皮层下感兴趣区为0.83。
  • 区域和全局SUVR比较的线性回归斜率、y截距和R²分别为1±0.027、0±0.040和≥0.976(P<0.001),组内相关系数≥0.988(P<0.001)。
  • 各临床痴呆评定量表评分组(0、0.5、1)的全局SUVR对应值分别为1±0.020、0±0.026、≥0.993和≥0.996(P<0.001)。
  • 基于MRI和基于CT的全局SUVR均随临床痴呆评定量表评分增加而一致升高。

关键数值与推荐

  • 46个感兴趣区的平均Dice相似系数为0.80,16个皮层和边缘系统感兴趣区为0.72,30个皮层下感兴趣区为0.83。
  • 区域和全局SUVR线性回归斜率1±0.027、y截距0±0.040、R²≥0.976(P<0.001),组内相关系数≥0.988(P<0.001)。
  • 临床痴呆评定量表评分0、0.5、1组的全局SUVR线性回归斜率1±0.020、y截距0±0.026、R²≥0.993、组内相关系数≥0.996(P<0.001)。

临床怎么用

  • 原文未据此给出推荐。

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: This study aimed to develop a deep learning (DL) model for brain region parcellation using CT data from PET/CT scans to enable accurate amyloid quantification in 18 F-FBB PET/CT without relying on high-resolution MRI. PATIENTS AND METHODS: A retrospective dataset of PET/CT and T1-weighted MRI pairs from 226 individuals (157 with mild cognitive impairment or dementia and 69 healthy controls) was used. The dataset was split into training/validation (60%) and test (40%) sets. Utilizing auto-generated segmentation labels, 3 UNets were independently trained for multiplanar brain parcellation on CT and subsequently ensembled. Amyloid load was measured across 46 volumes of interest (VOIs), derived from the Desikan-Killiany-Tourville atlas. Dice similarity coefficient between the proposed CT-based DL model and MRI-based (FreeSurfer) method was calculated, with SUVR comparison using linear regression analysis and intraclass correlation coefficient. Global SUVRs were also compared within groups with clinical dementia ratings (CDRs) of 0, 0.5, and 1. RESULTS: The DL-based CT parcellation achieved mean Dice similarity coefficients of 0.80 for all 46 VOIs, 0.72 for 16 cortical and limbic VOIs, and 0.83 for 30 subcortical VOIs. For regional and global SUVR comparisons, the linear regression yielded a slope, y-intercept, and R2 of 1 ± 0.027, 0 ± 0.040, and ≧0.976, respectively ( P < 0.001), and the intraclass correlation coefficient was ≧0.988 ( P < 0.001). For global SUVRs in each CDR group, these values were 1 ± 0.020, 0 ± 0.026, ≧0.993, and ≧0.996, respectively ( P < 0.001). Both MRI-based and CT-based global SUVR showed a consistent increase as the CDR score increased. CONCLUSIONS: The DL-based CT parcellation agrees strongly with MRI-based methods for amyloid PET quantification.

来源:Clin Nucl Med,查看原文。版权归原作者所有。

引用

  1. Choo K, Joo J, Lee S, et al. Deep Learning-Based Precontrast CT Parcellation for MRI-Free Brain Amyloid PET Quantification. Clin Nucl Med. 2025. PMID: 39876079. doi:10.1097/RLU.0000000000005652

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。