跨厂商、跨示踪剂与跨协议深度迁移学习用于心脏SPECT衰减图生成
研究探讨能否将基于单一扫描仪、示踪剂和协议数据预训练的深度学习网络,用于从不同扫描仪、示踪剂和协议采集的心脏SPECT生成CT来源的衰减图(μ图)。先用120例经99mTc-替曲膦(99mTc-tetrofosmin)注射、GE 850 SPECT/CT 360度机架旋转采集的检查预训练网络,再用80例经99mTc-甲氧基异丁基异腈(99mTc-sestamibi)注射、Philips BrightView SPECT/CT 180度机架旋转采集的检查微调并测试。迁移学习所得预测μ图与真实值的误差为5.13 ± 7.02%,低于未微调直接迁移的8.24 ± 5.01%和有限样本训练的6.45 ± 5.75%。
要点
- 迁移学习生成μ图误差为5.13 ± 7.02%,低于未微调直接迁移的8.24 ± 5.01%。
- 用预测μ图重建图像的误差为1.11 ± 1.57%,低于未微调直接迁移的1.72 ± 1.63%。
- 经适当迁移学习,可将一个扫描仪大数据预训练的网络用于另一扫描仪不同示踪剂和协议的数据。
核心结论
- 经适当迁移学习,可将一个扫描仪大量数据预训练的网络应用于另一扫描仪使用不同示踪剂和协议采集的数据。
研究设计与样本
- 预训练使用120例注射99mTc-替曲膦、GE 850 SPECT/CT 360度机架旋转采集的检查。
- 微调与测试使用80例注射99mTc-甲氧基异丁基异腈、Philips BrightView SPECT/CT 180度机架旋转采集的检查。
主要发现
- 迁移学习预测μ图与真实值的误差为5.13 ± 7.02%,未微调直接迁移为8.24 ± 5.01%,有限样本训练为6.45 ± 5.75%。
- 用预测μ图重建图像与真实值的误差:迁移学习为1.11 ± 1.57%,未微调直接迁移为1.72 ± 1.63%,有限样本训练为1.68 ± 1.21%。
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
It has been proved feasible to generate attenuation maps (μ-maps) from cardiac SPECT using deep learning. However, this assumed that the training and testing datasets were acquired using the same scanner, tracer, and protocol. We investigated a robust generation of CT-derived μ-maps from cardiac SPECT acquired by different scanners, tracers, and protocols from the training data. We first pre-trained a network using 120 studies injected with 99mTc-tetrofosmin acquired from a GE 850 SPECT/CT with 360-degree gantry rotation, which was then fine-tuned and tested using 80 studies injected with 99mTc-sestamibi acquired from a Philips BrightView SPECT/CT with 180-degree gantry rotation. The error between ground-truth and predicted μ-maps by transfer learning was 5.13 ± 7.02%, as compared to 8.24 ± 5.01% by direct transition without fine-tuning and 6.45 ± 5.75% by limited-sample training. The error between ground-truth and reconstructed images with predicted μ-maps by transfer learning was 1.11 ± 1.57%, as compared to 1.72 ± 1.63% by direct transition and 1.68 ± 1.21% by limited-sample training. It is feasible to apply a network pre-trained by a large amount of data from one scanner to data acquired by another scanner using different tracers and protocols, with proper transfer learning.
引用
- Chen X, Hendrik Pretorius P, Zhou B, et al. Cross-vender, cross-tracer, and cross-protocol deep transfer learning for attenuation map generation of cardiac SPECT. J Nucl Cardiol. 2022. PMID: 35474443. doi:10.1007/s12350-022-02978-7
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。