多巴氨基PET对SPECT域的适应:一个循环GAN翻译方法
Leonor Lopes1,2, Fangyang Jiao3, Song Xue1,4
1Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 18, Bern, 3010, Switzerland.
European journal of nuclear medicine and molecular imaging
|November 18, 2024
概括
这项研究开发了一种深度学习方法,将[11C]CFT PET扫描转换为[123I]FP-CIT SPECT图像,帮助诊断帕金森病. 人工智能模型生成了视觉上类似的SPECT图像,保留了关键的诊断信息.
科学领域:
- 神经成像是一种神经成像.
- 人工智能的人工智能
- 医学诊断 医学诊断 医学诊断
背景情况:
- 多巴胺载体成像对于诊断帕金森病 (PD) 和非典型帕金森综合征 (APS) 至关重要.
- 在成像数据的可用性方面存在差异,亚洲流行的是[11C]CFT PET,欧洲流行的是[123I]FP-CIT SPECT.
- 有限的APS数据阻碍了多中心研究和AI开发.
研究的目的:
- 开发一种基于深度学习的方法,用于将[11C]CFT PET图像转换为[123I]FP-CIT SPECT图像.
- 通过克服APS诊断中的数据短缺,促进多中心研究.
- 推进人工智能 (AI) 在神经退行性疾病诊断中的应用.
主要方法:
- 在[11C]CFT PET和[123I]FP-CIT SPECT图像的大数据集上训练了一个CycleGAN模型.
- 该模型从真实[11C]CFT PET测试数据中生成合成[123I]FP-CIT SPECT图像.
- 量化指标 (弗雷切开始距离) 和视觉评估评估了合成图像的质量和诊断实用性.
主要成果:
- 合成的SPECT图像与真实的SPECT图像具有很高的相似性.
- 在合成SPECT上训练的分类模型在真实SPECT数据上实现了高灵敏度 (97.2%) 和特异性 (90.0%).
- 视觉评估显示,合成的SPECT图像与真实图像是不可区分的,保留了疾病特定的信息.
结论:
- 这个CycleGAN模型成功地将[11C]CFT PET转换为[123I]FP-CIT SPECT成像.
- 这种交叉模式的合成是可行的,可以提高AI分类准确性PD和APS诊断.
- 该方法支持多中心研究,并解决了诊断帕金森综合征的数据限制.
更多相关视频
07:41Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
Published on: June 5, 2017
9.9K
10:24Genetic Incorporation of Biosynthesized L-dihydroxyphenylalanine DOPA and Its Application to Protein Conjugation
Published on: August 24, 2018
7.9K
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
