Dopaminergic PET to SPECT domain adaptation: a cycle GAN translation approach

核医学 Spect成像 人工智能 单光子发射计算机断层摄影术 多巴胺转运体 医学 计算机科学 模式识别(心理学) 多巴胺能 多巴胺 内科学
作者
Leonor Lopes,Fangyang Jiao,Song Xue,Thomas Pyka,Korbinian Krieger,Jingjie Ge,Qian Xu,Rachid Fahmi,Bruce Spottiswoode,Ahmed A. Soliman,Ralph Buchert,Matthias Brendel,Jimin Hong,Yihui Guan,Claudio L. Bassetti,Axel Rominger,Chuantao Zuo,Kuangyu Shi,Ping Wu
出处
期刊:European Journal of Nuclear Medicine and Molecular Imaging [Springer Nature]
标识
DOI:10.1007/s00259-024-06961-x
摘要

Abstract Purpose Dopamine transporter imaging is routinely used in Parkinson’s disease (PD) and atypical parkinsonian syndromes (APS) diagnosis. While [ 11 C]CFT PET is prevalent in Asia with a large APS database, Europe relies on [ 123 I]FP-CIT SPECT with limited APS data. Our aim was to develop a deep learning-based method to convert [ 11 C]CFT PET images to [ 123 I]FP-CIT SPECT images, facilitating multicenter studies and overcoming data scarcity to promote Artificial Intelligence (AI) advancements. Methods A CycleGAN was trained on [ 11 C]CFT PET ( n = 602, 72%PD) and [ 123 I]FP-CIT SPECT ( n = 1152, 85%PD) images from PD and non-parkinsonian control (NC) subjects. The model generated synthetic SPECT images from a real PET test set ( n = 67, 75%PD). Synthetic images were quantitatively and visually evaluated. Results Fréchet Inception Distance indicated higher similarity between synthetic and real SPECT than between synthetic SPECT and real PET. A deep learning classification model trained on synthetic SPECT achieved sensitivity of 97.2% and specificity of 90.0% on real SPECT images. Striatal specific binding ratios of synthetic SPECT were not significantly different from real SPECT. The striatal left-right differences and putamen binding ratio were significantly different only in the PD cohort. Real PET and real SPECT had higher contrast-to-noise ratio compared to synthetic SPECT. Visual grading analysis scores showed no significant differences between real and synthetic SPECT, although reduced diagnostic performance on synthetic images was observed. Conclusion CycleGAN generated synthetic SPECT images visually indistinguishable from real ones and retained disease-specific information, demonstrating the feasibility of translating [ 11 C]CFT PET to [ 123 I]FP-CIT SPECT. This cross-modality synthesis could enhance further AI classification accuracy, supporting the diagnosis of PD and APS.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
李还好完成签到,获得积分10
刚刚
满意的柏柳完成签到,获得积分10
1秒前
2秒前
3秒前
3秒前
buno应助88采纳,获得10
3秒前
4秒前
三千世界完成签到,获得积分10
4秒前
4秒前
愉快的访旋完成签到,获得积分10
5秒前
Alpha完成签到,获得积分10
6秒前
大大发布了新的文献求助30
6秒前
翠翠发布了新的文献求助10
7秒前
半山发布了新的文献求助10
8秒前
8秒前
天天快乐应助CO2采纳,获得10
8秒前
隐形曼青应助junzilan采纳,获得10
9秒前
Dksido发布了新的文献求助10
9秒前
10秒前
思源应助卓哥采纳,获得10
10秒前
mysci完成签到,获得积分10
13秒前
14秒前
Quzhengkai发布了新的文献求助10
15秒前
15秒前
16秒前
落寞晓灵完成签到,获得积分10
16秒前
ORAzzz应助翠翠采纳,获得20
17秒前
zoe完成签到,获得积分10
17秒前
习习应助学术小白采纳,获得10
17秒前
18秒前
19秒前
tianny关注了科研通微信公众号
20秒前
20秒前
CO2发布了新的文献求助10
20秒前
桐桐应助zhangscience采纳,获得10
21秒前
求助发布了新的文献求助10
22秒前
buno应助zoe采纳,获得10
23秒前
junzilan发布了新的文献求助10
23秒前
23秒前
细品岁月完成签到 ,获得积分10
23秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Social media impact on athlete mental health: #RealityCheck 1020
Ensartinib (Ensacove) for Non-Small Cell Lung Cancer 1000
Unseen Mendieta: The Unpublished Works of Ana Mendieta 1000
Bacterial collagenases and their clinical applications 800
El viaje de una vida: Memorias de María Lecea 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3527961
求助须知:如何正确求助?哪些是违规求助? 3108159
关于积分的说明 9287825
捐赠科研通 2805882
什么是DOI,文献DOI怎么找? 1540070
邀请新用户注册赠送积分活动 716926
科研通“疑难数据库(出版商)”最低求助积分说明 709808