基于深度学习的帕金森病多巴胺转运体 SPECT 跨模态纹状体分割技术

IF 4.6 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Haiyan Wang;Han Jiang;Gefei Chen;Yu Du;Zhonglin Lu;Zhanli Hu;Greta S. P. Mok
{"title":"基于深度学习的帕金森病多巴胺转运体 SPECT 跨模态纹状体分割技术","authors":"Haiyan Wang;Han Jiang;Gefei Chen;Yu Du;Zhonglin Lu;Zhanli Hu;Greta S. P. Mok","doi":"10.1109/TRPMS.2024.3398360","DOIUrl":null,"url":null,"abstract":"Striatum segmentation on dopamine transporter (DaT) SPECT is necessary to quantify striatal uptake for Parkinson’s disease (PD), but is challenging due to the inferior resolution. This work proposes a cross-modality automatic striatum segmentation, estimating MR-derived striatal contours from clinical SPECT images using the deep learning (DL) methods. \n<sup>123</sup>\nI-Ioflupane DaT SPECT and T1-weighted MR images from 200 subjects with 152 PD and 48 healthy controls are analyzed from the Parkinson’s progression markers initiative database. SPECT and MR images are registered, and four striatal compartment contours are manually segmented from MR images as the label. DL methods including nnU-Net, U-Net, generative adversarial networks, and SPECT thresholding-based method are implemented for comparison. SPECT and MR label pairs are split into train, validation, and test groups (136:24:40). Dice, Hausdorff distance (HD) 95%, and relative volume difference (RVD), striatal binding ratio (SBR) and asymmetry index (ASI) are analyzed. Results show that nnU-Net achieves better Dice (~0.7), HD 95% (~1.8), and RVD (~0.1) as compared to other methods for all striatal compartments and whole striatum. For clinical PD evaluation, nnU-Net also yields strong SBR consistency (mean difference, −0.012) and ASI correlation (Pearson correlation coefficient, 0.81). The proposed DL-based cross-modality striatum segmentation method is feasible for clinical DaT SPECT in PD.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10525203","citationCount":"0","resultStr":"{\"title\":\"Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease\",\"authors\":\"Haiyan Wang;Han Jiang;Gefei Chen;Yu Du;Zhonglin Lu;Zhanli Hu;Greta S. P. Mok\",\"doi\":\"10.1109/TRPMS.2024.3398360\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Striatum segmentation on dopamine transporter (DaT) SPECT is necessary to quantify striatal uptake for Parkinson’s disease (PD), but is challenging due to the inferior resolution. This work proposes a cross-modality automatic striatum segmentation, estimating MR-derived striatal contours from clinical SPECT images using the deep learning (DL) methods. \\n<sup>123</sup>\\nI-Ioflupane DaT SPECT and T1-weighted MR images from 200 subjects with 152 PD and 48 healthy controls are analyzed from the Parkinson’s progression markers initiative database. SPECT and MR images are registered, and four striatal compartment contours are manually segmented from MR images as the label. DL methods including nnU-Net, U-Net, generative adversarial networks, and SPECT thresholding-based method are implemented for comparison. SPECT and MR label pairs are split into train, validation, and test groups (136:24:40). Dice, Hausdorff distance (HD) 95%, and relative volume difference (RVD), striatal binding ratio (SBR) and asymmetry index (ASI) are analyzed. Results show that nnU-Net achieves better Dice (~0.7), HD 95% (~1.8), and RVD (~0.1) as compared to other methods for all striatal compartments and whole striatum. For clinical PD evaluation, nnU-Net also yields strong SBR consistency (mean difference, −0.012) and ASI correlation (Pearson correlation coefficient, 0.81). The proposed DL-based cross-modality striatum segmentation method is feasible for clinical DaT SPECT in PD.\",\"PeriodicalId\":46807,\"journal\":{\"name\":\"IEEE Transactions on Radiation and Plasma Medical Sciences\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-03-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10525203\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Radiation and Plasma Medical Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10525203/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Radiation and Plasma Medical Sciences","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10525203/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

多巴胺转运体(DaT)SPECT 的纹状体分割对于量化帕金森病(PD)的纹状体摄取量非常必要,但由于分辨率较低,因此具有挑战性。这项研究提出了一种跨模态纹状体自动分割方法,利用深度学习(DL)方法从临床 SPECT 图像中估计 MR 导出的纹状体轮廓。该研究分析了帕金森病进展标志物倡议数据库中的 123I-Ioflupane DaT SPECT 和 T1 加权 MR 图像,这些图像来自 200 名患有帕金森病的 152 名受试者和 48 名健康对照者。对 SPECT 和 MR 图像进行注册,并从 MR 图像中手动分割出四个纹状体区段轮廓作为标签。比较采用的 DL 方法包括 nnU-Net、U-Net、生成式对抗网络和基于 SPECT 阈值的方法。SPECT 和 MR 标签对被分成训练组、验证组和测试组 (136:24:40)。对骰子、豪斯多夫距离(HD)95%、相对体积差(RVD)、纹状体结合率(SBR)和不对称指数(ASI)进行分析。结果表明,与其他方法相比,nnU-Net 在所有纹状体区和整个纹状体的 Dice(约 0.7)、HD 95%(约 1.8)和 RVD(约 0.1)方面都有更好的表现。在临床帕金森病评估中,nnU-Net 还具有很强的 SBR 一致性(平均差为 -0.012)和 ASI 相关性(皮尔逊相关系数为 0.81)。所提出的基于DL的跨模态纹状体分割方法在临床DaT SPECT治疗帕金森病中是可行的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease
Striatum segmentation on dopamine transporter (DaT) SPECT is necessary to quantify striatal uptake for Parkinson’s disease (PD), but is challenging due to the inferior resolution. This work proposes a cross-modality automatic striatum segmentation, estimating MR-derived striatal contours from clinical SPECT images using the deep learning (DL) methods. 123 I-Ioflupane DaT SPECT and T1-weighted MR images from 200 subjects with 152 PD and 48 healthy controls are analyzed from the Parkinson’s progression markers initiative database. SPECT and MR images are registered, and four striatal compartment contours are manually segmented from MR images as the label. DL methods including nnU-Net, U-Net, generative adversarial networks, and SPECT thresholding-based method are implemented for comparison. SPECT and MR label pairs are split into train, validation, and test groups (136:24:40). Dice, Hausdorff distance (HD) 95%, and relative volume difference (RVD), striatal binding ratio (SBR) and asymmetry index (ASI) are analyzed. Results show that nnU-Net achieves better Dice (~0.7), HD 95% (~1.8), and RVD (~0.1) as compared to other methods for all striatal compartments and whole striatum. For clinical PD evaluation, nnU-Net also yields strong SBR consistency (mean difference, −0.012) and ASI correlation (Pearson correlation coefficient, 0.81). The proposed DL-based cross-modality striatum segmentation method is feasible for clinical DaT SPECT in PD.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Radiation and Plasma Medical Sciences
IEEE Transactions on Radiation and Plasma Medical Sciences RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
8.00
自引率
18.20%
发文量
109
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信