通过图神经网络跨数据集计算大脑测量值

Yixin Wang, Wei Peng, S. Tapert, Qingyu Zhao, K. Pohl
{"title":"通过图神经网络跨数据集计算大脑测量值","authors":"Yixin Wang, Wei Peng, S. Tapert, Qingyu Zhao, K. Pohl","doi":"10.48550/arXiv.2308.09907","DOIUrl":null,"url":null,"abstract":"Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not released by the Adolescent Brain Cognitive Development (ABCD) Study. One can address this issue by simply reapplying Freesurfer to the data set. However, this approach is generally computationally and labor intensive (e.g., requiring quality control). An alternative is to impute the missing measurements via a deep learning approach. However, the state-of-the-art is designed to estimate randomly missing values rather than entire measurements. We therefore propose to re-frame the imputation problem as a prediction task on another (public) data set that contains the missing measurements and shares some ROI measurements with the data sets of interest. A deep learning model is then trained to predict the missing measurements from the shared ones and afterwards is applied to the other data sets. Our proposed algorithm models the dependencies between ROI measurements via a graph neural network (GNN) and accounts for demographic differences in brain measurements (e.g. sex) by feeding the graph encoding into a parallel architecture. The architecture simultaneously optimizes a graph decoder to impute values and a classifier in predicting demographic factors. We test the approach, called Demographic Aware Graph-based Imputation (DAGI), on imputing those missing Freesurfer measurements of ABCD (N=3760) by training the predictor on those publicly released by the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA, N=540)...","PeriodicalId":344481,"journal":{"name":"PRIME@MICCAI","volume":"398 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Imputing Brain Measurements Across Data Sets via Graph Neural Networks\",\"authors\":\"Yixin Wang, Wei Peng, S. Tapert, Qingyu Zhao, K. Pohl\",\"doi\":\"10.48550/arXiv.2308.09907\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not released by the Adolescent Brain Cognitive Development (ABCD) Study. One can address this issue by simply reapplying Freesurfer to the data set. However, this approach is generally computationally and labor intensive (e.g., requiring quality control). An alternative is to impute the missing measurements via a deep learning approach. However, the state-of-the-art is designed to estimate randomly missing values rather than entire measurements. We therefore propose to re-frame the imputation problem as a prediction task on another (public) data set that contains the missing measurements and shares some ROI measurements with the data sets of interest. A deep learning model is then trained to predict the missing measurements from the shared ones and afterwards is applied to the other data sets. Our proposed algorithm models the dependencies between ROI measurements via a graph neural network (GNN) and accounts for demographic differences in brain measurements (e.g. sex) by feeding the graph encoding into a parallel architecture. The architecture simultaneously optimizes a graph decoder to impute values and a classifier in predicting demographic factors. We test the approach, called Demographic Aware Graph-based Imputation (DAGI), on imputing those missing Freesurfer measurements of ABCD (N=3760) by training the predictor on those publicly released by the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA, N=540)...\",\"PeriodicalId\":344481,\"journal\":{\"name\":\"PRIME@MICCAI\",\"volume\":\"398 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"PRIME@MICCAI\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2308.09907\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"PRIME@MICCAI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2308.09907","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

公开可用的结构核磁共振成像数据集可能不包含对训练机器学习模型很重要的大脑兴趣区域(roi)的具体测量。例如,Freesurfer计算的曲率分数并没有在青少年大脑认知发展(ABCD)研究中公布。我们可以通过简单地对数据集重新应用Freesurfer来解决这个问题。然而,这种方法通常是计算和劳动密集型的(例如,需要质量控制)。另一种方法是通过深度学习方法来计算缺失的测量值。然而,最先进的技术是用来估计随机缺失的值,而不是整个测量值。因此,我们建议将估算问题重新构建为另一个(公共)数据集上的预测任务,该数据集包含缺失的测量值,并与感兴趣的数据集共享一些ROI测量值。然后训练一个深度学习模型来预测共享数据中缺失的测量值,然后应用于其他数据集。我们提出的算法通过图神经网络(GNN)对ROI测量之间的依赖关系进行建模,并通过将图编码输入并行架构来解释大脑测量(例如性别)中的人口统计学差异。该体系结构同时优化了用于估算值的图形解码器和用于预测人口因素的分类器。我们测试了这种方法,称为基于人口统计意识图的Imputation (DAGI),通过对国家酒精和青少年神经发育协会(nanda, N=540)公开发布的预测器进行训练,来推算那些缺失的Freesurfer ABCD测量值(N=3760)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Imputing Brain Measurements Across Data Sets via Graph Neural Networks
Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not released by the Adolescent Brain Cognitive Development (ABCD) Study. One can address this issue by simply reapplying Freesurfer to the data set. However, this approach is generally computationally and labor intensive (e.g., requiring quality control). An alternative is to impute the missing measurements via a deep learning approach. However, the state-of-the-art is designed to estimate randomly missing values rather than entire measurements. We therefore propose to re-frame the imputation problem as a prediction task on another (public) data set that contains the missing measurements and shares some ROI measurements with the data sets of interest. A deep learning model is then trained to predict the missing measurements from the shared ones and afterwards is applied to the other data sets. Our proposed algorithm models the dependencies between ROI measurements via a graph neural network (GNN) and accounts for demographic differences in brain measurements (e.g. sex) by feeding the graph encoding into a parallel architecture. The architecture simultaneously optimizes a graph decoder to impute values and a classifier in predicting demographic factors. We test the approach, called Demographic Aware Graph-based Imputation (DAGI), on imputing those missing Freesurfer measurements of ABCD (N=3760) by training the predictor on those publicly released by the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA, N=540)...
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
自引率
0.00%
发文量
0
期刊最新文献
Video-Based Hand Pose Estimation for Remote Assessment of Bradykinesia in Parkinson's Disease Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia Imputing Brain Measurements Across Data Sets via Graph Neural Networks Self-supervised Landmark Learning with Deformation Reconstruction and Cross-subject Consistency Objectives Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1