神经成像三维形状模型大规模质量控制的机器学习

Dmitry Petrov, Boris A Gutman, Shih-Hua Julie Yu, Theo G M van Erp, Jessica A Turner, Lianne Schmaal, Dick Veltman, Lei Wang, Kathryn Alpert, Dmitry Isaev, Artemis Zavaliangos-Petropulu, Christopher R K Ching, Vince Calhoun, David Glahn, Theodore D Satterthwaite, Ole Andreas Andreasen, Stefan Borgwardt, Fleur Howells, Nynke Groenewold, Aristotle Voineskos, Joaquim Radua, Steven G Potkin, Benedicto Crespo-Facorro, Diana Tordesillas-Gutiérrez, Li Shen, Irina Lebedeva, Gianfranco Spalletta, Gary Donohoe, Peter Kochunov, Pedro G P Rosa, Anthony James, Udo Dannlowski, Bernhard T Baune, André Aleman, Ian H Gotlib, Henrik Walter, Martin Walter, Jair C Soares, Stefan Ehrlich, Ruben C Gur, N Trung Doan, Ingrid Agartz, Lars T Westlye, Fabienne Harrisberger, Anita Riecher-Rössler, Anne Uhlmann, Dan J Stein, Erin W Dickie, Edith Pomarol-Clotet, Paola Fuentes-Claramonte, Erick Jorge Canales-Rodríguez, Raymond Salvador, Alexander J Huang, Roberto Roiz-Santiañez, Shan Cong, Alexander Tomyshev, Fabrizio Piras, Daniela Vecchio, Nerisa Banaj, Valentina Ciullo, Elliot Hong, Geraldo Busatto, Marcus V Zanetti, Mauricio H Serpa, Simon Cervenka, Sinead Kelly, Dominik Grotegerd, Matthew D Sacchet, Ilya M Veer, Meng Li, Mon-Ju Wu, Benson Irungu, Esther Walton, Paul M Thompson
{"title":"神经成像三维形状模型大规模质量控制的机器学习","authors":"Dmitry Petrov, Boris A Gutman, Shih-Hua Julie Yu, Theo G M van Erp, Jessica A Turner, Lianne Schmaal, Dick Veltman, Lei Wang, Kathryn Alpert, Dmitry Isaev, Artemis Zavaliangos-Petropulu, Christopher R K Ching, Vince Calhoun, David Glahn, Theodore D Satterthwaite, Ole Andreas Andreasen, Stefan Borgwardt, Fleur Howells, Nynke Groenewold, Aristotle Voineskos, Joaquim Radua, Steven G Potkin, Benedicto Crespo-Facorro, Diana Tordesillas-Gutiérrez, Li Shen, Irina Lebedeva, Gianfranco Spalletta, Gary Donohoe, Peter Kochunov, Pedro G P Rosa, Anthony James, Udo Dannlowski, Bernhard T Baune, André Aleman, Ian H Gotlib, Henrik Walter, Martin Walter, Jair C Soares, Stefan Ehrlich, Ruben C Gur, N Trung Doan, Ingrid Agartz, Lars T Westlye, Fabienne Harrisberger, Anita Riecher-Rössler, Anne Uhlmann, Dan J Stein, Erin W Dickie, Edith Pomarol-Clotet, Paola Fuentes-Claramonte, Erick Jorge Canales-Rodríguez, Raymond Salvador, Alexander J Huang, Roberto Roiz-Santiañez, Shan Cong, Alexander Tomyshev, Fabrizio Piras, Daniela Vecchio, Nerisa Banaj, Valentina Ciullo, Elliot Hong, Geraldo Busatto, Marcus V Zanetti, Mauricio H Serpa, Simon Cervenka, Sinead Kelly, Dominik Grotegerd, Matthew D Sacchet, Ilya M Veer, Meng Li, Mon-Ju Wu, Benson Irungu, Esther Walton, Paul M Thompson","doi":"10.1007/978-3-319-67389-9_43","DOIUrl":null,"url":null,"abstract":"<p><p>As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.</p>","PeriodicalId":74092,"journal":{"name":"Machine learning in medical imaging. MLMI (Workshop)","volume":"10541 ","pages":"371-378"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6049825/pdf/nihms980690.pdf","citationCount":"0","resultStr":"{\"title\":\"Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging.\",\"authors\":\"Dmitry Petrov, Boris A Gutman, Shih-Hua Julie Yu, Theo G M van Erp, Jessica A Turner, Lianne Schmaal, Dick Veltman, Lei Wang, Kathryn Alpert, Dmitry Isaev, Artemis Zavaliangos-Petropulu, Christopher R K Ching, Vince Calhoun, David Glahn, Theodore D Satterthwaite, Ole Andreas Andreasen, Stefan Borgwardt, Fleur Howells, Nynke Groenewold, Aristotle Voineskos, Joaquim Radua, Steven G Potkin, Benedicto Crespo-Facorro, Diana Tordesillas-Gutiérrez, Li Shen, Irina Lebedeva, Gianfranco Spalletta, Gary Donohoe, Peter Kochunov, Pedro G P Rosa, Anthony James, Udo Dannlowski, Bernhard T Baune, André Aleman, Ian H Gotlib, Henrik Walter, Martin Walter, Jair C Soares, Stefan Ehrlich, Ruben C Gur, N Trung Doan, Ingrid Agartz, Lars T Westlye, Fabienne Harrisberger, Anita Riecher-Rössler, Anne Uhlmann, Dan J Stein, Erin W Dickie, Edith Pomarol-Clotet, Paola Fuentes-Claramonte, Erick Jorge Canales-Rodríguez, Raymond Salvador, Alexander J Huang, Roberto Roiz-Santiañez, Shan Cong, Alexander Tomyshev, Fabrizio Piras, Daniela Vecchio, Nerisa Banaj, Valentina Ciullo, Elliot Hong, Geraldo Busatto, Marcus V Zanetti, Mauricio H Serpa, Simon Cervenka, Sinead Kelly, Dominik Grotegerd, Matthew D Sacchet, Ilya M Veer, Meng Li, Mon-Ju Wu, Benson Irungu, Esther Walton, Paul M Thompson\",\"doi\":\"10.1007/978-3-319-67389-9_43\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.</p>\",\"PeriodicalId\":74092,\"journal\":{\"name\":\"Machine learning in medical imaging. MLMI (Workshop)\",\"volume\":\"10541 \",\"pages\":\"371-378\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6049825/pdf/nihms980690.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machine learning in medical imaging. MLMI (Workshop)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/978-3-319-67389-9_43\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2017/9/7 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine learning in medical imaging. MLMI (Workshop)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-319-67389-9_43","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2017/9/7 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

随着复杂神经影像表型的大型研究越来越常见,对核磁共振成像数据进行人工质量评估仍是最后的主要瓶颈之一。迄今为止,很少有人尝试用机器学习来解决这个问题。在这项工作中,我们优化了代表大脑深层结构形状的网格的质量预测模型。我们使用在 19 个队列和超过 7500 名人类评定对象中同源计算的标准顶点和全局形状特征,训练核化支持向量机和梯度提升决策树分类器来检测质量不合格的网格。我们的模型在不同的数据集和疾病中具有通用性,可减少 30% 到 70% 的人工工作量,对于规模相当的数据集来说,相当于减少了数百个人工评分时间,召回率接近评分者之间的可靠性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging.

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging.

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging.

As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.

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
×
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