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

被引：1

作者：

Petrov, Dmitry ^{[1
,2
]}

Gutman, Boris A. ^{[1
]}

Yu, Shih-Hua ^{[1
]}

Alpert, Kathryn ^{[3
]}

Zavaliangos-Petropulu, Artemis ^{[1
]}

Isaev, Dmitry ^{[1
]}

Turner, Jessica A. ^{[4
]}

van Erp, Theo G. M. ^{[5
]}

Wang, Lei ^{[3
]}

Schmaal, Lianne ^{[6
,7
]}

Veltman, Dick ^{[7
]}

Thompson, Paul M. ^{[1
]}

机构：

[1] Univ Southern Calif, Imaging Genet Ctr, Stevens Inst Neuroimaging & Informat, Los Angeles, CA 90089 USA

[2] Inst Informat Transmiss Problems, Moscow, Russia

[3] Northwestern Univ, Dept Psychiat, Chicago, IL 60611 USA

[4] Mind Res Network, Albuquerque, NM USA

[5] Univ Calif Irvine, Irvine, CA USA

[6] Orygen, Natl Ctr Excellence Youth Mental Hlth, Melbourne, Vic, Australia

[7] Vrije Univ Amsterdam Med Ctr, Dept Psychiat, Amsterdam, Netherlands

来源：

MACHINE LEARNING IN MEDICAL IMAGING (MLMI 2017) | 2017年 / 10541卷

基金：

俄罗斯科学基金会;

关键词：

Shape analysis; Machine learning; Quality control;

D O I：

10.1007/978-3-319-67389-9_43

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

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.

引用

页码：371 / 378

页数：8

共 12 条

[1] XGBoost: A Scalable Tree Boosting System [J].

Chen, Tianqi ;

Guestrin, Carlos .

KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794

[2]

Esteban O., 2017, BIORXIV

[3] FreeSurfer [J].

Fischl, Bruce .

NEUROIMAGE, 2012, 62 (02) :774-781

[4] Greedy function approximation: A gradient boosting machine [J].

Friedman, JH .

ANNALS OF STATISTICS, 2001, 29 (05) :1189-1232

[5]

Gutman Boris A., 2013, Multimodal Brain Image Analysis. Third International Workshop, MBIA 2013. Held in Conjunction with MICCAI 2013. Proceedings: LNCS 8159, P246, DOI 10.1007/978-3-319-02126-3_24

[6] Harmonized Large-Scale Anatomical Shape Analysis: Mapping Subcortical Differences across the Enigma Bipolar, Schizophrenia, and Major Depression Working Groups [J].

Gutman, Boris ;

Ching, Christopher ;

Andreassen, Ole ;

Schmaal, Lianne ;

Veltman, Dick ;

Van Erp, Theo ;

Turner, Jessica ;

Thompson, Paul M. .

BIOLOGICAL PSYCHIATRY, 2017, 81 (10) :S308-S308

[7]

Gutman BA, 2015, I S BIOMED IMAGING, P1402

[8]

Pedregosa F, 2011, J MACH LEARN RES, V12, P2825

[9] Heritability of the shape of subcortical brain structures in the general population [J].

Roshchupkin, Gennady V. ;

Gutman, Boris A. ;

Vernooij, Meike W. ;

Jahanshad, Neda ;

Martin, Nicholas G. ;

Hofman, Albert ;

McMahon, Katie L. ;

van der Lee, Sven J. ;

van Duijn, Cornelia M. ;

de Zubicaray, Greig I. ;

Uitterlinden, Andre G. ;

Wright, Margaret J. ;

Niessen, Wiro J. ;

Thompson, Paul M. ;

Ikram, M. Arfan ;

Adams, Hieab H. H. .

NATURE COMMUNICATIONS, 2016, 7

[10] Cortical abnormalities in adults and adolescents with major depression based on brain scans from 20 cohorts worldwide in the ENIGMA Major Depressive Disorder Working Group [J].

Schmaal, L. ;

Hibar, D. P. ;

Saemann, P. G. ;

Hall, G. B. ;

Baune, B. T. ;

Jahanshad, N. ;

Cheung, J. W. ;

van Erp, T. G. M. ;

Bos, D. ;

Ikram, M. A. ;

Vernooij, M. W. ;

Niessen, W. J. ;

Tiemeier, H. ;

Hofman, A. ;

Wittfeld, K. ;

Grabe, H. J. ;

Janowitz, D. ;

Buelow, R. ;

Selonke, M. ;

Voelzke, H. ;

Grotegerd, D. ;

Dannlowski, U. ;

Arolt, V. ;

Opel, N. ;

Heindel, W. ;

Kugel, H. ;

Hoehn, D. ;

Czisch, M. ;

Couvy-Duchesne, B. ;

Renteria, M. E. ;

Strike, L. T. ;

Wright, M. J. ;

Mills, N. T. ;

de Zubicaray, G. I. ;

McMahon, K. L. ;

Medland, S. E. ;

Martin, N. G. ;

Gillespie, N. A. ;

Goya-Maldonado, R. ;

Gruber, O. ;

Kraemer, B. ;

Hatton, S. N. ;

Lagopoulos, J. ;

Hickie, I. B. ;

Frodl, T. ;

Carballedo, A. ;

Frey, E. M. ;

van Velzen, L. S. ;

Penninx, B. W. J. H. ;

van Tol, M-J .

MOLECULAR PSYCHIATRY, 2017, 22 (06) :900-909

← 1 2 →