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

ENIGMA [Unknown], Dmitry Petrov, Boris A Gutman, Shih-Hua Julie Yu, Theo G M van Erp, Lianne Schmaal, Dick Veltman, 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 RaduaSteven 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, Esther Walton

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.
Original languageEnglish
Title of host publicationMachine Learning in Medical Imaging. MLMI 2017
EditorsQ. Wang, Y. Shi, H. I. Suk, K. Suzuki
Place of PublicationCham, Switzerland
PublisherSpringer
Pages371-378
Number of pages8
ISBN (Electronic)9783319673899
ISBN (Print)9783319673882
DOIs
Publication statusPublished - Sep 2017
Event8th International Workshop on Machine Learning in Medical Imaging (MLMI), 2017 - Quebec City, Canada
Duration: 10 Sep 201710 Sep 2017

Publication series

NameLecture Notes in Computer Science
Volume10541

Conference

Conference8th International Workshop on Machine Learning in Medical Imaging (MLMI), 2017
CountryCanada
CityQuebec City
Period10/09/1710/09/17

Cite this

[Unknown], ENIGMA., Petrov, D., Gutman, B. A., Yu, S-H. J., van Erp, T. G. M., Schmaal, L., Veltman, D., Alpert, K., Isaev, D., Zavaliangos-Petropulu, A., Ching, C. R. K., Calhoun, V., Glahn, D., Satterthwaite, T. D., Andreasen, O. A., Borgwardt, S., Howells, F., Groenewold, N., Voineskos, A., ... Walton, E. (2017). Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging. In Q. Wang, Y. Shi, H. I. Suk, & K. Suzuki (Eds.), Machine Learning in Medical Imaging. MLMI 2017 (pp. 371-378). (Lecture Notes in Computer Science; Vol. 10541). Springer. https://doi.org/10.1007/978-3-319-67389-9_43