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 or section in a book/report/conference proceedingChapter in a published conference proceeding

3 Citations (SciVal)


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
Number of pages8
ISBN (Electronic)9783319673899
ISBN (Print)9783319673882
Publication statusPublished - Sept 2017
Event8th International Workshop on Machine Learning in Medical Imaging (MLMI), 2017 - Quebec City, Canada
Duration: 10 Sept 201710 Sept 2017

Publication series

NameLecture Notes in Computer Science


Conference8th International Workshop on Machine Learning in Medical Imaging (MLMI), 2017
CityQuebec City


Dive into the research topics of 'Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging'. Together they form a unique fingerprint.

Cite this