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

Journal: Machine learning in medical imaging. MLMI (Workshop)

Volume: 10541

Issue: 

Year of Publication: 

Affiliated Institutions:  Imaging Genetics Center, Stevens Institute for Neuroimaging and Informatics, University of Southern California, Marina Del Rey, CA, USA. Department of Psychiatry and Human Behavior, University of California Irvine, Irvine, CA, USA. Psychology Department & Neuroscience Institute, Georgia State University, Atlanta GA, USA. Orygen, The National Centre of Excellence in Youth Mental Health, Melbourne, Australia. Department of Psychiatry, VU University Medical Center, Amsterdam, The Netherlands. Department of Psychiatry, Northwestern University, Chicago, IL, USA. The Mind Research Network, Albuquerque, NM, USA. Yale University School of Medicine, New Haven, CT, USA. Department of Psychiatry, University of Pennsylvania School of Medicine, Philadelphia, PA, USA. CoE NORMENT, KG Jebsen Centre for Psychosis Research, Division of Mental Health and Addiction, Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway. Department of Psychiatry, University of Basel, Basel, Switzerland. MRC Unit on Risk & Resilience to Mental Disorders, Department of Psychiatry and Mental Health, University of Cape Town, Cape Town, South Africa. Centre for Addiction and Mental Health, Toronto, Canada. FIDMAG Germanes Hospitalaries Research Foundation, Barcelona, Spain. University Hospital Marqués de Valdecilla, IDIVAL, Department of Psychiatry, School of Medicine, University of Cantabria, Santander, Spain. Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, USA. Mental Health Research Center, Moscow, Russia. Laboratory of Neuropsychiatry, Santa Lucia Foundation IRCCS, Rome, Italy. School of Psychology, NUI Galway, Galway, Ireland. Maryland Psychiatric Research Center, University of Maryland School of Medicine, Baltimore. Department of Psychiatry, Faculty of Medicine, University of São Paulo, São Paulo, Brazil. University of Oxford, Oxford, United Kingdom. Department of Psychiatry and Psychotherapy, University of Münster, Germany. Discipline of Psychiatry, Adelaide Medical School, The University of Adelaide. Interdisciplinary Center Psychopathology and Emotion regulation (ICPE), Neuroimaging Center (BCN-NIC), University Medical Center Groningen, University of Groningen, Groningen, The Netherlands. Department of Psychology, Stanford University, Stanford, CA, USA. Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Psychiatry and Psychotherapy, CCM, Berlin, German. Clinical Affective Neuroimaging Laboratory, Leibniz Institute for Neurobiology, Magdeburg, Germany. University of Texas Health Science Center at Houston, Houston, TX, USA. Division of Psychological and Social Medicine and Developmental Neurosciences, Faculty of Medicine, TU Dresden, Germany. Centre for Psychiatry Research, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden. Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.

Abstract summary 

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.

Authors & Co-authors:  Petrov Dmitry D Gutman Boris A BA Yu Shih-Hua Julie SJ van Erp Theo G M TGM Turner Jessica A JA Schmaal Lianne L Veltman Dick D Wang Lei L Alpert Kathryn K Isaev Dmitry D Zavaliangos-Petropulu Artemis A Ching Christopher R K CRK Calhoun Vince V Glahn David D Satterthwaite Theodore D TD Andreasen Ole Andreas OA Borgwardt Stefan S Howells Fleur F Groenewold Nynke N Voineskos Aristotle A Radua Joaquim J Potkin Steven G SG Crespo-Facorro Benedicto B Tordesillas-Gutiérrez Diana D Shen Li L Lebedeva Irina I Spalletta Gianfranco G Donohoe Gary G Kochunov Peter P Rosa Pedro G P PGP James Anthony A Dannlowski Udo U Baune Bernhard T BT Aleman André A Gotlib Ian H IH Walter Henrik H Walter Martin M Soares Jair C JC Ehrlich Stefan S Gur Ruben C RC Doan N Trung NT Agartz Ingrid I Westlye Lars T LT Harrisberger Fabienne F Riecher-Rössler Anita A Uhlmann Anne A Stein Dan J DJ Dickie Erin W EW Pomarol-Clotet Edith E Fuentes-Claramonte Paola P Canales-Rodríguez Erick Jorge EJ Salvador Raymond R Huang Alexander J AJ Roiz-Santiañez Roberto R Cong Shan S Tomyshev Alexander A Piras Fabrizio F Vecchio Daniela D Banaj Nerisa N Ciullo Valentina V Hong Elliot E Busatto Geraldo G Zanetti Marcus V MV Serpa Mauricio H MH Cervenka Simon S Kelly Sinead S Grotegerd Dominik D Sacchet Matthew D MD Veer Ilya M IM Li Meng M Wu Mon-Ju MJ Irungu Benson B Walton Esther E Thompson Paul M PM

Study Outcome 

Source Link: Visit source

Statistics
Citations :  Thompson PM, Andreassen OA, Arias-Vasquez A, Bearden CE, Boedhoe PS, Brouwer RM, Buckner RL, Buitelaar JK, Bulaeva KB, Cannon DM. ENIGMA and the individual: Predicting factors that affect the brain in 35 countries worldwide. Neuroimage. 2015;145(Pt B):389–408.
Authors :  74
Identifiers
Doi : 10.1007/978-3-319-67389-9_43
SSN : 
Study Population
Male,Female
Mesh Terms
Other Terms
machine learning;quality control;shape analysis
Study Design
Case Control Trial,Cross Sectional Study
Study Approach
Country of Study
Publication Country
Germany