Year: 2018
Type: preprint
Abstract: We present several deep learning models for assessing the morphometric fidelity of deep grey matter region models extracted from brain MRI. We test three different convolutional neural net architectures (VGGNet, ResNet and Inception) over 2D maps of geometric features. Further, we present a novel geometry feature augmentation technique based on a parametric spherical mapping. Finally, we present an approach for model decision visualization, allowing human raters to see the areas of subcortical shapes most likely to be deemed of failing quality by the machine. Our training data is comprised of 5200 subjects from the ENIGMA Schizophrenia MRI cohorts, and our test dataset contains 1500 subjects from the ENIGMA Major Depressive Disorder cohorts. Our final models reduce human rater time by 46-70%. ResNet outperforms VGGNet and Inception for all of our predictive tasks.
Source: arXiv (Cornell University)
Authors: Petrov, Dmitry, Kuznetsov, Boris A. Gutman Egor, van Erp, Theo G. M., Turner, Jessica A., Schmaal, Lianne, Veltman, Dick, Wang, Lei, Alpert, Kathryn, Isaev, Dmitry, Zavaliangos-Petropulu, Artemis, Ching, Christopher R. K., Calhoun, Vince, Glahn, David, Satterthwaite, Theodore D., Andreassen, Ole Andreas, Borgwardt, Stefan, Howells, Fleur, Groenewold, Nynke, Voineskos, Aristotle, Radua, Joaquim, Potkin, Steven G., Crespo-Facorro, Benedicto, Tordesillas-Gutierrez, Diana, Shen, Li, Lebedeva, Irina, Spalletta, Gianfranco, Donohoe, Gary, Kochunov, Peter, Rosa, Pedro G. P., James, Anthony, Dannlowski, Udo, Baune, Bernhard T., Aleman, Andre, Gotlib, Ian H., Walter, Henrik, Walter, Martin, Soares, Jair C., Ehrlich, Stefan, Gur, Ruben C., Doan, N. Trung, Agartz, Ingrid, Westlye, Lars T., Harrisberger, Fabienne, Riecher-Rossler, Anita, Uhlmann, Anne, Stein, Dan J., Dickie, Erin W., Pomarol-Clotet, Edith, Fuentes-Claramonte, Paola, Canales-Rodriguez, Erick Jorge, Salvador, Raymond, Huang, Alexander J., Roiz-Santianez, Roberto, Cong, Shan, Tomyshev, Alexander, Piras, Fabrizio, Vecchio, Daniela, Banaj, Nerisa, Ciullo, Valentina, Hong, Elliot, Busatto, Geraldo, Zanetti, Marcus V., Serpa, Mauricio H., Cervenka, Simon, Kelly, Sinead, Grotegerd, Dominik, Sacchet, Matthew D., Veer, Ilya M., Li, Meng, Wu, Mon-Ju, Irungu, Benson, Walton, Esther, Thompson, Paul M.
Institutions: University of Southern California, Institute for Information Transmission Problems, University of California, Irvine, Georgia State University, Amsterdam UMC Location Vrije Universiteit Amsterdam, Northwestern University, University of Oslo, Yale University, University of Pennsylvania, Oslo University Hospital, University of Basel, University of Cape Town, Marqués de Valdecilla University Hospital, Instituto de Investigación Marqués de Valdecilla, Indiana University Indianapolis, Indiana University School of Medicine, Mental Health Research Center of Russian Academy of Medical Sciences, Fondazione Santa Lucia, Ollscoil na Gaillimhe – University of Galway, University of Maryland, Baltimore, Universidade de São Paulo, University of Oxford, University of Münster, The University of Adelaide, Stanford University, Charité - Universitätsmedizin Berlin, Leibniz Institute for Neurobiology, The University of Texas Health Science Center at Houston, Centre for Addiction and Mental Health, Centro de Investigación Biomédica en Red de Salud Mental, Fidmag Sisters Hospitallers, Humboldt-Universität zu Berlin, Karolinska Institutet, Beth Israel Deaconess Medical Center, Harvard University, University Medical Center Groningen, University of Groningen, Universidad de Cantabria
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2949522483