Browsing by Author "Busatto, Geraldo"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Biomarkers for dementia in Latin American countries: Gaps and opportunities
    (Wiley, 2023) Parra, Mario A.; Orellana, Paulina; Leon, Tomas; Victoria, Cabello G.; Henriquez, Fernando; Gomez, Rodrigo; Avalos, Constanza; Damian, Andres; Slachevsky, Andrea; Ibañez, Agustin; Zetterberg, Henrik; Tijms, Betty M.; Yokoyama, Jennifer S.; Piña-Escudero, Stefanie D.; Cochran, J. Nicholas; Matallana, Diana L.; Acosta, Daisy; Allegri, Ricardo; Arias-Suárez, Bianca P.; Barra, Bernardo; Behrens, Maria Isabel; Brucki, Sonia M. D.; Busatto, Geraldo; Caramelli, Paulo; Castro-Suarez, Sheila; Contreras, Valeria; Custodio, Nilton; Dansilio, Sergio; De la Cruz-Puebla, Myriam; de Souza, Leonardo Cruz; Diaz, Monica M.; Duque, Lissette; Farías, Gonzalo A.; Ferreira, Sergio T.; Guimet, Nahuel Magrath; Kmaid, Ana; Lira, David; Lopera, Francisco; Mar Meza, Beatriz; Miotto, Eliane C.; Nitrini, Ricardo; Nuñez, Alberto; O'Neill, Santiago; Ochoa, John; Pintado-Caipa, Maritza; Resende, Elisa de Paula França; Risacher, Shannon; Rojas, Luz Angela; Sabaj, Valentina; Schilling, Lucas; Sellek, Allis F.; Sosa, Ana; Takada, Leonel T.; Teixeira, Antonio L.; Unaucho-Pilalumbo, Martha; Duran-Aniotz, Claudia; Radiology and Imaging Sciences, School of Medicine
    Limited knowledge on dementia biomarkers in Latin American and Caribbean (LAC) countries remains a serious barrier. Here, we reported a survey to explore the ongoing work, needs, interests, potential barriers, and opportunities for future studies related to biomarkers. The results show that neuroimaging is the most used biomarker (73%), followed by genetic studies (40%), peripheral fluids biomarkers (31%), and cerebrospinal fluid biomarkers (29%). Regarding barriers in LAC, lack of funding appears to undermine the implementation of biomarkers in clinical or research settings, followed by insufficient infrastructure and training. The survey revealed that despite the above barriers, the region holds a great potential to advance dementia biomarkers research. Considering the unique contributions that LAC could make to this growing field, we highlight the urgent need to expand biomarker research. These insights allowed us to propose an action plan that addresses the recommendations for a biomarker framework recently proposed by regional experts.
  • Thumbnail Image
    Item
    Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging
    (Springer Nature, 2017-09) Petrov, Dmitry; Gutman, Boris A.; Yu, Shih-Hua (Julie); 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.; Andreasen, Ole Andreas; Borgwardt, Stefan; Howells, Fleur; Groenewold, Nynke; Voineskos, Aristotle; Radua, Joaquim; Potkin, Steven G.; Crespo-Facorro, Benedicto; Tordesillas-Gutirrez, Diana; Shen, Li; Lebedeva, Irina; Spalletta, Gianfranco; Donohoe, Gary; Kochunov, Peter; Rosa, Pedro G.P.; James, Anthony; Dannlowski, Udo; Baune, Berhard 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; Richer-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, Illya M.; Li, Meng; Wu, Mon-Ju; Irungu, Benson; Walton, Esther; Thompson, Paul M.; Medicine, School of Medicine
    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.