@article{20662,
  abstract     = {Task-based functional magnetic resonance imaging (fMRI) reveals individual differences in neural correlates of cognition but faces scalability challenges due to cognitive demands, protocol variability, and limited task coverage in large datasets. Here, we propose DeepTaskGen, a deep-learning approach that synthesizes non-acquired task-based contrast maps from resting-state (rs-) fMRI. We validate this approach using the Human Connectome Project lifespan data, then generate 47 contrast maps from 7 different cognitive tasks for over 20,000 individuals from UK Biobank. DeepTaskGen outperforms several benchmarks in generating synthetic task-contrast maps, achieving superior reconstruction performance while retaining inter-individual variation essential for biomarker development. We further show comparable or superior predictive performance of synthetic maps relative to actual maps and rs-connectomes across diverse demographic, cognitive, and clinical variables. This approach facilitates the study of individual differences and the generation of task-related biomarkers by enabling the generation of arbitrary functional cognitive tasks from readily available rs-fMRI data.},
  author       = {Serin, Emin and Ritter, Kerstin and Schumann, Gunter and Banaschewski, Tobias and Marquand, Andre and Walter, Henrik and Ogoh, George and Stahl, Bernd Carsten and Brandlistuen, Ragnhild and Schikowski, Tamara and Young, Allan H. and Xinyang, Yu and Zhang, Zuo and Agunbiade, Kofoworola and Chen, Di and Desrivières, Sylvane and Clinton, Nicholas and Thompson, Paul and Köhler, Venessa and Schwalber, Ameli and Calhoun, Vince D. and Chang, Xiao and Zhang, Yanqing and Li, Yuzhu and Dai, Yuxiang and Yuan, Jiacan and Xia, Yunman and Jia, Tianye and Renner, Paul and Hese, Sören and Spanlang, Bernhard and Pearmund, Charlie and Athanasiadis, Anastasios Polykarpos and Petkoski, Spase and Jirsa, Viktor and Schmitt, Karen and Wilbertz, Johannes H. and Patraskaki, Myrto and Sommer, Peter and Heilmann-Heimbach, Stefanie and Mathey, Carina M. and Miller, Abigail J. and Claus, Isabelle and Nöthen, Markus M. and Hoffmann, Per and Forstner, Andreas J. and Pastor, Alvaro and Gallego, Jaime and Itatani, Reiya and Eiroa-Orosa, Francisco and Feixas, Guillem and Slater, Mel and Novarino, Gaia and Böttger, Sarah Jane and Tschorn, Mira and Rapp, Michael and Ask, Helga and Kjelkenes, Rikka and Fernandez, Sara and Van Der Meer, Dennis and Westlye, Lars T. and Andreassen, Ole A. and Aden, Rieke and Seefried, Beke and Nees, Frauke and Neidhart, Maja and Stringaris, Argyris and Schwarz, Emanuel and Holz, Nathalie and Tost, Heike and Meyer-Lindenberg, Andreas and Christmann, Nina and Janson, Karina and Schepanski, Kerstin and Schütz, Tatjana and Taron, Ulrike Helene and Eils, Roland and Roy, Jean Charles and Lett, Tristram A. and Kebir, Hedi and Polemiti, Elli and Hitchen, Esther and Jentsch, Marcel and Serin, Emin and Bernas, Antoine and Vaidya, Nilakshi and Twardziok, Sven and Ralser, Markus and Heinz, Andreas and Schumann, Gunter},
  issn         = {2399-3642},
  journal      = {Communications Biology},
  publisher    = {Springer Nature},
  title        = {{Generating synthetic task-based brain fingerprints for population neuroscience using deep learning}},
  doi          = {10.1038/s42003-025-09158-6},
  volume       = {8},
  year         = {2025},
}