연구 논문, 2008–2026

Jungyoon Min, Heehwan Wang, Eunji Lee, Bogyeom Kim, Gakyung Kim, Seung Yun Choi, Kahyun Choi, Sung Hee Hong, Yumin Jang, Yu Jin Rah, Ji Yeon Kim, Seunghui Han, Kyung Hwa Lee, Junhyung Kim, Milenna T. van Dijk, Jae-Won Kim, Grace H. Chung, Dongil Chung, Sang Ah Lee, Yoonjung Yoonie Joo, Jiook Cha

MBBN models fMRI BOLD dynamics across distinct statistical scaling regimes and evaluates predictive representations in UK Biobank, ABCD, and ABIDE. Performance varies by task and cohort; the reported prediction and model-attribution results do not establish causal mechanisms or clinical diagnostic validity.

Electroencephalography (EEG) is a non-invasive technique widely used in brain-computer interfaces and clinical applications, yet existing EEG foundation models face limitations in modeling spatio-temporal brain dynamics and lack channel permutation equivariance, preventing robust generalization across diverse electrode configurations. To address these challenges, we propose DIVER-0, a novel EEG foundation model that demonstrates how full spatio-temporal attention—rather than segregated spatial or temporal processing—achieves superior performance when properly designed with Rotary Position Embedding (RoPE) for temporal relationships and binary attention biases for channel differentiation. We also introduce Sliding Temporal Conditional Positional Encoding (STCPE), which improves upon existing conditional positional encoding approaches by maintaining both temporal translation equivariance and channel permutation equivariance, enabling robust adaptation to arbitrary electrode configurations unseen during pretraining. Experimental results demonstrate that DIVER-0 achieves competitive performance with only 10% of pretraining data while maintaining consistent results across all channel permutation conditions, validating its effectiveness for cross-dataset generalization and establishing key design principles for handling the inherent heterogeneity of neural recording setups.

Using cross-sectional ABCD data from 8,111 children, this study found that a depression polygenic score was associated with both multigenerational depression history and offspring psychopathology and statistically mediated 1.39–5.87% of their observed association. The analysis does not establish a causal transmission mechanism.

Foundation models for whole-brain fMRI analysis are dominated by two competing paradigms: Region-of-Interest (ROI) approaches that discard fine-grained spatial information, and hierarchical models with Transformer or Mamba backbones that retain it. However, the rigid, grid-based architecture of hierarchical models imposes critical limitations. They are forced to process vast, uninformative non-brain background regions (up to 60% of the data), creating significant computational inefficiency, and struggle with inter-subject anatomical variation. To overcome these challenges, we introduce NeuroMamba, a foundation model that enables direct sequence modeling of 4D whole-brain fMRI. NeuroMamba leverages Mamba backbone trained with an autoregressive objective given small spatiotemporal patches. Our approach facilitates the adaptive removal of nuisance background signals—a core inefficiency bottleneck for prior grid-based methods. To address anatomical variability, the model incorporates explicit frequency-based positional encodings, enhancing robustness across subjects. While direct sequence modeling is computationally demanding, the linear-time efficiency of Mamba, coupled with adaptive background suppression, makes whole-brain pre-training tractable. We demonstrate the first successful autoregressive pre-training on full-resolution fMRI, achieving state-of-the-art accuracy for sex classification and establishing a scalable paradigm for neuroimaging analysis.

Bogyeom Kim, Gakyung Kim, Yoshinari Abe, Pino Alonso, Stephanie H. Ameis, Alan Anticevic, Paul Arnold, Srinivas Balachander, Nerisa Banaj, Núria Bargalló, Marcelo C. Batistuzzo, Francesco Benedetti, Sara Bertolín, Jan C. Beucke, Irene Bollettini, Silvia Brem, Brian P. Brennan, Jan K. Buitelaar, Rosa Calvo, Miguel Castelo‐Branco, Yuqi Cheng, Ritu Bhusal Chhatkuli, Valentina Ciullo, Ana Coelho, Beatriz Couto, Sara Dallaspezia, Benjamin A. Ely, Sónia Ferreira, Martine Fontaine, Jean‐Paul Fouché, Rachael Grazioplene, Patricia Gruner, Kristen Hagen, Bjarne Hansen, Gregory L. Hanna, Yoshiyuki Hirano, Marcelo Q. Höxter, Morgan Hough, Hao Hu, Chaim Huyser, Toshikazu Ikuta, Neda Jahanshad, Anthony James, Fern Jaspers‐Fayer, Selina Kasprzak, Norbert Kathmann, Christian Kaufmann, Minah Kim, Kathrin Koch, Gerd Kvale, Jun Soo Kwon, Luisa Lázaro, Junhee Lee, Christine Löchner, Jin Lü, Daniela Rodriguez Manrique, Ignacio Martínez‐Zalacaín, Yoshitada Masuda, Koji Matsumoto, Maria Paula Maziero, José M. Menchón, Luciano Minuzzi, Pedro Silva Moreira, Pedro Morgado, Janardhanan C. Narayanaswamy, Jin Narumoto, Ana E. Ortiz, Junko Ota, José C. Pariente, Chris Perriello, Maria Picó‐Pérez, Christopher Pittenger, Sara Poletti, Eva Real, Y. C. Janardhan Reddy, Daan van Rooij, Yuki Sakai, João Ricardo Sato, Cinto Segalàs, Roseli Gedanke Shavitt, Zonglin Shen, Eiji Shimizu, Venkataram Shivakumar, Noam Soreni, Carles Soriano‐Mas, Nuno Sousa, Mafalda Machado Sousa, Gianfranco Spalletta, Emily Stern, S. Evelyn Stewart, Philip R. Szeszko, Rajat M. Thomas, Sophia I. Thomopoulos, Daniela Vecchio, Ganesan Venkatasubramanian, Chris Vriend, Susanne Walitza, Zhen Wang, Anri Watanabe, Lidewij H. Wolters

Milenna T. van Dijk, Ardesheer Talati, Pratik Kashyap, Karan Desai, Nora Clancy Kelsall, Marc J. Gameroff, Natalie Aw, Eyal Abraham, Breda Cullen, Jiook Cha, Christoph Anacker, Myrna M. Weissman, Jonathan Posner

Claudia Lugo‐Candelas, Yajing Pang, Seonjoo Lee, Jiook Cha, Susie Hong, Lisa M. Ranzenhofer, Rachel Korn, Haley Davis, Hailey McInerny, Janet Schebendach, Wendy K. Chung, Rudolph L. Leibel, B. Timothy Walsh, Jonathan Posner, Michael Rosenbaum, Laurel Mayer

Emily L. Dennis, Seth G. Disner, Negar Fani, Lauren E. Salminen, Mark W. Logue, Emily K. Clarke‐Rubright, Courtney C. Haswell, Christopher L. Averill, Lee A. Baugh, Jessica Bomyea, Steven E. Bruce, Jiook Cha, Kyle Choi, Nicholas D. Davenport, Maria Densmore, Stéfan du Plessis, Gina L. Forster, Jessie L. Frijling, A. Gönenç, Staci A. Gruber, Daniel W. Grupe, Jeffrey P. Guenette, Jasmeet P. Hayes, David Hofmann, Jonathan Ipser, Tanja Jovanović, Sinéad Kelly, Mitzy Kennis, Philipp Kinzel, Saskia B.J. Koch, Inga K. Koerte, Sheri‐Michelle Koopowitz, Mayuresh S. Korgaonkar, John H. Krystal, Lauren A. M. Lebois, Gen Li, Vincent A. Magnotta, Antje Manthey, Geoff J. May, Deleene S. Menefee, Laura Nawijn, Steven M. Nelson, Richard W. J. Neufeld, Jack B. Nitschke, Daniel C.M. O'Doherty, Matthew Peverill, Kerry J. Ressler, Annerine Roos, Margaret A. Sheridan, Anika Sierk, Alan N. Simmons, Raluca M. Simons, Jeffrey S. Simons, Jennifer S. Stevens, Benjamin Suarez‐Jimenez, Danielle R. Sullivan, Jean Théberge, Jana K. Tran, Leigh L. van den Heuvel, Steven J.A. van der Werff, Sanne J.H. van Rooij, Mirjam van Zuiden, Carmen Vélez, Mieke Verfaellie, Robert Vermeiren, Benjamin Wade, Tor D. Wager, Henrik Walter, Sherry Winternitz, Jonathan D. Wolff, Gerald E. York, Ye Zhu, Xi Zhu, Chadi G. Abdallah, Richard A. Bryant, Judith K. Daniels, Richard J. Davidson, Kelene A. Fercho, Carol E. Franz, Elbert Geuze, Evan M. Gordon, Milissa L. Kaufman, William S. Kremen, Jim Lagopoulos, Ruth A. Lanius, Michael J. Lyons, Stephen R. McCauley, Regina E. McGlinchey, Katie A. McLaughlin, William Milberg, Yuval Neria, Miranda Olff, Soraya Seedat, Martha E. Shenton, Scott R. Sponheim, Dan J. Stein, Murray B. Stein, Thomas Straube, David F. Tate, Nic J.A. van der Wee

Claudia Lugo‐Candelas, Jiook Cha, Susie N. Hong, Vanessa Bastidas, Myrna M. Weissman, William P. Fifer, Michael Myers, Ardesheer Talati, Ravi Bansal, Bradley S. Peterson, Catherine Monk, Jay A. Gingrich, Jonathan Posner

Dominik Biezonski, Relish Shah, А. А. Кривко, Jiook Cha, David N. Guilfoyle, Jan Hrabě, Scott Gerum, Shan Xie, Yuping Duan, Ravi Bansal, Bennett Leventhal, Bradley S. Peterson, Christoph Kellendonk, Jonathan Posner