Functional Ultrasound Imaging of Epileptic Dynamics: A Model-Based Investigation

Welcome to the Conference Abstract Server Here you can explore all conference abstracts, sorted by session and listed below. Talks: Invited Talks (IT) and Contributed Talks (CT) are numbered in order of appearance. Posters: Posters (P) are grouped by Poster Session (I–IV) and listed by poster board number. Log in to mark abstracts as favourites. Click the asterisk symbol ★ above an abstract to add it to "My Favourites". The asterisk will also appear in the list overview for quick reference. Functional Ultrasound Imaging of Epileptic Dynamics: A Model-Based Investigation Benedetta Gambosi , Christian Buda , Melissa Monti , Nicola Toschi , Laura Astolfi 1. Department of Computer Control and Management Engineering, University of Rome ‘Sapienza’, Italy 2. Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi”, University of Bologna, Italy 3. Department of Biomedicine and Prevention, University of Rome Tor Vergata, Italy 4. A.A. Martinos Center for Biomedical Imaging, Harvard Medical School, United States of America 5. Department of Psychology, School of Biological Sciences, University of Cambidge, United Kingdom Functional ultrasound imaging (fUSI) enables access to deep brain activity through neurovascular coupling, complementing the surface-biased perspective of EEG [1, 2]. In this study, we evaluated whether synthetic fUSI signals, derived from stereo EEG (sEEG), could aid seizure phase classification, particularly for detecting preictal states relevant to early intervention. We trained one-dimensional convolutional neural networks (1D-CNNs) on sEEG recordings from 34 drugresistant epilepsy patients from the HUP iEEG Epilepsy Dataset [2]. Signals were resampled to 500 Hz, high-pass filtered at 1 Hz, and cleaned using spectral interpolation and bipolar rereferencing. For each seizure, 2-minute preictal and 30-second postictal segments were extracted, along with matched interictal epochs. Data were split using 3-second input windows. Synthetic fUSI signals were obtained by convolving sEEG data with an experimentally derived hemodynamic response function (HRF), modeling neurovascular dynamics [3]. To support training, we employed a Wilson-Cowan neural mass model with dynamic excitatory-inhibitory coupling to simulate transitions across interictal, preictal, and ictal phases [4]. Synthetic electrophysiological signals were convolved with the HRF to produce fUSI-like data. The CNN architecture consisted of three convolutional layers with ReLU activation, batch normalization, dropout, and global average pooling. Regularization and early stopping were used to prevent overfitting. 1 1 2 3, 4, 5 1 Pretraining on the synthetic dataset significantly enhanced performance on real sEEG recordings. On the test set, the model achieved 0.85 accuracy for interictal vs. ictal classification and 0.75 for interictal vs. preictal, demonstrating strong discriminative capability, including during early seizure phases. Comparable results were obtained using synthetic fUSI signals derived from the sEEG data, with accuracies of 0.78 and 0.70, respectively. Our work suggests that fUSI data may provide phase-specific information relevant to seizure monitoring, indicating its potential utility in clinical neuroimaging applications. Beyond classification, such models may support interpretability by revealing phase-specific dynamics in latent space. Future work will explore scaling this approach to larger cohorts and integrating scalp EEG with synthetic or real fUSI to develop robust, non-invasive, deep-aware seizure prediction systems suited for closed-loop neuromodulation. Acknowledgements Research supported by the Italian Ministry of University and Research—PRIN (2022LB7WKJ and 20207S3NB8) and by the AEGEUS project funded by the European Union, Horizon Europe Programme (GA 101099210) References 1. E. Mac., G. Montaldo, I. Cohen, M. Baulac, M. Fink, and M. Tanter, “Functional ultrasound imaging of the brain,” Nature Methods, 2011, 10.1016/j.neuroscience.2021.03.005 (http://dx.doi.org/10.1016/j.neuroscience.2021.03.005) 2. R. Abreu, A. Leal, and P. Figueiredo, “Eeg-informed mri: a review of data analysis methods,” Frontiers in Human neuroscience, 2018., 10.3389/fnhum.2018.00029 (http://dx.doi.org/10.3389/fnhum.2018.00029) 3. J. M. Bernabei and A. Li and A. Y. Revell and R. J. Smith and K. M. Gunnarsdottir and I. Z. Ong and K. A. Davis and N. Sinha and S. Sarma and B. Litt, "HUP iEEG Epilepsy Dataset." OpenNeuro, 2023., 10.18112/openneuro.ds004100.v1.1.3 (http://dx.doi.org/10.18112/openneuro.ds004100.v1.1.3) 4. A. O. Nunez-Elizalde, M. Krumin, C. B. Reddy, G. Montaldo, A. Urban, K. D. Harris, and M. Carandini, “Neural correlates of blood flow measured by ultrasound,” Neuron, 2022., 10.1016/j.neuron.2022.02.012 (http://dx.doi.org/10.1016/j.neuron.2022.02.012) 5. Meijer, H.G.E., Eissa, T.L., Kiewiet, B. et al. "Modeling Focal Epileptic Activity in the Wilson–Cowan Model with Depolarization Block." J. Math. Neurosc. 2015, 10.1186/s13408-015-0019-4 (http://dx.doi.org/10.1186/s13408-015-0019-4) Copyright: © (2025) Gambosi B, Buda C, Monti M, Toschi N, Astolfi L Citation: Gambosi B, Buda C, Monti M, Toschi N, Astolfi L (2025) Functional Ultrasound Imaging of Epileptic Dynamics: A Model-Based Investigation. Bernstein Conference 2025. doi: 10.12751/nncn.bc2025.031 (http://doi.org/10.12751/nncn.bc2025.031) State Log Date State Editor Message 08/21/2025 Accepted Samira Kalemba 07/16/2025 InReview Abstracts Admin 07/15/2025 Submitted Benedetta Gambosi 07/15/2025 InPreparation Benedetta Gambosi Initial abstract creation