Deep Learning-Based Visual Complexity Analysis of Electroencephalography Time-Frequency Images: Can It Localize the Epileptogenic Zone in the Brain?
Navaneethakrishna Makaram,
Sarvagya Gupta,
Matthew Pesce,
Jeffrey Bolton,
Scellig Stone,
Daniel Haehn,
Marc Pomplun,
Christos Papadelis,
Phillip Pearl,
Alexander Rotenberg,
Patricia Ellen Grant,
Eleonora Tamilia
Affiliations
Navaneethakrishna Makaram
Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Sarvagya Gupta
Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Matthew Pesce
Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Jeffrey Bolton
Department of Neurology, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Scellig Stone
Division of Epilepsy Surgery, Department of Neurosurgery, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Daniel Haehn
Department of Computer Science, University of Massachusetts Boston, Boston, MA 02115, USA
Marc Pomplun
Department of Computer Science, University of Massachusetts Boston, Boston, MA 02115, USA
Christos Papadelis
Jane and John Justin Institute for Mind Health, Cook Children’s Health Care System, Fort Worth, TX 76104, USA
Phillip Pearl
Department of Neurology, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Alexander Rotenberg
Department of Neurology, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Patricia Ellen Grant
Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
Eleonora Tamilia
Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, USA
In drug-resistant epilepsy, a visual inspection of intracranial electroencephalography (iEEG) signals is often needed to localize the epileptogenic zone (EZ) and guide neurosurgery. The visual assessment of iEEG time-frequency (TF) images is an alternative to signal inspection, but subtle variations may escape the human eye. Here, we propose a deep learning-based metric of visual complexity to interpret TF images extracted from iEEG data and aim to assess its ability to identify the EZ in the brain. We analyzed interictal iEEG data from 1928 contacts recorded from 20 children with drug-resistant epilepsy who became seizure-free after neurosurgery. We localized each iEEG contact in the MRI, created TF images (1–70 Hz) for each contact, and used a pre-trained VGG16 network to measure their visual complexity by extracting unsupervised activation energy (UAE) from 13 convolutional layers. We identified points of interest in the brain using the UAE values via patient- and layer-specific thresholds (based on extreme value distribution) and using a support vector machine classifier. Results show that contacts inside the seizure onset zone exhibit lower UAE than outside, with larger differences in deep layers (L10, L12, and L13: p < 0.001). Furthermore, the points of interest identified using the support vector machine, localized the EZ with 7 mm accuracy. In conclusion, we presented a pre-surgical computerized tool that facilitates the EZ localization in the patient’s MRI without requiring long-term iEEG inspection.
