Localization of Epileptic Seizure Focus by Computerized Analysis of fMRI Recordings
| Autor: | Robert Azencott, Michael J. Paldino, Zili D. Chu, Rasoul Hekmati, Wei Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Time series
Computer science Cognitive Neuroscience Overfitting lcsh:Computer applications to medicine. Medical informatics Quantitative Biology - Quantitative Methods 030218 nuclear medicine & medical imaging 03 medical and health sciences Epilepsy 0302 clinical medicine medicine Quantitative Methods (q-bio.QM) Seizure focus lcsh:Computer software business.industry Research Deep learning Computerized analysis fMRI Pattern recognition Mutual information medicine.disease Perceptron Computer Science Applications lcsh:QA76.75-76.765 Neurology Quantitative Biology - Neurons and Cognition FOS: Biological sciences lcsh:R858-859.7 Neurons and Cognition (q-bio.NC) Artificial intelligence Epileptic seizure medicine.symptom business Classifier (UML) 030217 neurology & neurosurgery |
| Zdroj: | Brain Informatics, Vol 7, Iss 1, Pp 1-13 (2020) Brain Informatics |
| Popis: | By computerized analysis of cortical activity recorded via fMRI for pediatric epilepsy patients, we implement algorithmic localization of epileptic seizure focus within one of eight cortical lobes. Our innovative machine learning techniques involve intensive analysis of large matrices of mutual information coefficients between pairs of anatomically identified cortical regions. Drastic selection of pairs of regions with significant inter-connectivity provide efficient inputs for our Multi-Layer Perceptron (MLP) classifier. By imposing rigorous parameter parsimony to avoid over fitting we construct a small size MLP with very good percentages of successful classification. Comment: 25 pages,5 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|