Hekmati Rasoul, Azencott Robert, Zhang Wei, Chu Zili D, Paldino Michael J
Department of Mathematics, University of Houston, Houston, TX, USA.
Department of Radiology, Texas Children's Hospital, Houston, TX, USA.
Brain Inform. 2020 Oct 31;7(1):13. doi: 10.1186/s40708-020-00114-0.
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 biologically significant inter-connectivity provides efficient inputs for our multi-layer perceptron (MLP) classifier. By imposing rigorous parameter parsimony to avoid overfitting, we construct a small-size MLP with very good percentages of successful classification.
通过对小儿癫痫患者功能磁共振成像记录的皮质活动进行计算机分析，我们在八个皮质叶之一内实现了癫痫发作灶的算法定位。我们创新的机器学习技术涉及对解剖学确定的皮质区域对之间的互信息系数大矩阵进行深入分析。对具有生物学显著互连性的区域对进行严格选择，为我们的多层感知器（MLP）分类器提供了有效的输入。通过严格限制参数简约性以避免过度拟合，我们构建了一个小型MLP，其成功分类的百分比非常高。
