Lateralization of temporal lobe epilepsy by multimodal multinomial hippocampal response-driven models

JOURNAL OF THE NEUROLOGICAL SCIENCES

卷:347

Article

Nazem-Zadeh, Mohammad-Reza^1,2  Elisevich, Kost V.³  Schwalb, Jason M.⁴  Bagher-Ebadian, Hassan^2,5  Mahmoudi, Fariborz^1,2,6  Soltanian-Zadeh, Hamid^1,2,7 

[1] Henry Ford Hlth Syst, Dept Res Adm, Detroit, MI 48202 USA

[2] Henry Ford Hlth Syst, Dept Radiol, Detroit, MI 48202 USA

[3] Spectrum Hlth Med Grp, Dept Clin Neurosci, Grand Rapids, MI 49503 USA

[4] Henry Ford Hlth Syst, Dept Neurosurg, Detroit, MI 48202 USA

[5] Henry Ford Hlth Syst, Dept Neurol, Detroit, MI 48202 USA

[6] Islamic Azad Univ, Comp & IT Engn Fac, Qazvin Branch, Tehran, Iran

[7] Univ Tehran, Sch Elect & Comp, Control & Intelligent Proc Ctr Excellence CIPCE, Tehran, Iran

关键词: Temporal lobe epilepsy (TLE);    Hippocampus;    Magnetic resonance imaging (MRI);    Single photon emission computed tomography (SPECT);    Multimodal multinomial response-driven lateralization models;    Bayesian model averaging (BMA);   

DOI  :  10.1016/j.jns.2014.09.029

来源: Elsevier

【 摘 要 】

Purpose: Multiple modalities are used in determining laterality in mesial temporal lobe epilepsy (mTLE). It is unclear how much different imaging modalities should be weighted in decision-making. The purpose of this study is to develop response-driven multimodal multinomial models for lateralization of epileptogenicity in mTLE patients based upon imaging features in order to maximize the accuracy of noninvasive studies. Methods and materials: The volumes, means and standard deviations of FLAIR intensity and means of normalizedictal-interictal SPECT intensity of the left and right hippocampi were extracted from preoperative images of a retrospective cohort of 45 mTLE patients with Engel class I surgical outcomes, as well as images of a cohort of 20 control, nonepileptic subjects. Using multinomial logistic function regression, the parameters of various univariate and multivariate models were estimated. Based on the Bayesian model averaging (BMA) theorem, response models were developed as compositions of independent univariate models. Results: A BMA model composed of posterior probabilities of univariate response models of hippocampal volumes, means and standard deviations of FLAIR intensity, and means of SPECT intensity with the estimated weighting coefficients of 028, 032, 0.09, and 031, respectively, as well as a multivariate response model incorporating all mentioned attributes, demonstrated complete reliability by achieving a probability of detection of one with no false alarms to establish proper laterality in all mTLE patients. Conclusion: The proposed multinomial multivariate response-driven model provides a reliable lateralization of mesial temporal epileptogenicity including those patients who require phase II assessment. (C) 2014 Elsevier B.V. All rights reserved.

【 授权许可】

Free