Lesion location algorithm of epilepsy signals based on image features

Hui Yi; Chunsheng Wang; Wei Wang; Zijian Liu

doi:10.1117/12.2524206

6 May 2019 Lesion location algorithm of epilepsy signals based on image features

Hui Yi, Chunsheng Wang, Wei Wang, Zijian Liu

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110690U (2019) https://doi.org/10.1117/12.2524206
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

Aiming at the problem that the traditional one - dimensional linear processing method can’t effectively extract the characteristic information of the weak signal of the brain, this paper presents a lesion location algorithm of electroencephalogram (EEG) based on image features. Image features is introduced into epileptic signal processing, which can extract feature information and locate lesions in EEG weak signals. First of all, the theoretical basis of onedimensional signal reconstruction into two-dimensional signal is described in this paper. Then, in order to make the image have the intuitionistic distinguishing feature, the Hadamard transform is introduced, which amplifies the original degree of chaos and provides the basis for qualitative and quantitative analysis. Finally, Gabor filter and Fourier spectrum analysis are used to process the Hadamard transformed image. The processed image retains some larger details such as the edge and contrast, which makes the processed image result more intuitive. The lesion lead images can be distinguished by the intuitive differentiation. At the same time, the mean value, contrast and energy entropy of the Fourier spectrum are calculated, and the results are clear. The effectiveness of the proposed method is verified by real epileptic EEG data.

Citation Download Citation

Hui Yi, Chunsheng Wang, Wei Wang, and Zijian Liu "Lesion location algorithm of epilepsy signals based on image features", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110690U (6 May 2019); https://doi.org/10.1117/12.2524206

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available