Nader Jafarnia Dabanloo - Faculty of Biomedical Engineering , Science and Research Campus, Azad University ,
Sepideh Sabouri - Faculty of Biomedical Engineering , Science and Research Campus, Azad University ,
Hamid SadAbadi - Faculty of Mechanical Engineering , Concordia University Montreal, Quebec, Canada,
Ali Jalali - Faculty of Mechanical Engineering , KN Toosi University of Technology

The aim of this paper is to establish how well one can characterize the location of moderate to large relatively compact infarcis using electrocardiographic evidence , in comparison with a "gold standard" expert analysis of gadolinium - enhanced MRI data . We address on innovative semi autimated method base on behavior of some ECG; features , which are Qwave amplitudes and ST despersion. we call these "Q curve " and "ST curves ". At the first step by p;otiing the vaiability of these features for nodes that lies in lines of torso plane . these curves are obtained .The behavior of the mintioned curves for normal lines both in horizontal and vertical line differ from the abnormal ones. Athreshold method is used here to determine the abnormal body surface area based on this concept. Finally , a semi automated method is applied to localize the MI. We evaluated the method on the physionet Challenge 2007 database which is the expert analysis of gadolinum - enhanced MRI data for four individuals with MI and their ECG data. the results that represented by parameter OS. show the method can predict the location of MI reliably . The simplicity of the method is its major advantage.

ECG signals processing, Myocardinal Infarction, ECG feature , BSPM, Semi - Automated Method