Multichannel evoked signal reconstruction for MEG

The method of singular value decomposition is applied in the separation of the heart and the brain signals which are assumed linearly superimposed in a magnetoencephalographic recording. The signals have been obtained by a SQUID device operating in a separate epoch mode. Each signal is recorded by 37 channels and at the middle of its duration an auditory stimulus was heard by the subject. At the same time a 38th channel was recording the ECG signal. Averaging over all the epochs of the same channel aligned according to the auditory stimulus, and under the assumption that the brain and the heart signals are linearly superimposed, we eliminate any signal synchronous with the heart and retain any signal from the brain synchronous with the auditory stimulus. Aligning all the signals of each channel according to the heart, as defined by the QRS complex in the ECG, and averaging again, we eliminate any signal synchronous with the auditory signal and thus obtain a signal which consists from components aligned with the heart. We use these two 37 channel signals to define a subspace in the 37-dimensional space spanned by the signals recorded by the 37 channels in which the heart component is minimal and the brain component is maximal. The vector basis which is obtained this way defines the weights by which the single epoch signals that are recorded by the 37 channels can be linearly blended to form the underlying true brain signal.