There are various kinds of methods on activated regions detection,<br> including model-driven method and data-driven method, univariate method and<br> multivariate method, frequency domain analysis and time-domain analysis etc.<br> We investigated the problems of principal component analysis applied to activated<br> regions detection,an autocovariance based principal component analysis<br> method was proposed. Firstly,the time series were converted to the autocovariance<br> series, a