Medical image fusion techniques are extensively used to aid medical diagnosis by combining features of two or more images of various modalities such as Computed Tomography (CT), Magnetic Resonance Image (MRI), and positron emission tomography (PET) into a single output image that contains salient features from all inputs. This paper proposes a hybrid fusion algorithm and is applied on a CT and MRI images. The largest Eigenvalue of the covariance matrices of each image are used to obtain weights for next stage image by Principal Component Analysis (PCA) and different frequency components of the input image are separated by Discrete Cosine Transform (DCT), noise in output images from first two stages. Performance evaluation of CT-MRI image fusion with the hybrid algorithm by Discrete Wavelet Transform (DWT) improves the image quality compared to established methods. Overall, the non-linear fusion rule holds strong potential to help improve image fusion applications in medicine and in other fields.