MRI enhancement based on visual-attention by adaptive contrast adjustment and image fusion

Motivation: Medical image enhancement is a crucial part to improve the quality of the images. The excellent visual effects and image quality can help doctors make quick diagnoses. Among medical images, Magnetic Resonance Imaging (MRI) images play a vital role in clinical diagnosis. Its imaging principle highlights the human tissue part ignoring the boundary information sometimes. Moreover, some imaging results lose details in visual due to the low contrast and the quality of the images. To overcome these limitations, we propose an MRI enhancement method based on visual-attention by means of contrast adjustment and illumination component preservation. Description: The proposed framework includes image generation and image fusion to tackle the limitation of a single image. First, we assume an MRI image composed of tissues and details. We design an adaptive attenuation weight matrix based on the input MRI image according to a new definition of pixel energy. Then, an illumination-preserving image is introduced into the model for the attenuated image as compensation. Finally, an effective image fusion decision map calculation method is devised to create an enhanced MRI image with higher contrast and better perceptual quality. Results and conclusion: The experimental results show that it is a more effective enhancement method which has better performance on most of the objective evaluation metrics and stability than other 14 methods as well as maintains the balance between contrast and illumination of enhanced MRI images.