Image quality assessment for medical images based on gradient information

Natural and medical images may have a variety of distortions which may result in a degradation of visual quality. Image quality assessment (IQA) plays an important role in many image processing tasks to quantitatively measure image quality. Although several IQA methods have been developed for decades, each method has its individual characteristic and there is a few researches focusing on the development of quality assessment in a specific type of image such as medical images. We propose a new IQA method based on image gradient which is sensitive to the changed detail in images. This metric computed the similarity of gradient direction and also apply gradient magnitude information to weight these similarity values in pooling process. Experimental results demonstrate that this metric performs well especially in the distortion types that effect to image detail and can be used as the complementary part to the other IQA metrics for evaluating medical images quality.