An information-theoretic detector based scheme for registration of speckled medical images

摘要: Several studies dealt with medical ultrasound registration. Their similarity metrics relied on pixel-to-pixel intensity comparisons. Hence, they are not well suited to the case of speckled images. To better handle speckle noise, our previous work proposed an information-theoretic feature detector-based registration approach. This aims extend it cases where image model is Rayleigh or normalized Fisher-Tippett distributed. Using modeling based these distributions, a speckle-specific information- theoretic detector constructed and applied provide Those images then registered using differential equations, solution which provides transformation bring into alignment. Compared standard gradient-based techniques, experimental results demonstrate effectiveness method, particularly for low contrast