Medical CT imaging has an important sense in thetreatment process. However, the low resolution of CT images could easilyaffect the final diagnosis, which is influenced by the resolution and theradiation dosage. We propose to solve this problem by using an adaptiveimage super-resolution reconstruction algorithm. First, the algorithm of theCT image of quad-tree decomposition obtains adaptive access to differentscales of the image patches. Then, we exploit K-means clustering algorithmto determine the cluster center. Using the center of cluster, we can obtainthe mapping function between the low-resolution image patches and thehigh-resolution image patches. Finally, the algorithm reconstructs ahigh-resolution image through the mapping function. The experimental resultshave shown that the proposed method is capable of enhanced CT imagereconstruction, peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).
展开▼
