In the process of diagnosis using medical image, it is necessary to do image enhancement efficiently in order to mine more information for decision-making as much as possible. However, the traditional medical image enhancement algorithm has some shortcomes, such as creating noise and fuzziness. Therefore, an image enhancement algorithm based on shearlet domain and improved Pal-King algorithm is proposed. First, the shearlet transform is used to decompose the image two parts, high frequency part and low frequency part. Then the adaptive threshold denoising method is used to denoise the image efficiently. After that, the inverse shear wave transform is used to reconstruct the image. Finally, Pal-King algorithm is used to enhance contrast to highlight the details of the image. In order to verify the validity of this algorithm, the processing results of the proposed algorithm are compared with shear wave, fractional differential and the improved Pal-King enhancement method respectively by using the self-built image database. Results show that both the enhancement effect and contrast of image by the proposed algorithm has significant improvements.