Abstract:Medical imaging applications are facing increasingly high-definition and big-capacity signal data, which require low-radiation acquisition and prompt processing. Although image compressive sensing (ICS) has significant advantages in reducing observed data, such as lower complexity and small storage burden, it also faces challenges in dealing with different image types such as medical images. This paper firstly analyzes the characteristics of medical images, and then proposes a specialized compressive sensing algorithm called Sparsity-precise Iterative Hard Thresholding (SIHT), which is specifically designed to address their specific features such as low sparsity and low frequency. SIHT adaptively measures sparsity and step length which becomes more precise during the iteration process to achieve a certain quality improvement in medical image reconstruction. Experimental results demonstrate that as compared to other ICS reconstruction algorithms across three different types of medical image datasets (X-Ray, Ultrasound, MRI), SIHT can achieve the best subjective recovery quality particularly in terms of mitigating blocky artifacts and noise, where a notable improvement is obtained in terms of PSNR an SSIM of medical ICS reconstruction.