<p>Medical imaging plays an important role in clinical diagnosis and disease analysis, providing essential information for lesion detection, treatment planning, and therapeutic evaluation. However, due to limitations in imaging resolution, scanning time, and radiation dose control, medical images often suffer from insufficient resolution and blurred details, which may affect the observation of fine structures and early lesions. To address this issue, this paper proposes a medical image super-resolution reconstruction method that combines wavelet transform and attention mechanisms. In the proposed network, discrete wavelet transform (DWT) and inverse wavelet transform (IWT) are introduced to exploit multi-scale frequency information and facilitate collaborative modeling of low- and high-frequency features. In addition, a Residual Wavelet Attention Block (RWAB) and a spatial self-attention mechanism are designed to adaptively emphasize important texture and edge details, thereby enhancing structural feature representation. Experimental results on multiple medical image datasets show that the proposed method achieves relatively good reconstruction performance under different upscaling factors. In terms of objective evaluation metrics, including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), and learned perceptual image patch similarity (LPIPS), the proposed method obtains relatively favorable results, while subjective visual comparisons also indicate good detail recovery and image clarity. The proposed approach provides a useful reference for medical image super-resolution reconstruction and related clinical image analysis tasks.</p>