Automated Medical Image Processing for Early and Precise Disease Diagnosis Across Multiple Modalities

This project focuses on the development of a MATLAB-based MRI image reconstruction pipeline designed to address common limitations in medical imaging, such as noise, low resolution, and artifacts. Leveraging classical image processing techniques, the system enhances MRI image quality through a structured sequence of operations including normalization, Wiener filtering-based denoising, compressed sensing reconstruction via total variation minimization, and super-resolution using bicubic interpolation. Additional postprocessing steps further improve image sharpness and contrast, facilitating better visualization of anatomical structures. By improving the clarity and diagnostic utility of under-sampled MRI data, this approach not only demonstrates the effectiveness of traditional methods but also sets the foundation for future integration with advanced deep learning models to achieve more accurate and efficient medical image reconstruction.