<![CDATA[Medical image reconstruction is a crucial element in magnetic resonance imaging (MRI) to produce high-quality images that support clinical diagnosis. This study aims to develop a medical image reconstruction method based on interpolation techniques that improves spatial accuracy and visual detail in MRI imaging results. The methodology used includes the implementation of bilinear and bicubic interpolation algorithms to process signal data obtained from MRI imaging. The dataset used in this study is brain MRI data from an open database that has been validated. The results show that the bilinear interpolation method provides higher computing speed, while bicubic interpolation produces better visual details on edges and small structures. Quantitative analysis using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics showed an improvement in the quality of the reconstruction images compared to conventional methods. In the brain dataset trial, bicubic interpolation recorded an average PSNR of 38.7 db and SSIM of 0.94, showing a significant improvement compared to the standard method. This research contributes to reducing artifacts and blurring in MRI reconstruction results, thus supporting more accurate medical decision-making. The implementation of this method also shows great potential to be applied in a variety of other clinical applications, such as soft tissue or internal organ imaging. This research is expected to be integrated with deep learning techniques to improve the efficiency and performance of medical image reconstruction in real time.]]>
Copyrights © 2024
