The Magnetic Resonance Imaging acquires raw data in frequency domain. The data is reconstructed to the image. The data acquired in k-space can be undersampled to reduce reconstruction time. Accelerating the imaging while preserving diagnostic quality is an active area of research. Robust Principal Component Analysis (RPCA) is a powerful method for MRI reconstruction. The process decomposes the data matrix into two components: a low-rank component and a sparse component. The former reveals the structured background and the latter indicates the fine details. Our work majorly focuses on Ishchemic Stroke lesions. The lesions will be represented by the sparse component matrix. The weighting parameter controls the balance between the two matrix parts. This research explores the effect of adjusting the sparse component weighting parameter \( \lambda \) on the efficiency of RPCA-based MR image reconstruction. The study was done on diffusion-weighted MR images. RPCA was implemented slice-by-slice, and image was reconstructed for varying values of \( \lambda \) . Quality of reconstruction was measured quantitatively in terms of Mean Squared Error (MSE), Structural Similarity Index Measure (SSIM), and Peak Signal-to-Noise Ratio (PSNR), with focus on region-of-interest (ROI). This paper emphasizes the impact of the parameter \( \lambda \) within model-based MR reconstruction technique.