Accurate segmentation of the corpus callosum (CC) in magnetic resonance imaging (MRI) plays a critical role in the diagnosis and monitoring of many neurological and psychiatric disorders. Manual segmentation is often time-consuming and subject to observer variability, highlighting the need for robust automated methods. In this research work, we have proposed a fully automated segmentation approach for the CC by using the Mask R-CNN deep learning architecture. The proposed model is trained and validated on a publicly available dataset of brain MR images to accurately localize and delineate the CC structure. Unlike traditional segmentation models, the proposed Mask R-CNN framework enables pixel-level instance segmentation with improved boundary accuracy. Experimental results show that the proposed method achieves a Dice Similarity Coefficient (DSC) of 94.8%, outperforming several deep learning models on the same task. These results demonstrate the effectiveness of the proposed instance segmentation approach in capturing the complex morphology of CC. The high accuracy and fully automated nature of the system suggest its potential as a valuable tool in clinical neuroimaging workflows for rapid and reproducible analysis of brain structure.