This study comprehensively investigates the swelling behavior and structural changes in a prismatic lithium-ion battery module using CT imaging and in-situ mechanical measurements. To facilitate efficient and accurate segmentation of battery cells within the module, an automated CT image processing algorithm based on computer vision and machine learning was developed. By comparing CT scans taken at begin of life and end of cycling (~40% SOH), significant geometric and mechanical changes were observed, with the central regions of the cells showing more pronounced swelling compared to other areas. Notably, the peak swelling at the end of cycling was measured to be 250% of the maximum value recorded at begin of life. These results provide quantitative metrics for optimizing module design and offer important insights for improving the operational safety and reliability of lithium-ion battery systems.