This work represents a comprehensive analysis of the performance of two popular deep learning architectures, ResNet and MobileNet, with particular attention to their use in the classification of magnetic resonance imaging (MRI) pictures. Healthcare professionals need to accurately classify medical images in order to make precise diagnosis and develop successful treatment plans. In this paper authors have done thorough comparative research to clarify the quantitative performance indicators while also exploring qualitative elements, such as the subtle differences between each model's strengths and weaknesses. Beyond the technical assessment, the study investigates ResNet’s and MobileNet’s computational effectiveness and flexibility in response to the various features present in medical imaging data. The project aims to provide a sophisticated understanding of these deep learning systems in order to make a significant addition to the medical image analysis field as a whole. The ultimate goal is to promote improvements in diagnostic accuracy, which will enable healthcare providers to make better judgments and provide better patient care. The results of this study will be crucial in determining the direction of future advancements in this important field as deep learning and medical imaging continue to cross paths. They provide insightful information that goes beyond ResNet and MobileNet to affect the larger field of deep learning applications in medical diagnostics and treatment planning. The aforementioned study highlights the profound potential of deep learning technology to enhance healthcare procedures and further advance medical science.