The purpose of this study is to investigate the potential of machine learning models trained on a wide range of medical imaging datasets for detection and classification of cancerous and tumorous growths of various types. The models analyze large datasets using complex neural networks, picking up subtle patterns that might escape human observation. Integrating these models can enhance the precision and efficiency of cancer diagnosis for radiologists and physicians around the world. The study focuses on training established machine learning models and quantifying their achieved metrics, facilitating the interpretation and sharing of findings within the scientific community. Among all the models trained across both datasets, it is observed that Efficientnet_b4 surpasses the rest in their respective degrees of accuracy while testing.