 Executed a pipeline for processing Digital Imaging and Communications in Medicine (DICOM) images in batches to ensure efficient handling of a large dataset Applied preprocessing steps, including normalization to standardize pixel intensity values, inversion of monochrome pixel values, resizing images, and conversion to PNG format to facilitate compatibility with the neural network Randomly selected 2000 patients and partitioned the dataset into training, validation, and testing based on class labels, “cancer” and “normal” Carried out data-to-image mapping to ensure that each PNG file corresponded to its respective patient data entry in a CSV file Deployed EfficientNet architectures for image classification tasks, that implemented data augmentation techniques such as random rotations, translations, and flips to enhance robustness and generalization, as well as early stopping to prevent overfitting