The strength of deep neural networks lies in the magnitude of the dataset available for training. Feeding sufficient data to the machine learning algorithm is a challenging task in the field of healthcare. Data augmentation is a persuasive way of expanding the dataset artificially using tweaks to create a diversity of samples sufficient to train deep neural networks. Healthcare organizations are now leveraging data augmentation as their crucial resource. To realize the above-cited use cases, we have proposed a collaborative data augmentation technique that uses an elementary transformation technique and an optimized generative augmentation technique. Deep generative models like GANs are capable of generating high-resolution plausible annotated medical images, which are the need of the hour in the medical research and development domain. Data augmentation overcomes the paucity of medical images and the class imbalance problem. The proposed augmentation method could perform classification with an accuracy of 97.76%.