A Generative Data Augmentation framework for Brain Tumour and Chest X ray Classification using DCGAN and Diffusion Models

Author(s)	Ms. Madhuri Pandit Pujari, Prof. Prasad Bhosale, Prof. Shaminabano Shaikh, Prof. Vishal Shinde
Country	India
Abstract	The performance of deep learning models in medical image classification is often limited by data scarcity, class imbalance and privacy constraints. This paper proposes a generative data augmentation framework that integrates Deep Convolutional Generative Adversarial Networks (DCGAN) and Diffusion Models to enhance brain tumour MRI and chest X ray classification tasks. Synthetic images are generated using both models and combined with real datasets to improve training diversity. The quality of generated images is quantitatively evaluated using Frechet Inception Distance (FID) and Structural Similarity Index (SSIM). A ResNet-50 classifier is trained on original and augmented datasets to assess improvements in diagnostic performance. Experimental results demonstrate that diffusion based augmentation achieves superior image fidelity and improved classification robustness, while DCGAN provides computational efficiency. The proposed framework effectively mitigates data scarcity and enhances medical image classification reliability.
Keywords	Generative Adversarial Networks, Diffusion Models, Structural Similarity Index, ResNet 50, X ray, Brain tumour, Chest X-ray Analysis, Diffusion Models, Data Augmentation, Medical Image Classification
Field	Engineering
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-13

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research