<![CDATA[The development of robust machine learning models for medical diagnostics is constrained by the scarcity of large, annotated imaging datasets, a challenge rooted in high acquisition costs and stringent privacy regulations. To address this, generative approaches for data synthesis have emerged as an essential tool, and this study explores the use of diffusion models to generate medical images. This study introduces a novel Diffusion Autoencoder Model (DAM) integrated with a semantic encoder framework to generate interpretable and decodable image representations. Our DAM learns disentangled latent features via its encoder, which then conditions a diffusion probabilistic model acting as the decoder, enabling the synthesis of highly informative medical images. The model’s performance is assessed by using quantitative metrics demonstrating superior results compared to state-of-the-art generative models. In addition to its generative precision, the proposed model has significant potential for image classification. Notably, the semantic encoder learned by the model generates representations that lead to a significant increase in classification accuracy: for PneumoniaMNIST, the binary classification accuracy improved from 0.854 to 0.95; for RetinaMNIST, the multiclass accuracy increased from 0.528 to 0.94. These findings underscore the potential of DAMs to tackle data scarcity issues, enhance classification performance, and ultimately improve diagnostic methodologies.]]>
Copyrights © 2026
