We propose a data augmentation technique utilizing a Diffusion-based generative deep learning model to address the issue of data scarcity in skin disease diagnosis research. Specifically, we enhanced the Stable Diffusion model, a Latent Diffusion Model (LDM), to generate high-quality synthetic images. To mitigate detail loss in existing Diffusion models, we incorporated lesion area masks and improved the encoder and decoder structures of the LDM. Multi-level embeddings were applied using a CLIP encoder-based image encoder to capture detailed representations, ranging from textures to overall shapes. Additionally, we employed pre-trained segmentation and inpainting models to generate normal skin regions and used interpolation techniques to synthesize synthetic images with gradually varying visual characteristics, while having limitations for clinical use, this approach contributes to enhanced data diversity and can be used as reference material. To validate our method, we conducted classification experiments on seven skin diseases using datasets combining synthetic and real images. The results showed improvements in classification performance, demonstrating the effectiveness of the proposed technique in addressing medical data scarcity and enhancing diagnostic accuracy.

Pressure injuries pose significant health risks, especially for the elderly, immobile individuals, and those with sensory impairments. These injuries can rapidly become chronic, making initial diagnosis important. Due to the difficulty of transporting patients from local health facilities to higher-level general hospitals for treatment, it is essential to utilize telemedicine tools, such as chatbots, to ensure rapid initial diagnosis. Recent advances in artificial intelligence have demonstrated potential for medical imaging and disease classification. Ongoing research in the field of dermatological diseases focuses on disease classification. However, the assessment accuracy of artificial intelligence is often limited by unequal class distributions and insufficient dataset quantities. In this study, we aim to enhance the accuracy of artificial intelligence models by generating synthetic datasets. Specifically, we focused on training models for Pressure Injury assessment using both real and synthetic datasets. We used PI data at a domestic medical university. As part of our supplementary research, we established a chatbot system to facilitate the assessment of pressure injuries. Using both constructed and synthetic data, we achieved a top-1 accuracy of 92.03%. The experimental results demonstrate that combining real and synthetic data significantly improves model accuracy. These findings suggest that synthetic datasets can be effectively utilized to address the limitations of small-scale datasets in medical applications. Future research should explore the use of diverse synthetic data generation methods and validate model performance on a variety of datasets to enhance the generalization and robustness of AI models for Pressure Injury assessment.