Fine-Tuning a Small Vision Language Model Using Synthetic Data for Explaining Bacterial Skin Disease Images

<b>Background/Objectives:</b> Vision language models (VLMs) show strong potential for medical image understanding, but their large scale often limits practical deployment. This study investigates whether a compact VLM can be effectively adapted for dermatology, with a focus on explaining bacterial skin disease images. <b>Methods:</b> We curate a dataset derived from PMC-OA using the BIOMEDICA dataset and construct PMC-derma-VQA-bacteria by pairing images with inherited figure captions and synthetically generated question-answer (QA) supervision produced by Google's Gemini model. SmolVLM is fine-tuned under three supervision settings: QA-only, caption-only, and a combined QA+caption strategy. The models are evaluated on a held-out test set for both text-generation quality and diagnostic classification performance. <b>Results:</b> QA-only supervision yields the best report-generation performance, while the combined QA+caption setting achieves the highest classification accuracy (70.20%). <b>Conclusions:</b> Synthetic QA supervision can meaningfully enhance compact VLMs for medical image understanding and diagnostic support in dermatology.