{"ID":2892135,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15361","arxiv_id":"2507.15361","title":"Latent Space Synergy: Text-Guided Data Augmentation for Direct Diffusion Biomedical Segmentation","abstract":"Medical image segmentation suffers from data scarcity, particularly in polyp detection where annotation requires specialized expertise. We present SynDiff, a framework combining text-guided synthetic data generation with efficient diffusion-based segmentation. Our approach employs latent diffusion models to generate clinically realistic synthetic polyps through text-conditioned inpainting, augmenting limited training data with semantically diverse samples. Unlike traditional diffusion methods requiring iterative denoising, we introduce direct latent estimation enabling single-step inference with T x computational speedup. On CVC-ClinicDB, SynDiff achieves 96.0% Dice and 92.9% IoU while maintaining real-time capability suitable for clinical deployment. The framework demonstrates that controlled synthetic augmentation improves segmentation robustness without distribution shift. SynDiff bridges the gap between data-hungry deep learning models and clinical constraints, offering an efficient solution for deployment in resourcelimited medical settings.","short_abstract":"Medical image segmentation suffers from data scarcity, particularly in polyp detection where annotation requires specialized expertise. We present SynDiff, a framework combining text-guided synthetic data generation with efficient diffusion-based segmentation. Our approach employs latent diffusion models to generate cl...","url_abs":"https://arxiv.org/abs/2507.15361","url_pdf":"https://arxiv.org/pdf/2507.15361v1","authors":"[\"Muhammad Aqeel\",\"Maham Nazir\",\"Zanxi Ruan\",\"Francesco Setti\"]","published":"2025-07-21T08:15:17Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}