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.
@article{arxiv.2507.15361,
title = {Latent Space Synergy: Text-Guided Data Augmentation for Direct Diffusion Biomedical Segmentation},
author = {Muhammad Aqeel and Maham Nazir and Zanxi Ruan and Francesco Setti},
journal= {arXiv preprint arXiv:2507.15361},
year = {2025}
}