DANG: Data Augmentation Based on NIR-II Guided Diffusion Model for Fluorescence Molecular Tomography

作者：Qiushi Huang, Chunzhao Li, Anqi Xiao, Jie Tian, Zhenhua Hu · 发表于：IEEE Transactions on Computational Imaging · 年份：2025 · DOI：10.1109/tci.2025.3643313 · 被引用次数：2 · 研究领域：Optical Imaging and Spectroscopy Techniques、Nanoplatforms for cancer theranostics、Optical Coherence Tomography Applications

Fluorescence molecular tomography (FMT), particularly within the second near-infrared window (NIR-II, 1000-1700 nm), is a sophisticated imaging technique for numerous medical applications, enabling reconstruction of the three-dimensional (3D) distribution of internal tumors from surface fluorescence signals. Recent studies have demonstrated the effectiveness of deep learning methods in FMT reconstruction tasks, however, their performance heavily relies on large-scale, diverse labeled datasets. The existing researches primarily focused on datasets with static tumor characteristics, including fixed tumor numbers, locations, and sizes, which shows an insufficient pattern diversity, limiting neural networks' generalization ability for complex real-world scenarios beyond the training dataset. To address this limitation, we draw inspiration from the similarity between Monte Carlo photon simulation and sampling process of diffusion model, to propose a diffusion model-based data augmentation strategy. Further, we introduce a novel NIR-II-specific guidance mechanism to enhance sample fidelity and diversity by incorporating NIR-II spectral optical properties. Quantitative analysis validated that high-quality NIR-II fluorescence signal samples are synthesized, where the proposed NIR-II guidance achieved a 56.7% reduction in Fréchet Inception Distance(FID) and a 21.5% improvement in Inception Score (IS), covering a broad spectrum of patterns. Since the synthetic samples are unlabeled whi...