AI-driven dual-mode phase and label-free fluorescence imaging platform using a single-shot gabor hologram.

Simultaneous acquisition of quantitative phase and fluorescence information is essential for comprehensive cellular analysis, as these complementary modalities provide structural and biochemical insights, respectively. However, conventional dual-mode imaging systems require fluorescent labeling, complex optical architectures, and multiple acquisition channels, which limit scalability, increase cost, and hinder deployment in low-resource or high-throughput settings. Here, we present an AI-driven dual-mode phase and label-free fluorescence imaging platform using a single-shot Gabor hologram. The proposed framework enables simultaneous reconstruction of quantitative phase images and virtual fluorescence channels from a single low-cost holographic measurement, eliminating the need for fluorescent staining, multi-shot acquisition, or multimodal optical hardware. To achieve this, we introduce a one-sided unsupervised diffusion model that learns a unidirectional mapping from Gabor holograms to dual-mode outputs without requiring paired training data or cycle-consistency constraints. The model integrates contrastive learning-based hologram synthesis with hologram-conditioned denoising diffusion to ensure high structural fidelity and robust cross-modal reconstruction. Ground-truth phase and fluorescence images acquired from a conventional dual-mode optical system are used only during training, while inference relies exclusively on a single-shot Gabor hologram captured with a minimal optical configuration. Experimental validation across multiple cancer cell lines and organelle-specific fluorescence channels demonstrates that the proposed platform accurately recovers cellular morphology and subcellular distributions, achieving an FID of 57.74, SSIM of 0.76, PSNR of 26.89 dB, and LPIPS of 0.12, and further generalizes to unseen conditions including higher magnification, different cell type, low-illumination, and defocused acquisitions. These results support quantitative analysis, cell-type discrimination, and drug-response assessment, establishing a scalable and cost-effective platform that paves the way toward compact, high-content label-free imaging solutions.