Repository Collection: null

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

2026-10-19T04:40:21Z

Title: AI-driven dual-mode phase and label-free fluorescence imaging platform using a single-shot gabor hologram Author(s): Park, Seonghwan; Lee, Jaeseong; Park, Jaewoo; Moon, Inkyu Abstract: 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.

AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms

2026-09-23T06:10:15Z

Title: AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms Author(s): Moon, Inkyu; Javidi, Bahram Abstract: Recent progress in artificial intelligence (AI) and digital holographic microscopy (DHM) has enabled quantitative, label-free, and noninvasive cellular imaging with unprecedented precision. This review provides an overview of AI-driven DHM technologies that transform classical holographic phase reconstruction and cellular analysis into real-time, portable biomedical solutions. After outlining the optical and computational fundamentals of DHM and quantitative phase imaging, we describe how deep generative and diffusion models substantially enhance phase retrieval accuracy under noisy or single-shot conditions. We then summarize recent biomedical applications, integrating blood, cancer, and cardiac cell analyses into a unified framework of AI-assisted quantitative phenotyping. Deep and self-supervised learning approaches are shown to enable high-accuracy classification of red blood cells and cancer cells and label-free evaluation of cardiomyocyte contractility and drug response. The combination of AI-based reconstruction, self-supervised learning, and physics-informed modeling demonstrates robust performance even with limited labeled data. Finally, we discuss the system-level transition toward low-cost, edge-AIenabled DHM platforms capable of real-time phase imaging in point-of-care or field environments. We highlight key challenges in data standardization, interpretability, and multimodal integration. Collectively, this review envisions AI-integrated DHM as a scalable, accessible technology bridging advanced quantitative imaging with practical biomedical diagnostics.

AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms

2026-06-08T18:01:22Z

Title: AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms Author(s): Moon, Inkyu; Javidi, Bahram Abstract: Recent progress in artificial intelligence (AI) and digital holographic microscopy (DHM) has enabled quantitative, label-free, and noninvasive cellular imaging with unprecedented precision. This review provides an overview of AI-driven DHM technologies that transform classical holographic phase reconstruction and cellular analysis into real-time, portable biomedical solutions. After outlining the optical and computational fundamentals of DHM and quantitative phase imaging, we describe how deep generative and diffusion models substantially enhance phase retrieval accuracy under noisy or single-shot conditions. We then summarize recent biomedical applications, integrating blood, cancer, and cardiac cell analyses into a unified framework of AI-assisted quantitative phenotyping. Deep and self-supervised learning approaches are shown to enable high-accuracy classification of red blood cells and cancer cells and label-free evaluation of cardiomyocyte contractility and drug response. The combination of AI-based reconstruction, self-supervised learning, and physics-informed modeling demonstrates robust performance even with limited labeled data. Finally, we discuss the system-level transition toward low-cost, edge-AI-enabled DHM platforms capable of real-time phase imaging in point-of-care or field environments. We highlight key challenges in data standardization, interpretability, and multimodal integration. Collectively, this review envisions AI-integrated DHM as a scalable, accessible technology bridging advanced quantitative imaging with practical biomedical diagnostics. (c) 2026 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

Scalable Neural Cryptanalysis of Block Ciphers in Federated Attack Environments

2026-04-15T18:01:45Z

Title: Scalable Neural Cryptanalysis of Block Ciphers in Federated Attack Environments Author(s): Jeong, Ongee; Park, Seonghwan; Moon, Inkyu Abstract: This paper presents an extended investigation into deep learning-based cryptanalysis of block ciphers by introducing and evaluating a multi-server attack environment. Building upon our prior work in centralized settings, we explore the practicality and scalability of deploying such attacks across multiple distributed edge servers. We assess the vulnerability of five representative block ciphers-DES, SDES, AES-128, SAES, and SPECK32/64-under two neural attack models: Encryption Emulation (EE) and Plaintext Recovery (PR), using both fully connected neural networks and Recurrent Neural Networks (RNNs) based on bidirectional Long Short-Term Memory (BiLSTM). Our experimental results show that the proposed federated learning-based cryptanalysis framework achieves performance nearly identical to that of centralized attacks, particularly for ciphers with low round complexity. Even as the number of edge servers increases to 32, the attack models maintain high accuracy in reduced-round settings. We validate our security assessments through formal statistical significance testing using two-tailed binomial tests with 99% confidence intervals. Additionally, our scalability analysis demonstrates that aggregation times remain negligible (<0.01% of total training time), confirming the computational efficiency of the federated framework. Overall, this work provides both a scalable cryptanalysis framework and valuable insights into the design of cryptographic algorithms that are resilient to distributed, deep learning-based threats.