From droplets to diagnosis: AI-driven imaging and system integration in digital nucleic acid amplification testing

Digital nucleic acid amplification testing (dNAAT)-including digital PCR and isothermal techniques-has transformed precision diagnostics by enabling single-molecule quantification. However, its widespread adoption in point-of-care testing (POCT) remains limited by challenges in partitioning diversity, signal interpretation, and workflow integration. In this review, we provide the first systematic synthesis of artificial intelligence (AI)-driven fluorescence image analysis in dNAAT, detailing the evolution from classical classifiers to modern deep learning and foundation models (e.g., SAM, ViT, GPT-4o). We propose a structured framework that redefines dNAAT into five stages: Sample Preparation, Partition, Amplification, Detection, and Analysis, highlighting advancements enhancing precision, scalability, and automation at each step. The review also surveys integrated system prototypes for POCT and explores translational opportunities for AI-native platforms. Finally, we discuss key limitations-including data scarcity and model generalizability-and outline future research directions toward democratized molecular diagnostics.