Advances in optical and artificial intelligence-powered techniques for rapid and real-time detection of bacterial pathogens in food and clinical applications

Rapid and real-time detection of bacterial pathogens is crucial for food safety, public health, and clinical diagnostics. Recent advancements in spectroscopy, optical imaging, and artificial intelligence (AI) technologies have significantly enhanced the accuracy and practicality of optical approaches for microbial analysis. Here, useful techniques, such as Fourier transform infrared spectroscopy, hyperspectral imaging, laser speckle imaging, and time-lapse shadow image analysis, which have demonstrated their effectiveness in identifying and quantifying pathogenic bacteria, are explored. Additionally, the integration of machine learning models, particularly convolutional neural networks and transformer networks, is examined for the automated classification of microbial images. The application of these technologies to detect pathogens in clinical and food samples, and the need for further integration of AI with spectroscopic and optical imaging methods, are discussed. Future directions are proposed to advance non-invasive and label-free bacterial detection technologies that can further enhance food safety and clinical diagnostics.