Hyperspectral imaging and machine learning in food microbiology: Developments and challenges in detection of bacterial, fungal, and viral contaminants

Abstract

Hyperspectral imaging (HSI) is a robust and nondestructive method that can detect foreign particles such as microbial, chemical, and physical contamination in food. This review summarizes the work done in the last two decades in this field with a highlight on challenges, risks, and research gaps. Considering the challenges of using HSI on complex matrices like food (e.g., the confounding and masking effects of background signals), application of machine learning and modeling approaches that have been successful in achieving better accuracy as well as increasing the detection limit have also been discussed here. Foodborne microbial contaminants such as bacteria, fungi, viruses, yeast, and protozoa are of interest and concern to food manufacturers due to the potential risk of either food poisoning or food spoilage. Detection of these contaminants using fast and efficient methods would not only prevent outbreaks and recalls but will also increase consumer acceptance and demand for shelf-stable food products. The conventional culture-based methods for microbial detection are time and labor-intensive, whereas hyperspectral imaging (HSI) is robust, nondestructive with minimum sample preparation, and has gained significant attention due to its rapid approach to detection of microbial contaminants. This review is a comprehensive summary of the detection of bacterial, viral, and fungal contaminants in food with detailed emphasis on the specific modeling and datamining approaches used to overcome the specific challenges associated with background and data complexity.

Petri-plate, bacteria, and laser optical scattering sensor

“…Hyperspectral imaging (HSI) technology combines spectroscopy and imaging as a reliable nondestructive technique for bacterial colony counting, and detection and identification on various food, inert surfaces, or clinical specimens ( Gowen et al., 2015 ; Park et al., 2015 ; Bonah et al., 2019 ; Lu et al., 2020 ; Soni et al., 2022 ). Lights with small wavelength bandwidth from visible to near-infrared (Vis-NIR) are often used to generate a complete spatiospectral map of a colony for pathogen detection and identification.…”

“…Inelastic scattering technologies such as near-infrared (NIR) ( Dubois et al., 2005 ), Fourier transform Infrared (FT-IR) ( Naumann et al., 1991 ), Raman ( Stöckel et al., 2016 ), and hyperspectral imaging ( Soni et al., 2022 ) have been used to identify bacterial pathogens that are obtained from isolated colonies from a Petri-dish. Often colony isolated bacterial cell suspensions are dispersed on appropriate substrates (for example, silicon wafer, CaF 2 ) and applied to above mentioned inelastic/vibrational spectroscopy for pathogen identification.…”

Perspective Chapter: Hyperspectral Imaging for the Analysis of Seafood

“…Furthermore, other researchers have analyzed the potential of hyperspectral imaging for food microbiology inspection [14] or for the optimization of agricultural procedures [15].…”

Multicomponent hyperspectral grade evaluation of ilmenite using spectral-spatial joint features

“…Furthermore, HSI offers several benets, including a wider wavelength range, narrower wavelength bands, heightened sensitivity to trace components, and a broader scope for capturing multicomponent information. 8 Since the 1970s, Hunt 9,10 has conducted initial explorations of the hyperspectral properties of various minerals, rocks, and organic matter, focusing on high-resolution spectral reectance characteristics. Recently, Thangavelu et al 11 introduced a hyperspectral-based technique for determining the grade of various iron ore samples.…”