Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #391033

Research Project: Advancement of Sensing Technologies for Food Safety and Security Applications

Location: Environmental Microbial & Food Safety Laboratory

Title: Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

item GORJI, HAMED - University Of North Dakota
item SHAHABI, SEYED - University Of North Dakota
item SHARMA, AKSHAY - State University Of New York (SUNY)
item TAMDE, LUCAS - University Of Minnesota
item HUSARIK, KAYLEE - University Of North Dakota
item Qin, Jianwei - Tony Qin
item Chan, Diane
item BAEK, INSUCK - Orise Fellow
item Kim, Moon
item MACKINNON, NICHOLAS - Collaborator
item MORRO, JEFFERY - Collaborator
item SOKOLOV, STANISSALV - Collaborator
item AKHBARDEH, ALIREZA - Collaborator
item VASEFI, FARTASH - Collaborator
item TAVAKOLIAN, KOUHYAR - University Of North Dakota

Submitted to: Nature Scientific Reports
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/25/2022
Publication Date: 2/14/2022
Citation: Gorji, H.T., Shahabi, S.M., Sharma, A., Tamde, L.Q., Husarik, K., Qin, J., Chan, D.E., Baek, I., Kim, M.S., Mackinnon, N., Morro, J., Sokolov, S., Akhbardeh, A., Vasefi, F., Tavakolian, K. 2022. Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses. Nature Scientific Reports. 12:2392.

Interpretive Summary: Animal fecal matter and ingesta can host bacterial pathogens such as E. coli and Salmonella, which are a potential contaminant source for various meat products. Detection of fecal contamination on meat carcasses is important to reduce food safety risks and foodborne diseases to the consumers. In this study, a contamination, sanitization inspection and disinfection (CSI-D) handheld imaging device, which was developed and commercialized based on an ARS patented technology, was used to collect fluorescence images from beef and sheep carcasses in three meat processing facilities in North Dakota. State-of-the-art deep learning algorithms were developed to segment and identify areas of the fecal residues in the fluorescence images. The results demonstrated that the clean and fecal contaminated carcasses can be differentiated with an approximate accuracy of 97%. The combination of the CSI-D handheld imaging and deep learning techniques would benefit the meat industry and the regulatory agencies (e.g., USDA FSIS and FDA) in ensuring and enforcing the food safety standards for the meat and related products.

Technical Abstract: Food safety and foodborne diseases are significant global public health concerns, and billions of people throughout the world are at risk. Meat and poultry have been a key component of human nutrition and can be contaminated by pathogens like E. coli and salmonella. Since animal fecal matter and ingesta can host these pathogens, detection of contaminated regions on meat surfaces is crucial. Fluorescence imaging technology has proven its potential for the detection of fecal residue. This study investigated the use of fluorescence imaging and state-of-the-art deep learning algorithms for detecting and segmenting areas of fecal matter in images of carcasses. An EfficientNet-B0 was employed first to determine which meat surface images showed fecal contamination, and then U-Net was used to precisely segment the areas of contamination. The model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discrimination between clean and contaminated carcass images, and provided image segmentation of fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can be used to improve food safety assurance.