Detection of Visible and Invisible Fecal Contamination on Chicken Carcasses Using Multispectral Fluorescence Imaging and Machine Learning to Mitigate Salmonella Risks

Salmonella, mainly associated with raw poultry, remains a major food safety concern as the number of illnesses has not reduced over the past decade warranting a need for convergent, disruptive approaches. In poultry processing plants, the USDA-FSIS implements a "zero visible fecal tolerance" policy on eviscerated broiler carcasses entering the chiller as a step to reduce the pathogen from cross-contamination. The efficacy of multispectral fluorescence imaging technology to detect visible and invisible fecal matter from different sections of the gastrointestinal tract was assessed on 404 carcasses to enhance automation in processing plants. Results indicated that multispectral imaging combined with data analytics can detect fecal contamination on carcasses but cannot distinguish between fecal sources above 55.40% with a threshold of 50 on large contaminant placed sites. The most significant finding was the ability to detect fecal contamination invisible to the naked eye, and those spots were positive for Salmonella warranting changes in existing practices of detecting fecal matter and rinsing-off carcasses to reduce the pathogen load. To our knowledge, this is the first report to detect invisible fecal contamination on broiler carcasses. An unexpected finding of Salmonella on 100 postchilled carcasses, due to the abrasive action of swabs, indicates a need to improve Salmonella sampling methods in the poultry industry. Improvement over the existing poultry Salmonella sample collection method may provide a better understanding of the levels of Salmonella on raw poultry and aid in developing measures to reduce the pathogen. Validation of laboratory results at a processing facility on 114 swab samples provides a cue for wider investigation. The research provides next steps to the USDA-FSIS and the poultry industry to investigate modern technologies as well as enhance practices to reduce Salmonella in poultry and protect public health.

Authors

Institutions

Publication Details

Journal
Journal of Food Protection
Published
2025-09-01
DOI
https://doi.org/10.1016/j.jfp.2025.100613
Primary Topic
Salmonella and Campylobacter epidemiology
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Detection of Visible and Invisible Fecal Contamination on Chicken Carcasses Using Multispectral Fluorescence Imaging and Machine Learning to Mitigate Salmonella Risks

Moon Il Kim, Jianwei Qin, Сергей Соколов, Luis A. Guzmán et al.
Journal of Food Protection
Salmonella and Campylobacter epidemiology
article

Detection of Visible and Invisible Fecal Contamination on Chicken Carcasses Using Multispectral Fluorescence Imaging and Machine Learning to Mitigate Salmonella Risks

Moon Il Kim, Jianwei Qin, Сергей Соколов, Luis A. Guzmán, Nicholas MacKinnon, Fartash Vasefi, Laura J. Garner, Katherine Paternina-Sierra, Aftab Siddique, Amit Morey, Insuck Baek, Kevin Chao, Diane E. Chan, M. BLACK, Vianca Tashiguano
article en

Abstract

Salmonella, mainly associated with raw poultry, remains a major food safety concern as the number of illnesses has not reduced over the past decade warranting a need for convergent, disruptive approaches. In poultry processing plants, the USDA-FSIS implements a "zero visible fecal tolerance" policy on eviscerated broiler carcasses entering the chiller as a step to reduce the pathogen from cross-contamination. The efficacy of multispectral fluorescence imaging technology to detect visible and invisible fecal matter from different sections of the gastrointestinal tract was assessed on 404 carcasses to enhance automation in processing plants. Results indicated that multispectral imaging combined with data analytics can detect fecal contamination on carcasses but cannot distinguish between fecal sources above 55.40% with a threshold of 50 on large contaminant placed sites. The most significant finding was the ability to detect fecal contamination invisible to the naked eye, and those spots were positive for Salmonella warranting changes in existing practices of detecting fecal matter and rinsing-off carcasses to reduce the pathogen load. To our knowledge, this is the first report to detect invisible fecal contamination on broiler carcasses. An unexpected finding of Salmonella on 100 postchilled carcasses, due to the abrasive action of swabs, indicates a need to improve Salmonella sampling methods in the poultry industry. Improvement over the existing poultry Salmonella sample collection method may provide a better understanding of the levels of Salmonella on raw poultry and aid in developing measures to reduce the pathogen. Validation of laboratory results at a processing facility on 114 swab samples provides a cue for wider investigation. The research provides next steps to the USDA-FSIS and the poultry industry to investigate modern technologies as well as enhance practices to reduce Salmonella in poultry and protect public health.

Journal of Food ProtectionVol. 88(10)
Auburn University (US)
Agricultural Research Service
Openalex Percentile: Top 72%
Salmonella and Campylobacter epidemiology
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.