Detection of Woody Breast Condition in Broiler Breast Fillets Using Light Scattering Imaging

Abstract

Listen

Translate article

HighlightsBroadband light scattering images were acquired from broiler breast fillets affected with woody breast (WB).Both deep-learning-based and hand-crafted features were extracted from scattering images for model development.The hand-crafted scattering image features performed better in differentiating normal from WB-affected samples.An overall accuracy of 92.3% was achieved by the model based on selected hand-crafted scattering features.Abstract. Muscular myopathies such as woody or wooden breast, which impair the eating quality and marketability of poultry products, are threatening the profitability of poultry industries worldwide, with an estimated annual loss exceeding $500 million for the United States (U.S.) poultry industry. WB-affected fillets are characterized by abnormal tissue hardness and muscle rigidity with varying degrees of severity. The assessment of WB conditions at processing facilities currently relies on tactile palpation combined with a visual examination by trained personnel. This approach is subjective, labor-intensive, costly, and may induce contamination due to physical contact. Optical imaging technology offers a promising alternative for objective and non-invasive quality assessment of broiler meat. This study presents a novel investigation of light scattering imaging (LSI) that captures light-scattering characteristics of meat tissues for the detection of WB conditions in broiler breast fillets. Broadband scattering images, induced under the illumination of a highly focused broadband light beam, were acquired from broiler meat samples. Two types of image features, i.e., (1) deep-learning-based and (2) hand-crafted scattering features, were extracted for building classification models using regularized linear discriminant analysis to differentiate samples into two categories, i.e., “Normal” (no WB) and “Defective” (WB-affected). Deep-learning-based features yielded an overall classification accuracy of 80.4%, while an accuracy of 91.7% was obtained by hand-crafted scattering features, representing a significant improvement of 11.3% (P < 0.01). Furthermore, feature reduction approaches, including MRMR (minimum redundancy maximum relevance) and PCA (principal component analysis), were conducted to reduce the model complexity, leading to a further accuracy improvement to 92.3% with the top-ranked 65 features identified by MRMR and 25 principal components (PCs), respectively. This study has demonstrated the LSI technique is promising for WB assessment of broiler breast meat. Keywords: Light scattering, Machine learning, Optical imaging, Poultry, Woody breast.