Prediction of raw meat texture and myopathic severity of broiler breast meat with the wooden breast condition by hyperspectral imaging

Authors: LIU, QING - Qingdao Agricultural University; JINGXIN, SUN - Qingdao Agricultural University; Zhuang, Hong; Yoon, Seung; Bowker, Brian; YANG, YI - Beijing Technology And Business University; BIN, PANG - Qingdao Agricultural University

Submitted to: British Poultry Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/14/2025
Publication Date: 3/24/2025
Citation: Liu, Q., Jingxin, S., Zhuang, H., Yoon, S.C., Bowker, B.C., Yang, Y., Bin, P. 2025. Prediction of raw meat texture and myopathic severity of broiler breast meat with the wooden breast condition by hyperspectral imaging. British Poultry Science. https://doi.org/10.1080/00071668.2025.2471450.
DOI: https://doi.org/10.1080/00071668.2025.2471450

Interpretive Summary: The woody breast (WB) condition is a muscle abnormality in broiler fillets and costs the poultry industry millions of dollars annually due to its negative impact on meat quality. The WB meat is generally differentiated by palpable hardness throughout the raw broiler chicken fillets. However, this method is subjective and time-consuming. Poultry researchers and industry are interested in developing a technique that enables a rapid, nondestructive, and specific prediction of the WB condition of broiler fillets. Hyperspectral Imaging (HSI) has emerged as a promising technology for nondestructively predicting meat quality. It simultaneously provides spectral and spatial information on samples. The objective of this study was to investigate the potential of HSI in predicting meat texture traits and the severity of intact raw WB fillets. Our results show that using the full wavelength range of visible and near-infrared spectra of HSI successfully predicts meat texture traits and myopathic severity of raw broiler fillets with the WB condition, with peak count of shear exhibiting the highest predictive ability. Reducing the full wavelengths to key wavelengths shows comparable predictive performance. Our study demonstrates that HSI could be a potential objective and efficient technique in identifying the WB condition in broiler fillets.

Technical Abstract: This research explored the potential of hyperspectral imaging (HSI) to predict meat texture and the wooden breast (WB) condition in intact raw chicken breast fillets, categorized as normal, moderate WB, and severe WB. The Meullenet-Owens Razor Shear (MORS) measurement was employed to characterize meat texture traits, including force, energy, and peak count. Significant differences in MORS force, energy, and peak count were observed between normal and severe WB fillets, while no distinctions were noted in meat texture traits between normal and moderate WB fillets. Utilizing the full wavelength range of visible and near-infrared (Vis-NIR) spectra, partial least square regression (PLSR) models successfully predicted meat texture traits, with MORS peak count exhibiting the highest predictive ability (Rp = 0.915 and RMSEp = 2.26). Key wavelengths were identified by the regression coefficient (RC) method, highlighting their significance in characterizing meat texture. Subsequent PLSR models based on these key wavelengths demonstrated comparable predictive performance to the full-wavelength models. Additionally, a linear discriminant analysis (LDA) model, incorporating all key wavelengths, achieved accurate predictions of WB severity, with 84.72% in the calibration set and 77.78% in the prediction set. This model also showcased the potential of HSI in distinguishing WB fillets from normal ones with high accuracy (97.22% in the calibration set and 91.67% in the prediction set). Distribution maps generated using key wavelengths visually depicted variations in meat texture traits and WB severity. This study underscores the efficacy of HSI technology in predicting meat texture and WB severity in raw chicken breast fillets.