Computed tomography has improved precision for prediction of intramuscular fat percent in the M. longissimus thoracis et lumborum in cattle compared to manual grading

The application of computer vision systems in meat science and industry - A review

Computer vision systems (CVS) are applied to macro- and microscopic digital photographs captured using digital cameras, ultrasound scanners, computer tomography, and wide-angle imaging cameras. Diverse image acquisition devices make it technically feasible to obtain information about both the external features and internal structures of targeted objects. Attributes measured in CVS can be used to evaluate meat quality. CVS are also used in research related to assessing the composition of animal carcasses, which might help determine the impact of cross-breeding or rearing systems on the quality of meat. The results obtained by the CVS technique also contribute to assessing the impact of technological treatments on the quality of raw and cooked meat. CVS have many positive attributes including objectivity, non-invasiveness, speed, and low cost of analysis and systems are under constant development an improvement. The present review covers computer vision system techniques, stages of measurements, and possibilities for using these to assess carcass and meat quality.

Objective measurement technologies for transforming the Australian & New Zealand livestock industries

This paper introduces the special edition of Meat Science focused upon the development, calibration and validation of technologies that measure traits influencing meat eating quality, or carcass fat and lean composition. These papers reflect the combined research efforts of groups in Australia, through the Advanced Livestock Measurement Technologies project, and New Zealand through AgResearch. We describe the various technologies being developed, how these devices are being trained upon common gold-standard measurements, and how their outputs are being simultaneously integrated into existing industry systems. We outline how this enhances the industry uptake and adoption of these technologies, and how this is further accelerated by education programs and strategic industry investment into their commercialisation.

Prediction of dressing percentage, carcass characteristics and meat yield of goats, and implications for live assessment and carcass-grading systems

Abstract Context Dressing percentage (DP) and meat yield (MY) predictions using live assessments and carcass measurements enable objective valuation of animals and their carcasses. We hypothesised that distribution of goat carcass tissues affects predictive value of live body condition scoring (CS) methods and carcass measurements for these traits. Aims The present paper aimed to assess the value of CS methods for prediction of DP and MY and of carcass measurements for prediction of MY. Methods Correlation and regression analyses from a dataset (n = 1014 goats) highly heterogeneous for factors influencing DP and MY were used to assess (1) the value of live-goat assessments and classifications, including five CS methods, age (dentition), liveweight (LW), sex, fleece characteristics and breed or genotype to predict DP and MY, and (2) the value of hot standard carcass weight (HSCW) and carcass GR (soft tissue over the 12th rib) tissue depth, eye-muscle depth and eye-muscle area to predict MY. Key results Among kids, LW accounted for 1% (residual standard deviation of 2.6%) of variation in DP, 22% (2.3%) in MY (% LW) and 34% (2.5%) in MY (% HSCW). LW plus the best CS method accounted for 24% (2.3%) of variation in DP, 58% (1.7%) in MY (% LW) and 61% (2.0%) in MY (% HSCW). Among all goats, LW plus CS accounted for up to 21% (3.2%), 39% (2.1%) and 45% (2.2%) of variation in these traits. Regression models that included age, sex, fleece type, breed or genotype, LW and CS accounted for 67% (2.5%), 72% (1.9%) and 72% (2.1%) of variation in DP, MY (% LW) and MY (% HSCW). Among carcass measurements, HSCW plus eye-muscle depth had best predictive value, accounting for 61% (2.3%) of variation in MY (% HSCW) for kids and 40% (2.9%) for all goats. Conclusions The body condition-score methods that best relate to DP and MY (% LW or % HSCW) assessed the shape of M. longissimus lumborum (eye muscle) in the lumbar region, which relates to muscularity of goats, rather than subcutaneous fat depth such as assessed at the GR-site. Implications The results guide potential targets for future developments in live-goat assessment, carcass classification and grading, and trading languages underpinned by value-based marketing.

Association between visual marbling score and chemical intramuscular fat with camera marbling percentage in Australian beef carcasses

This study assessed the precision and accuracy in the prediction of chemical intramuscular fat (IMF%), Meat Standards Australia (MSA) marbling score and AUS-MEAT eye-muscle area (EMA) using Meat Imaging Japan (MIJ) prototype camera systems. Eleven carcass datasets from the Beef Information Nucleus (BIN) project were compiled with carcass grading, IMF% and camera data. Camera prediction of IMF%, MSA marbling score and EMA was assessed using a leave-one-out cross validation method. There was an association between MIJ mirror and MIJ-30 camera traits and IMF%, MSA marbling score and EMA. However, for both prototypes precision varied for IMF% (R² = 0.4-0.5, RMSECV = 1.5-1.6%), MSA marbling (R² = 0.3-0.5, RMSECV = 57.5-59.3) and EMA (R² = 0.7-0.6, RMSECV = 4.1-5.8 cm²). Accuracy also fluctuated with average bias values of 1.7-1.8%, 45.8-40.0 units and 3.8-4.1 cm² for IMF%, MSA marbling score and EMA respectively. Key differences between carcass and camera traits and processing factors affecting the grading site are likely to have contributed to this variation.

Prediction of consumer palatability in beef using visual marbling scores and chemical intramuscular fat percentage

With development of objective technologies that can predict chemical intramuscular fat percentage (IMF%), there is a need to understand the relationships between existing marbling traits, IMF% and eating quality. This study utilised historical carcass data (n = 9641 observations) from the Meat Standards Australia (MSA) industry research dataset and included MSA grading data, chemical IMF% data and weighted composite eating quality scores (MQ4). Several analyses were performed to assess the prediction of MQ4 by MSA marbling, M. longissimus thoracis et lumborum (striploin) IMF% and cut specific IMF%. Results demonstrated that there was similar precision between chemical IMF% (R² = 0.32, RSE = 11.8) and MSA marbling (R² = 0.28, RSE = 11.9) in the prediction of grilled 14 day aged striploin MQ4, with similar results across other cut by cook by days aged combinations. These results support the development of objective technologies that predict chemical IMF% in parallel with MSA marbling for carcass grading and the prediction of eating quality.

Research in Beef Tenderness and Palatability in the Era of Big Data

For decades, research has focused on predicting beef palatability using muscle biochemical traits, and various biomarkers. In these approaches, a precise definition of the variable to predict (tenderness assessed by panelists, untrained consumers, or shear force), and repeatability of the measurements are crucial for creating significant data resources for the derivation of robust predictive models, and rigorous validation testing. This “big data” approach also requires careful definition of traits and transparent principles for data sharing and management. As in other fields, meat science researchers should improve the Findability, Accessibility, Interoperability, and Reuse of data (known as the FAIR principles). Furthermore, with the rapid evolution of new measurement technologies, the traits that they measure must be consistently described, enhancing our ability to integrate these new measurements into existing description systems. For beef, strategic choices have been made in order to consider real consumers’ expectations, not well estimated correctly by lab approaches. This strategy has been successfully developed in Australia, which set up the “Meat Standards Australia” grading scheme, now partly adopted by the beef industry. The ambitions of the International Meat Research 3G Foundation is to develop beef ontology, to set up an international database with a huge number of consumers’ scores related to beef palatability and collected according to standard protocols. The foundation also aims to support the beef industry by offering an international predictive model of beef palatability, flexible enough to take into account any local livestock characteristics or regional consumer specificity. This approach is supported by the United Nations Economic Commission for Europe (UNECE), which is promoting development of regulations and norms, technical cooperation and exchange of best expertise and practices. This will substantially improve the transparency of data flow and price signaling between all participants of the value chain, from beef producers through to consumers at retail.