Prediction of Carcass Composition and Meat and Fat Quality Using Sensing Technologies: A Review

Abstract

Consumer demand for high-quality healthy food is increasing,  thus meat processors require the means toassess these rapidly, accurately, and inexpensively. Traditional methods forquality assessments are time-consuming, expensive, invasive, and have potentialto negatively impact the environment. Consequently, emphasis has been put onfinding non-destructive, fast, and accurate technologies for productcomposition and quality evaluation. Research in this area is advancing rapidlythrough recent developments in the areas of portability, accuracy, and machinelearning. The present review, therefore, critically evaluates and summarizes developmentsof popular non-invasive technologies (i.e., from imaging to spectroscopicsensing technologies) for estimating beef, pork, and lamb composition andquality, which will hopefully assist in the implementation of thesetechnologies for rapid evaluation/real-timegrading of livestock products in the nearfuture.

Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview

“… Liseune et al (2021) were able to successfully create a DL model able to predict a cow’s lactation curve based on the historical sequence of milk yield, as well as reproduction and health issues that occurred in the previous cycle. In the meat industry, developments have been made in the prediction of carcass composition while the animal is still alive through sensing methodologies (computed tomography, dual-energy X-Ray absorptiometry and CV) ( Leighton et al, 2022 ).…”

“…Food quality : in a review regarding sensing technologies used to evaluate carcass composition and quality of meat and fat, Leighton et al (2022) pointed out that CV systems have many applications in this area of expertise, as seen in Pinto et al (2023) , where a model capable of classifying different intramuscular fat patterns in the ribeye area was trained, providing an automatic assessment to meat marbling scoring. Moreover, in order to guarantee milk quality and safety, Lima et al (2022) developed a high performance process to detect milk adulteration with cheese whey through Fourier-transform infrared spectroscopy associated with DL techniques.…”

Aplicación de la Imagen de Resonancia Magnética (IRM) al análisis morfológico no destructivo de piezas cárnicas. Una aproximación a la selección de perniles

“…En este contexto, tanto para la estimación del contenido graso, como para la detección de alteraciones y lesiones, la industria cárnica recurre a distintas técnicas no destructivas o mínimamente invasivas (Pérez-Santaescolástica et al, 2019), como las basadas en el uso de ultrasonidos (Contreras et al, 2021), la espectroscopía de infrarrojo cercano (Kademi et al, 2019), la imagen hiperespectral (Gou et al, 2013), o el empleo de rayos X, entre las que se encuentra también la tomografía computerizada (de Prados et al, 2015) y las recientes técnicas de absorciometría de rayos X de energía dual (Dual-energy X-ray absorptiometry, DXa) (Leighton et al, 2022).…”

Impact of chilling rates on beef quality; the potential of DEXA to predict fat content; and the genomic breed traceability of certified Angus beef sold in Brazil

“…Thus, non-destructive, and objective methods for evaluating carcasses and meat offer enhancements to existing commercial subjective grading, which is susceptible to biases. The adoption of technologies based on X-ray (Calnan et al, 2021), nuclear magnetic resonance (Bernau et al, 2015), video image analysis (Hopkins et al, 2004), ultrasound (Aass et al, 2006), bioelectric impedance (Leighton et al, 2022;Zollinger et al, 2010), and spectroscopy (Kombolo-Ngah et al, 2023) have been evaluated for predicting marketable attributes such as yield, eating quality attributes, and carcass dimensions .…”