As researchers look to improve the reliability and efficiency of carcass processing, technology is at the forefront of their efforts.
This was evident in Beef2026 open day At Teagasc Grange this week, where Agriland I heard how new technological developments are being tested to improve the carcass grading process.
According to researchers, the beef processing sector has fallen behind poultry Pork is innovating due to carcass challenges, such as larger size and greater variation between carcasses of different breeds.
Meat Technology Ireland (MTI), a major industry-led technology hub hosted by Teagasc, has placed a significant focus on meat digitization research into computer vision systems and artificial intelligence technologies.
talking to Agriland At the event, Teagasc Research Officer, Jingjing Liu, discussed how these technologies are often adapted from medical fields and tested to determine their feasibility for use in the beef sector.
Old vs. new
Current vision techniques rely primarily on color and depth information but often cannot provide detailed characterization of the carcass at the tissue level.
X-ray systems can provide internal composition information, but require specialized infrastructure that most small and medium processors do not have.
Visible near-infrared spectroscopy (V-NIS) is a technique that in layman’s terms means measuring how something interacts with light and measuring the wavelengths produced when light hits it. It does not cause damage to the carcass and is relatively cost-effective.
In one study, MTI combined V-NIS with several machine learning techniques and used it to differentiate more than 300 tissue types (e.g. muscle, fat, marrow, bone, cartilage, tendon).
The results showed a clear ability to distinguish between muscle, fatty and spinal tissue, while an overlap occurred where ligaments, tendons and other similar tissues were analyzed for their similar chemical composition.
The study showed that some machine learning models worked better.
When the V-NIS was replaced by the more accurate near-infrared spectrometer, this resulted in an overall classification accuracy of 100%.
This demonstrates the great potential of combining these techniques to improve carcass characterization.
Artificial Intelligence (AI) It will play a role in future classification systems.
Experiments using two deep learning frameworks analyzed 118 cadavers. The models were trained to identify large features (the gyrus, ribcage, and diaphysis bone) and smaller, more complex features such as individual ribs.
Average accuracy for large structures ranged from 94-97%, but decreased to between 78-92.4% for small features.
Computed tomography (CT) is the gold standard for determining lean meat content in a carcass. It uses rotating X-rays and uses computer algorithms to enable differentiation and identification of tissues.
Although CT and 3D scanning techniques are time consuming, they are valuable in determining diversity in carcasses, and when used in conjunction with training in new techniques.
EUROP Network Challenge
Teagasc also pointed to a 2018 study of consumer experiences in four European countries, which found that 19% of sirloin steaks, 25% of rump, and 53% of topside cuts were rated as unsatisfactory.
According to the researchers, this discrepancy undermines consumer confidence, who cannot predict the quality of eating at the point of purchase and may experience different levels of satisfaction despite paying similar prices.
The European beef carcass grading system, the EUROP network, was introduced in 1981 and continues to dominate carcass grading and pricing throughout the EU.
However, its importance has diminished as the beef industry increasingly relies not only on overall carcass characteristics but also on the eating quality of individual prime cuts, the researchers said.
In response to similar challenges, many international beef grading systems have incorporated attributes related to quality as well as salable meat production.
The systems of the United States, Japan, Korea, and Australia all include marbling in the carcass classification.
According to the researchers, the “most consumer-oriented and scientifically validated approach” is the Meat Standards Australia (MSA), developed since the 1990s, which includes factors such as hanging time, muscle pH and hump height, in giving each carcass an eating quality score.
Meanwhile, rapid evaporation ionization mass spectrometry (REIMS) has shown great potential for online beef quality prediction.
It works by pointing a hot surgical knife at the surface of the meat, creating a mist that is then analyzed by a mass spectrometer creating a lipid (fatty) fingerprint that acts as a guide to quality.
REIMS achieved 99% accuracy in assessing whether or not a consumer likes the flavor of meat.
Since tenderness is a trait highly valued by consumers, predictability of quality is essential in minimizing negative experiences with beef products.
Commenting on the challenges of REIMS, the researchers noted how infrastructure is a major concern, as mass spectrometry is not possible on the majority of small and medium processors.
They noted the need for continued research to identify the best technologies, which are simple and effective and can be deployed on a large scale.
These technologies, when introduced at scale, would help address labor shortages, improve carcass grading accuracy, and reduce waste and consumer dissatisfaction.
Further details of the research presented at BEEF2026 on this topic and a wide range of other topics related to beef production are available at Agriland‘s BEEF2026 Knowledge Center.
