Predicting carcass tissue composition in Blackbelly sheep using ultrasound measurements and machine learning methods.

This study aimed to predict Blackbelly sheep carcass tissue composition using ultrasound measurements and machine learning models. The models evaluated were decision trees, random forests, support vector machines, and multi-layer perceptrons and were used to predict the total carcass bone (TCB), total carcass fat (TCF), and total carcass muscle (TCM). The best model for predicting the three parameters, TCB, TCF, and TCM was random forests, with mean squared error (MSE) of 0.31, 0.33, and 0.53; mean absolute error (MAE) of 0.26, 0.29, and 0.53; and the coefficient of determination (R2) of 0.67, 0.69, and 0.76, respectively. The results showed that machine learning methods from in vivo ultrasound measurements can be used as determinants of carcass tissue composition, resulting in reliable results.

Estimation of Carcass Tissue Composition from the Neck and Shoulder Composition in Growing Blackbelly Male Lambs.

This study was designed to develop predictive equations estimating carcass tissue composition in growing Blackbelly male lambs using as predictor variables for tissue composition of wholesale cuts of low economic value (i.e., neck and shoulder). For that, 40 lambs with 29.9 ± 3.18 kg of body weight were slaughtered and then the left half carcasses were weighed and divided in wholesale cuts, which were dissected to record weights of fat, muscle, and bone from leg, loin, neck, rib, and shoulder. Total weights of muscle (CM), bone (CB) and fat (CF) in carcass were recorded by adding the weights of each tissue from cuts. The CM, CF and CB positively correlated (p < 0.05; 0.36 ≤ r ≤ 0.86), from moderate to high, with most of the shoulder tissue components, but it was less evident (p ≤ 0.05; 0.32≤ r ≤0.63) with the neck tissue composition. In fact, CM did not correlate with neck fat and bone weights. Final models explained (p < 0.01) 94, 92 and 88% of the variation observed for CM, CF and CB, respectively. Overall, results showed that prediction of carcass composition from shoulder (shoulder) tissue composition is a viable option over the more accurate method of analyzing the whole carcass.