Computer image analysis for prediction of carcass composition from cross-sections of Japanese Black steers

An open-access computer image analysis (CIA) method to predict meat and fat content from an android smartphone-derived picture of the bovine 5th-6th rib

Marbling and rib composition are important attributes related to carcass yields and values, beef quality, consumer satisfaction and purchasing decisions. An open-access computer image analysis method based on a fresh beef rib image captured under nonstandardized and uncontrolled conditions was developed to determine the intramuscular, intermuscular and total fat content. For this purpose, cross-section images of the 5th-6th rib from 130 bovine carcasses were captured with a Galaxy S8 smartphone. The pictures were analyzed with a program developed using ImageJ open source software. The 17 processed image features that were obtained were mined relative to gold standard measures, namely, intermuscular fat, total fat and muscles dissected from a rib and weighed, and intramuscular fat content (IMF - marbling) determined by the Soxhlet method. The best predictions with the lowest prediction errors were obtained by the sparse partial least squares method for both IMF percent and rib composition and from a combination of animal and image analysis features captured from the caudal face of the 6th rib captured on a table. These predictions were more accurate than those based on animal and image analysis features captured from the caudal face of the 5th rib on hanging carcasses. The external-validated prediction precision was 90% for IMF and ranged from 71 to 86% for the total fat, intermuscular and muscle rib weight ratios. Therefore, an easy, low-cost, user-friendly and rapid method based on a smartphone picture from the 6th rib of bovine carcasses provides an accurate method for fat content determination.

Simple spot method of image analysis for evaluation of highly marbled beef

The simple method of evaluating highly marbled beef was examined by image analysis. The images of the cross section at the 6 to 7th rib were obtained from 82 carcasses of Wagyu cattle. By using an overall trace method, the surrounding edges of the longissimus thoracis and three muscles were traced automatically and manually with image analysis. In a spot method, 3 to 5 locations (2.5 or 3.0 cm in diameter) for each muscle were rapidly selected with no manual trace. The images were flattened, binarized, and the ratio of fat area to muscle area was determined. The correlation coefficients for marbling between different muscles, and between the overall trace and the spot methods were 0.55 to 0.81 between different muscles and 0.89 to 0.97, respectively. These results suggested that the simple spot method is speedy and almost as useful as the overall trace method as a measuring technique for beef marbling in loin muscles, especially for highly marbled beef.

Accuracy of body measurements using digital image analysis in female Holstein calves

The objective of this study was to determine the accuracy of body measurements (BM) in Holstein female calves using digital image analysis. BM including body length, wither height, chest depth, hip height, and hip width of calves were recorded by stick and tape measurements at birth, weaning and 24 weeks of age. Then photos of calves were taken while calves were standing in a squeeze chute by a digital camera and were analysed by image analysis software to obtain BM of each calf from the image in centimetres. After comparing the actual and predicted BM, the accuracy was determined as 71, 97 and 99% for body length, 69, 87 and 99% for wither height, 43, 98 and 99% for chest depth, 74, 99 and 99% for hip height and 53, 99 and 98% for hip width at birth, weaning and 24 weeks of age, respectively. The difference between actual and predicted BM was significant at birth (P < 0.01). Although there were numerical differences between actual and predicted BM, the differences were not significant at weaning and 24 weeks of age (P > 0.01). According to these results, the BM estimation of Holstein female calves using digital image analysis produced high prediction accuracy at weaning and 24 weeks of age, but not at birth. The data presented in this study indicate that the digital image analysis provides very close agreement and reality for prediction of BM of Holstein female calves.

Genetic correlations among carcass cross-sectional fat area ratios, production traits, intramuscular fat, and serum leptin concentration in Duroc pigs

Animals accumulate fat in tissues as subcutaneous, intermuscular, intramuscular, and abdominal fat. Genetic interrelationships of respective fat depositions, however, have not been examined in depth. This study estimated genetic parameters for subcutaneous, intermuscular, and abdominal fat areas of 545 Duroc purebred pigs slaughtered at 105 kg of BW. Measurements were obtained using an image analysis system for positions between the 5th and the 6th thoracic vertebra (56TV), at half body length (HBL), and at the last thoracic vertebra (LTV) of the carcass. Moreover, serum leptin, which is a hormone product that is synthesized and predominantly expressed by adipocytes, was measured to determine if serum concentrations of leptin are useful as physiological predictors of fat accumulation in pigs. The heritability estimate of all fat area percentage at the HBL (0.70 +/- 0.03) was significantly greater than at the 56TV (0.53 +/- 0.03) or the LTV (0.55 +/- 0.04). Furthermore, the heritability estimate of subcutaneous fat areas at the HBL (0.71 +/- 0.04) was greater than at the 56TV (0.56 +/- 0.04) or LTV (0.60 +/- 0.03). Moreover, high heritabilities were estimated for ultrasound backfat thickness (BF; 0.72 +/- 0.03) on the left side at the position of HBL, intramuscular fat content of the loin (0.51 +/- 0.03), the seam fat score (SFS; 0.49 +/- 0.04), and the serum leptin concentration (0.62 +/- 0.05). Increased genetic correlations of BF with the fat area percentage of subcutaneous fat and all fat at 56TV (0.90 +/- 0.03 and 0.91 +/- 0.03), at HBL (0.88 +/- 0.03 and 0.94 +/- 0.01), and at LTV (0.88 +/- 0.03 and 0.90 +/- 0.02) were estimated. The genetic correlations of serum leptin concentration with the percentage of subcutaneous fat area and all fat areas at each position were also high (0.72 to 0.82 and 0.83 to 0.84, respectively). These results suggest that BF and leptin are good indicators of selection for decreasing fat deposition. Increased genetic correlation of the SFS with intermuscular fat area at 56TV (0.74) suggests that SFS is an effective indicator for decreasing intermuscular fat. The genetic correlation between the leptin concentration and feed conversion ratio was high (0.75 +/- 0.04). Results of this study indicate that the combination of BF and serum leptin concentration is a valuable indicator that can be incorporated into selection programs to improve carcass quality and feed efficiency in pigs.