Automated body condition scoring of dairy cows using 3-dimensional feature extraction from multiple body regions

Machine vision technology has been used in automated body condition score (BCS) classification of dairy cows. The current vision-based classifications use information acquired from a limited number of body regions of the cow. Our study aimed to improve automated BCS classification by including multiple body condition–related features extracted from 3 viewpoints in 8 body regions. The data set of this study included 44 lactating cows with their BCS evenly distributed over the scale of BCS from 1.5 to 4.5 units. The body images of these cows were recorded over 2 consecutive days using 3-dimensional cameras positioned to view the cow from the top, right side, and rear. Each image was automatically processed to identify anatomical landmarks on the body surface. Around these anatomical landmarks, the bony prominences and body surface depressions were quantified to describe 8 body condition–related features. A manual BCS of each cow was independently assigned by 2 trained assessors using the same predefined protocol. With the extracted features as inputs and manual BCS as the reference, we built a nearest-neighbor classification model to classify BCS and obtained an overall classification sensitivity of 0.72 using a 10-fold cross-validation. We conclude that the sensitivity of automated BCS classification has been improved by expanding the selection of body condition–related features extracted from multiple body regions.     

Cow body shape and automation of condition scoring

The feasibility of including a body shape measure in methods for automatic monitoring of body reserves of cattle was evaluated. The hypothesis tested was that the body shape of a fatter cow is rounder than that of a thin cow and, therefore, may better fit a parabolic shape. An image-processing model was designed that calculates a parameter to assess body shape. The model was implemented, and its outputs were validated against ultrasonic and thermal camera measurements of the thickness of fat and muscle layers, and manual body condition scoring of 186 Holstein-Friesian cows. The thermal camera overcomes some of the drawbacks of a regular camera; the hooks and the tailhead nadirs of a thin cow diverged from the parabolic shape. The correlation between thermal camera's measurements and fat and muscle thickness was 0.47. Mean body condition scorings were 2.18, 2.15, and 2.23, with no significant difference found across the assessment methods. Further research is needed to achieve fully automatic, accurate body condition scoring.     

Potential for estimation of body condition scores in dairy cattle from digital images

Body condition scoring, an indirect measure of the level of subcutaneous fat in dairy cattle, has been widely adopted for research and field assessment or for management purposes on farms. The feasibility of utilizing digital images to determine body condition score (BCS) was assessed for lactating dairy cows at the Scottish Agricultural College Crichton Royal Farm. Two measures of BCS were obtained by using the primary systems utilized in the United Kingdom (UK-BCS) and the United States (USBCS). Means were 2.12 (±0.35) and 2.89 (±0.40), modes were 2.25 and 2.75, and ranges were 1.0 to 3.5 and 1.5 to 4.5 for the UKBCS (n = 2,346) and USBCS (n = 2,571), respectively. Up to 23 anatomical points were manually identified on images captured automatically as cows passed through a weigh station. Points around the hooks were easier to identify on images than points around pins and the tailhead. All identifiable points were used to define and formulate measures describing the cow's contour. For both BCS systems, hook angle, posterior hook angle, and tailhead depression were significant predictors of BCS. When the full data set testing only the angles around the hooks was used, 100% of predicted BCS were within 0.50 points of actual USBCS and 92.79% were within 0.25 points; and 99.87% of predicted BCS were within 0.50 points of actual UKBCS and 89.95% were within 0.25 points. In a reduced data set considering only observations in which the tailhead depression angle was available, adding the tailhead depression to models did not improve model predictions. The relationships of the calculated angles with USBCS were stronger than those with UKBCS. This research demonstrates the potential for using digital images for assessing BCS. Future efforts should explore ways to automate this process by using a larger number of animals to predict scores accurately for cows across all levels of body condition.     

Associations among body condition score, body weight, somatic cell count, and clinical mastitis in seasonally calving dairy cattle

The objective of this study was to determine if an association existed among body condition score (BCS), body weight (BW), and udder health, as indicated by somatic cell score (SCS) and cases of clinical mastitis (CM). The data consisted of 2,635 lactations from Holstein-Friesian (n = 523) and Jersey (n = 374) cows in a seasonal calving pasture-based research herd between the years 1986 and 2000, inclusive. Increased BCS at calving was associated with reduced SCS in first- and second-parity cows, and greater SCS in cows of third parity or greater. This relationship persisted for most BCS traits throughout lactation. Body weight was positively associated with SCS, although the effect was greater in Jersey cows than in Holstein-Friesians. Increased BCS and BW loss in early lactation were associated with lower SCS and a reduced probability of a high test-day SCC. Body condition score was not significantly related to CM with the exception of a curvilinear relationship between the daily rate of BCS change to nadir and CM in early lactation. Several BW variables were positively associated with a greater likelihood of CM. Nevertheless, most associations with udder health lacked biological significance within the ranges of BCS and BW generally observed on-farm. Results are important in assuring the public that modern dairy systems, where cows are subjected to substantial amounts of BCS mobilization in early lactation, do not unduly compromise cow udder health.     

Holstein-Friesian strain and feed effects on milk production, body weight, and body condition score profiles in grazing dairy cows

Data from 113 lactations across 76 cows between the years 2002 to 2004 were used to determine the effect of strain of Holstein-Friesian (HF) dairy cow and concentrate supplementation on milk production, body weight (BW), and body condition score (BCS; 1 to 5 scale) lactation profiles. New Zealand (NZ) and North American (NA) HF cows were randomly allocated to 1 of 3 levels of concentrate supplementation [0, 3, or 6 kg of dry matter (DM)/cow per d] on a basal pasture diet. The Wilmink exponential model was fitted within lactation (Y_DIM = a + b e(^{−0.05 × DIM)} + c × DIM). The median variation explained by the function for milk yield was 86%, between 62 and 69% for milk composition, and 80 and 70% for BW and BCS, respectively. North American cows and cows supplemented with concentrates had greater peak and 270-d milk yield. Concentrate supplementation tended to accelerate the rate of incline to peak milk yield, but persistency of lactation was not affected by either strain of HF or concentrate supplementation. No significant strain by diet interaction was found for parameters reported. New Zealand cows reached nadir BCS 14 d earlier and lost less BW (22 kg) postcalving than NA cows. Concentrate supplementation reduced the postpartum interval to nadir BW and BCS, and incrementally increased nadir BCS. New Zealand cows gained significantly more BCS (i.e., 0.9 × 10⁻³ units/d more) postnadir than NA cows, and the rate of BCS replenishment increased linearly with concentrate supplementation from 0.5 × 10⁻³ at 0 kg of DM/d to 0.8 × 10⁻³ and 1.6 × 10⁻³ units/d at 3 and 6 kg of DM/d concentrates, respectively. Although there was no significant strain by diet interaction for parameters reported, there was a tendency for a strain by diet interaction in 270-d BCS, suggesting that the effect of concentrate supplementation on BCS gain was, at least partly, strain dependent.     

Associations among patterns in daily body weight, body condition scoring, and reproductive performance in high-producing dairy cows

The objective was to investigate the associations between body condition scores (BCS) and daily body weight (BW) in the first 150 d of lactation (DIM) and reproductive performance in high-producing dairy cows. Data included automated daily BW measurements and BCS of 2,020 Israeli Holstein cows from 7 commercial farms. Individual BW series were smoothed using penalized cubic splines, and variables representing BW patterns were generated. The presence of 7- and 21-d cycles in BW was determined using time-series analysis. Associations between BW and BCS and conception at first artificial insemination (AI) were analyzed using generalized estimating equations. Multivariate survival analysis was used for associations between BW and BCS and the calving-to-first AI interval, first AI-to-conception interval, and calving-to-conception interval. First-parity cows that lost ≥12% and second-parity cows that lost ≥15% of their BW from calving to nadir BW were less likely to conceive at first AI. Cows without 7-d cycles in BW were 1.48 times more likely to conceive at first AI relative to cows with 7-d cycles. The odds of conceiving at first AI increased by 53% for each additional unit in BCS from 40 to 60 DIM. In the multivariate survival analysis, a BCS of ≤2.5 between 40 and 60 DIM, the percentage of BW lost from calving to nadir BW, and a BW loss of ≥7% from calving to 10 DIM were associated with reduced reproductive performance. The presence of 21-d cycles in BW was associated with high reproductive performance in first-parity [odds ratio (OR) = 1.18] and second-parity cows (OR = 1.22). The presence of 7-d cycles in BW was associated with low reproductive performance in first-parity cows (OR = 0.77), but not in older cows. Based on previous findings and on the associations found in this study, we postulate that 21-d cycles are probably related to the sexual cycle and could be used as a proxy for assessing ovarian activity. Variables representing relative BW loss (%) were better predictors for impaired reproductive performance than those representing absolute BW loss (kg) and may be more suitable for estimating individual adaptation to negative energy balance in herds for which automated daily BW is available.     

Relationships between fertility and postpartum changes in body condition and body weight in lactating dairy cows

The relationship between energy status and fertility in dairy cattle was retrospectively analyzed by comparing fertility with body condition score (BCS) near artificial insemination (AI; experiment 1), early postpartum changes in BCS (experiment 2), and postpartum changes in body weight (BW; experiment 3). To reduce the effect of cyclicity status, all cows were synchronized with Double-Ovsynch protocol before timed AI. In experiment 1, BCS of lactating dairy cows (n = 1,103) was evaluated near AI. Most cows (93%) were cycling at initiation of the breeding Ovsynch protocol (first GnRH injection). A lower percentage pregnant to AI (P/AI) was found in cows with lower (≤2.50) versus higher (≥2.75) BCS (40.4 vs. 49.2%). In experiment 2, lactating dairy cows on 2 commercial dairies (n = 1,887) were divided by BCS change from calving until the third week postpartum. Overall, P/AI at 70-d pregnancy diagnosis differed dramatically by BCS change and was least for cows that lost BCS, intermediate for cows that maintained BCS, and greatest for cows that gained BCS [22.8% (180/789), 36.0% (243/675), and 78.3% (331/423), respectively]. Surprisingly, a difference existed between farms with BCS change dramatically affecting P/AI on one farm and no effect on the other farm. In experiment 3, lactating dairy cows (n = 71) had BW measured weekly from the first to ninth week postpartum and then had superovulation induced using a modified Double-Ovsynch protocol. Cows were divided into quartiles (Q) by percentage of BW change (Q1 = least change; Q4 = most change) from calving until the third week postpartum. No effect was detected of quartile on number of ovulations, total embryos collected, or percentage of oocytes that were fertilized; however, the percentage of fertilized oocytes that were transferable embryos was greater for cows in Q1, Q2, and Q3 than Q4 (83.8, 75.2, 82.6, and 53.2%, respectively). In addition, percentage of degenerated embryos was least for cows in Q1, Q2, and Q3 and greatest for Q4 (9.6, 14.5, 12.6, and 35.2% respectively). In conclusion, for cows synchronized with a Double-Ovsynch protocol, an effect of low BCS (≤2.50) near AI on fertility was detected, but change in BCS during the first 3 wk postpartum had a more profound effect on P/AI to first timed AI. This effect could be partially explained by the reduction in embryo quality and increase in degenerate embryos by d 7 after AI in cows that lost more BW from the first to third week postpartum.     

Thin and fat cows,and the nonlinear genetic relationship between body condition score and fertility

Thin and fat cows are often credited for low fertility, but body condition score (BCS) has been traditionally treated as a linear trait when genetic correlations with reproductive performance have been estimated. The aims of this study were to assess genetic parameters for fertility, production, and body condition traits in the Brown Swiss population reared in the Alps (Bolzano-Bozen Province, Italy), and to investigate the possible nonlinearity among BCS and other traits by analyzing fat and thin cows. Records of BCS measured on a 5-point scale were preadjusted for year-season and days in milk at scoring, and were considered positive (1) for fat cows if they exceeded the value of 1 residual standard deviation or null (0) otherwise, whereas positive values for thin cows were imputed to records below −1 residual standard deviation. Fertility indicators measured on first- and second-parity cows were interval from parturition to first service, interval from first service to conception, interval from parturition to conception, number of inseminations to conception, conception at first service, and nonreturn rate at 56 d after first service. Production traits were peak milk yield, lactation milk yield, and lactation length. Data were from 1,413 herds and included 16,324 records of BCS, fertility, and production for first-parity, and 10,086 fertility records for second-parity cows. Animals calved from 2002 to 2007 and were progeny of 420 artificial insemination bulls. Genetic parameters for the aforementioned traits were obtained under univariate and bivariate threshold and censored linear sire models implemented in a Bayesian framework. Posterior means of heritabilities for BCS, fat cows, and thin cows were 0.141, 0.122, and 0.115, respectively. Genetic correlations of body condition traits with contemporary production were moderate to high and were between −0.556 and 0.623. Body condition score was moderately related to fertility in first (−0.280 to 0.497) and second (−0.392 to 0.248) lactation. The fat cow trait was scarcely related to fertility, particularly in first-parity cows (−0.203 to 0.281). Finally, the genetic relationships between thin cows and fertility were higher than those between BCS and fertility, both in first (−0.456 to 0.431) and second (−0.335 to 0.524) lactation. Body condition score can be considered a predictor of fertility, and it could be included in evaluation either as linear measure or as thin cow. In the second case, the genetic relationship with fertility was stronger, exacerbating the poorest body condition and considering the possible nonlinearity between fertility and energy reserves of the cow.     

Association between body condition genomic values and feed intake,milk production,and body weight in French Holstein cows

Body condition score (BCS) offers a good estimate of the amount of stored fat on the body, and its variations can be used as a proxy for energy balance. Many countries have implemented a genomic evaluation of BCS, including France, where estimated breeding values are based on an individual BCS determination during the first lactation. In this article, we investigate the degree to which this genomic estimated breeding value based on a single phenotype record per cow might reflect different profiles of body reserves throughout lactation and be used to predict, and perhaps limit, their mobilization during early lactation. We also investigate whether selection on BCS affects other traits. A data set including 686 lactations of 435 Holstein cows from 3 experimental farms not used in the reference population for genomic evaluation was used to estimate the effects of the BCS direct genomic value (iBCS) on BCS, body weight, feed intake, milk production, and fat and protein contents throughout the lactation period. For each trait, the model included different iBCS regressions and an effect of the direct genomic value of the trait itself when available. It thus appeared that cows with a positive iBCS always had a higher BCS than negative iBCS cows, whatever the lactation stage, and that this difference increased during the first 6 mo to reach a difference of 0.8 point. A similar effect was seen regarding body weight, but it was the opposite for milk production, with negative iBCS cows producing slightly more milk (difference of about 3% over lactation). Feed intake increased slightly faster at the beginning of lactation for cows with positive iBCS. Therefore, iBCS is a promising tool that could help to limit intense mobilization during early lactation. Should feed efficiency be included in the breeding goal, greater attention should be paid to BCS to avoid further body mobilization in early lactation.     

Calving body condition score affects indicators of health in grazing dairy cows

The objectives of this study were to determine the effect of calving body condition score (BCS) on cow health during the transition period in a pasture-based dairying system. Feed inputs were managed during the second half of the previous lactation so that BCS differed at drying off (BCS 5.0, 4.0, and 3.0 for high, medium, and low treatments, respectively: a 10-point scale); feed allowance was managed after cows were dried off, such that the BCS differences established during lactation remained at the subsequent calving (BCS 5.5, 4.5, and 3.5; n = 20, 18, and 19, for high, medium, and low treatments, respectively). After calving, cows were allocated pasture and pasture silage to ensure grazing residuals >1,600 kg of DM/ha. Milk production was measured weekly; blood was sampled regularly pre- and postpartum to measure indicators of health, and udder and uterine health were evaluated during the 6 wk after calving. Milk weight, fat, protein, and lactose yields, and fat content increased with calving BCS during the first 6 wk of lactation. The effect of calving BCS on the metabolic profile was nonlinear. Before calving, cows in the low group had lower mean plasma β-hydroxybutyrate and serum Mg concentrations and greater mean serum urea than cows in the medium and high BCS groups, which did not differ from each other. During the 6 wk after calving, cows in the low group had lower serum albumin and fructosamine concentrations than cows in the other 2 treatment groups, whereas cows in the low- and medium-BCS groups had proportionately more polymorphonucleated cells in their uterine secretions at 3 and 5 wk postpartum than high-BCS cows. In comparison, plasma β-hydroxybutyrate and nonesterified fatty acid concentrations increased linearly in early lactation with calving BCS, consistent with a greater negative energy balance in these cows. Many of the parameters measured did not vary with BCS. The results highlight that calving BCS and, therefore, BCS through early lactation are not effective indicators of functional welfare, with the analyses presented indicating that both low and high BCS at calving will increase the risk of disease: cows in the low group were more prone to reproductive compromise and fatter cows had an increased risk of metabolic diseases. These results are important in defining the welfare consequences of cow BCS.     

The effect of body condition score at calving and supplementation with Saccharomyces cerevisiae on milk production, metabolic status, and rumen fermentation of dairy cows in early lactation

The objective of this study was to examine the effects of live yeast (LY) supplementation and body condition score (BCS, 1-5 scale) at calving on milk production, metabolic status, and rumen physiology of postpartum (PP) dairy cows. Forty Holstein-Friesian dairy cows were randomly allocated to a 2 × 2 factorial design and blocked by yield, parity, BCS, and predicted calving date. Treatments were body condition at calving (low for BCS ≤3.5 or high for BCS ≥3.75; n = 20) and supplementation with LY (2.5 and 10 g of LY/d per cow for pre- and postcalving, respectively; control, no LY supplementation; n = 20). The supplement contained 10⁹ cfu of Saccharomyces cerevisiae/g (Yea-Sacc¹⁰²⁶ TS, Alltech Inc., Nashville, TN). Daily milk yield, dry matter intake, milk composition, BCS, body weight, and backfat thickness were recorded. Blood samples were harvested for metabolite analysis on d 1, 5, 15, 25, and 35 PP. Liver samples were harvested by biopsy for triacylglycerol (TAG) and glycogen analysis on d 7 precalving, and on d 7 and 21 PP. Rumen fluid was sampled by rumenocentesis for all cows on d 7 and 21 PP. Supplementation with LY had no effect on milk yield, dry matter intake, rumen fluid pH, or blood metabolites concentration of dairy cows with high or low BCS at calving. Feeding LY increased rumen acetate proportion and protozoal population, tended to increase liver glycogen, and decreased rumen ammonia nitrogen during early lactation. Over-conditioned cows at calving had greater body reserve mobilization and milk production and lower feed intake, whereas cows with a moderate BCS at calving had greater feed intake, lower concentrations of nonesterified fatty acids and β-hydroxybutyrate, lower liver TAG and TAG:glycogen ratio, and faster recovery from body condition loss. Additionally, the data suggest that concentrations of liver enzymes in blood might be used as an indicator for liver TAG:glycogen ratio. Results indicate that in the case of this experiment, where the control treatment was associated with an acceptable rumen pH, feeding yeast did not significantly improve indicators of energy status in dairy cows.     

Body condition assessment using digital images

This project assessed the ability to assign a body condition score (BCS) to a dairy cow from digital photographs or videos. Images were taken from the rear of the cow at a 0 to 20° angle relative to the tail head. Four observers assigned a BCS to each of 57 cows at a farm visit (live, farm 1) and later from a photograph (photo). Means ± standard deviations of BCS by method and observer were as follows: live = 3.25 ± 0.51, 3.42 ± 0.49, 3.32 ± 0.58, 3.13 ± 0.62; photo = 3.36 ± 0.52, 3.32 ± 0.43, 3.44 ± 0.62, 3.14 ± 0.6 for observers 1 to 4, respectively. Body condition score means differed across observers for live (observer 2 higher and observer 4 lower, compared with observers 1 and 3) and photo methods (observer 3 lower, compared with observers 1, 2, and 3); however, within observer, the mean live BCS did not differ from the mean photo BCS. Correlation coefficients between BCS assigned live and from photos were 0.84, 0.82, 0.82, and 0.90 for observers 1 to 4, respectively. Subsequently, observer 1 visited 2 farms, assigned a live BCS, and digitally photographed 187 cows (56 and 131 cows from farms 2 and 3, respectively). Observers 2, 3, and 4 assigned a BCS from the photographs. Means ± standard deviations of BCS by observer (method) were 1 (live) 3.35 ± 0.55; 2 (photo) 3.33 ± 0.49; 3 (photo) 3.60 ± 0.54; and 4 (photo) 3.26 ± 0.62. The mean BCS for observer 3 was higher and that for observer 4 was lower than for observers 1 and 2. Correlation coefficients between observer 1 and observers 2 through 4 were 0.78, 0.76, and 0.79, respectively. Observer 1 assigned a BCS to 41 cows at a farm visit and 3 wk later assessed the BCS of cows from a video taken at a farm visit by a different individual. Cows were restrained in headlocks at a feed bunk when assessing BCS and for video production. No difference was detected for the mean BCS, for the standard deviation of the mean BCS, or in the distribution of BCS between the live and video assessments. Mean and SD for 17 groups of Holstein cows from 20 farms were used to generate 10,000 random samples of BCS. Groups of 25, 50, 100, and 150 cows were created from the random samples, and estimates of mean BCS were determined by sampling 3 to 80% of the group. Estimates of mean BCS with a sample size of 30% or more from a group of cows fell within the 95% confidence limit of the true mean more than 98% of the time. Digital photographs provide adequate imaging for assessment of BCS. Sampling 30% of a group should be adequate to assess the mean BCS. Video imaging allowed a rapid assessment of BCS but did not permit identification of individual cows.     

Genetic relationships between body condition score and reproduction traits in Canadian Holstein and Ayrshire first-parity cows

The objective of this study was to investigate the genetic relationship between body condition score (BCS) and reproduction traits for first-parity Canadian Ayrshire and Holstein cows. Body condition scores were collected by field staff several times over the lactation in herds from Québec, and reproduction records (including both fertility and calving traits) were extracted from the official database used for the Canadian genetic evaluation of those herds. For each breed, six 2-trait animal models were run; they included random regressions that allowed the estimation of genetic correlations between BCS over the lactation and reproduction traits that are measured as a single lactation record. Analyses were undertaken on data from 108 Ayrshire herds and 342 Holstein herds. Average daily heritabilities of BCS were close to 0.13 for both breeds; these relatively low estimates might be explained by the high variability among herds and BCS evaluators. Genetic correlations between BCS and interval fertility traits (days from calving to first service, days from first service to conception, and days open) were negative and ranged between −0.77 and −0.58 for Ayrshire and between −0.31 and −0.03 for Holstein. Genetic correlations between BCS and 56-d nonreturn rate at first insemination were positive and moderate. The trends of these genetic correlations over the lactation suggest that a genetically low BCS in early lactation would increase the number of days that the primiparous cow was not pregnant and would decrease the chances of the primiparous cow to conceive at first service. Genetic correlations between BCS and calving traits were generally the strongest at calving and decreased with increasing days in milk. The correlation between BCS at calving and maternal calving ease was 0.21 for Holstein and 0.31 for Ayrshire and emphasized the relationship between fat cows around calving and dystocia. Genetic correlations between calving traits and BCS during the subsequent lactation were moderate and favorable, indicating that primiparous cows with a genetically high BCS over the lactation would have a greater chance of producing a calf that survived (maternal calf survival) and would transmit the genes that allowed the calf to be born more easily (maternal calving ease) and to survive (direct calving ease).     

Effects of dry period length and concentrate protein content in late lactation on body condition score change and subsequent lactation performance of thin high genetic merit dairy cows

Improving body condition score of thin cows in late lactation is necessary, because cows that are thin at drying off exhibit decreased fertility postpartum and are at increased risk of disease and of being culled in the subsequent lactation. Offering a diet low in crude protein (CP) content in late lactation may help to improve body condition score (BCS) at drying off, whereas imposing an extended dry period (EDP) has been advocated as another way to increase BCS at calving. To test these hypotheses, 65 thin cows (mean BCS 2.25 at 14 wk precalving) were managed on 1 of 3 treatments between 13 and 9 wk prepartum: normal protein control {NP; grass silage + 5 kg/d of a normal protein concentrate [228 g of CP/kg of dry matter (DM)]}, low protein [LP; grass silage + 5 kg/d of a low-protein concentrate (153 g of CP/kg of DM)], or EDP (cows dried off at 13 wk precalving and offered a grass silage-only diet). Both NP and LP cows were dried off at wk 8 prepartum, after which all cows were offered a grass silage-only diet until calving. After calving, all cows were offered a common diet (supplying 11.1 kg of concentrate DM/cow per day) for 19 wk. Between 13 and 9 wk prepartum, LP cows had lower DM intake, milk yield, and body weight than NP cows. Whereas EDP cows had lower serum β-hydroxybutyrate and fatty acid concentrations than those of NP cows, BCS at wk 9 prepartum did not differ between treatments. Cows on the LP treatment continued to have lower DMI and BW than those of NP and EDP cows between 8 wk prepartum and calving, but only EDP cows had a higher BCS at calving. Treatment did not affect calving difficulty score or calf birth weight. Although all cows were offered a common diet postpartum, cows on the LP treatment had lower DM intake and milk fat + plus protein yield than cows on any other treatment during the 19-wk period postpartum, but we found no differences in any postpartum indicator of body tissue reserves. The treatments imposed from wk 13 to 9 prepartum had no effect on any fertility or health parameters examined postpartum. Extending the dry period for thin cows improved their BCS at calving but did not allow these cows to achieve the target BCS of 2.75, and we found no beneficial effects of this treatment on cow performance postpartum. Offering a lower-protein diet to thin cows in late lactation did not improve BCS at calving above that of cows on a normal protein diet, but had unexplained long-term negative effects on cow performance.     

Automatic monitoring system for individual dairy cows based on a deep learning framework that provides identification via body parts and estimation of body condition score

Body condition score (BCS) is a common tool for indirectly estimating the mobilization of energy reserves in the fat and muscle of cattle that meets the requirements of animal welfare and precision livestock farming for the effective monitoring of individual animals. However, previous studies on automatic BCS systems have used manual scoring for data collection, and traditional image extraction methods have limited model performance accuracy. In addition, the radio frequency identification device system commonly used in ranching has the disadvantages of misreadings and damage to bovine bodies. Therefore, the aim of this research was to develop and validate an automatic system for identifying individuals and assessing BCS using a deep learning framework. This work developed a linear regression model of BCS using ultrasound backfat thickness to determine BCS for training sets and tested a system based on convolutional neural networks with 3 channels, including depth, gray, and phase congruency, to analyze the back images of 686 cows. After we performed an analysis of image model performance, online verification was used to evaluate the accuracy and precision of the system. The results showed that the selected linear regression model had a high coefficient of determination value (0.976), and the correlation coefficient between manual BCS and ultrasonic BCS was 0.94. Although the overall accuracy of the BCS estimations was high (0.45, 0.77, and 0.98 within 0, 0.25, and 0.5 unit, respectively), the validation for actual BCS ranging from 3.25 to 3.5 was weak (the F1 scores were only 0.6 and 0.57, respectively, within the 0.25-unit range). Overall, individual identification and BCS assessment performed well in the online measurement, with accuracies of 0.937 and 0.409, respectively. A system for individual identification and BCS assessment was developed, and a convolutional neural network using depth, gray, and phase congruency channels to interpret image features exhibited advantages for monitoring thin cows.     

Pre-conception energy balance and secondary sex ratio--partial support for the Trivers-Willard hypothesis in dairy cows

According to the Trivers-Willard hypothesis, maternal condition at or around conception affects the secondary sex ratio in mammals. However, there are little or no data available on indicators of maternal condition in dairy cows on the sex of the resultant offspring. A total of 76,607 body condition score (BCS; scale of 1 to 5) records and 76,611 body weight (BW) records from 3,209 lactations across 1,172 cows were extracted from a research database collated from one research herd between 1986 and 2004, inclusive. Exclusion of multiple births and cows with no information before calving (e.g., nulliparous animals) resulted in 2,029 records with BCS and BW observations from the previous calving, and 2,002 and 1,872 lactations with BCS and BW observations at conception and midgestation, respectively. Change in BCS and BW between calving and conception and between conception and midgestation was calculated per lactation. Generalized estimating equations were used to model the logit of the probability of a male calf, in which cow was included as a repeated effect with a first-order autoregressive correlation structure assumed among records within cow. Of the BCS variables investigated, there was a linear relationship between the logit of the probability of a male calf and BCS change between calving and conception, the rate of BCS change over this period (BCS divided by days in milk), and BCS at the calving event immediately before conception. The birth of a bull calf was 1.85 times more likely in cows that lost no BCS from calving to conception compared with cows that lost one BCS unit from calving to conception. This increase in odds was equivalent to a 14% unit increase in the probability of a male calf (from 54 to 68%). The amount of BW lost between calving and conception and the rate of loss affected the sex of the resultant offspring. Less BW loss or greater BW gain between calving and conception was associated with greater likelihood of a male calf. Results suggested a positive effect of pre-conception BCS and BW change on secondary sex ratio, agreeing with the Trivers-Willard hypothesis that females in good physiological condition are more likely to produce male offspring.     

The effect of claw horn disruption lesions and body condition score at dry-off on survivability, reproductive performance, and milk production in the subsequent lactation

The objective of this study was to evaluate the effects of claw horn disruption lesions (CHDL; sole ulcers and white line disease) and body condition score (BCS) at dry-off on survivability, milk production, and reproductive performance during the subsequent lactation. An observational prospective cohort study was conducted on a large commercial dairy in Cayuga County, New York, from September 2008 until January 2009. A total of 573 cows enrolled at dry-off were scored for body condition and hoof trimmed; digits were visually inspected for the presence of CHDL. The BCS data were recategorized into a 3-level variable BCS group (BCSG), with cows with BCS <3 placed in BCSG 1 (n = 113), cows with BCS = 3 placed in BCSG 2 (n = 254), and cows with BCS >3 placed in BCSG 3 (n = 206). Cows in BCSG 2 were 1.35 and 1.02 times more likely to conceive than cows in BCSG 1 and 3, respectively. The cull/death hazard for BCSG 1 cows was 1.55 and 1.47 times higher than for cows in BCSG 2 and BCSG 3, respectively. Milk yield for cows in BCSG 2 (44.6 kg/d, 95% CI 43.4-45.8) was significantly greater than that for cows in BCSG 1 (41.5 kg/d, 95% CI 39.8-43.3). Cows with previous lactation days open ≤91 had 1.6 times higher odds of being classified into BCSG 1 at dry-off; cows with previous lactation mature-equivalent 305-d milk >14,054 kg had a similar 1.6 times higher odds of being classified into BCSG 1. Claw horn disruption lesions were found in 24.4% of the cows (n = 140) at dry-off. Cows without CHDL were 1.4 times more likely to conceive than cows with CHDL. Additionally, lesion cows were 1.7 times more likely to die or be culled than nonlesion cows. Absence of CHDL did not have a significant effect on milk yield. These findings highlight the importance of claw health and BCS at the end of lactation on future survival and performance.     

Describing the body condition score change between successive calvings: a novel strategy generalizable to diverse cohorts

The objective of this study was to explore the derivation of a mathematical model that adequately describes the intercalving body condition score (BCS) profile in dairy cows and is robust and applicable to different animal cohorts. The data used to generate the function were 75,352 daily BCS records across 3,209 lactations in 1,172 cows from a research herd in New Zealand. Mean daily BCS (scale 1 to 10) across all data were plotted and 4 distinct phases were observed. The functional form used to describe the pattern and quantify its features comprised the sum of the 4 phase functions created from intercepts, rates of change, approximate timing of phase transition points, and the sharpness of these transition points in the BCS profile. The generality and applicability of the described model were tested across substrata of BCS at calving and parity. A second data set consisting of a multiyear study comparing cows fed a total mixed ration (TMR) or grazing fresh pasture was compiled from a different research farm. This data set consisted of 4,112 BCS records from 211 lactations on 95 cows. The third data set was a collation of data from another multiyear experiment comparing animal performance under different stocking rates. The data set consisted of 12,414 BCS test-day records on 564 lactations from 287 cows. The presented model is robust and applicable to different animal cohorts, explaining between 29 and 79% of variation depending on the cohort studied. A notable second period of negative energy balance was evident in all grazing cows during midlactation, irrespective of calving BCS, parity, or stocking rate, but did not appear in cows fed TMR. The amount of BCS lost postcalving and nadir BCS were positively correlated with calving BCS, with fatter cows at calving losing more BCS postcalving but remaining at a greater BCS at nadir. Primiparous cows calved at a greater BCS than multiparous cows, as dictated by management protocols, but they failed to regain BCS postnadir as effectively as their multiparous counterparts. Results may highlight the need for preferential feeding of younger cows during late lactation, at least in grazing systems, to ensure that they achieve the required calving BCS at second calving. Cows receiving TMR lost BCS at a slower rate than cows on pasture but for a longer period; the amount of BCS lost between calving and nadir did not differ between the different feeding treatments. Calving BCS declined with increasing stocking rate, and the rates of both loss and gain were negatively affected by stocking rate. The presented model accurately identified biological attributes of the intercalving BCS profile of different groups of cows.     

Effects of body condition score at calving on indicators of fat and protein mobilization of periparturient Holstein-Friesian cows

The objective was to study the effects of body condition score (BCS) at calving on dairy performance, indicators of fat and protein mobilization, and metabolic and hormonal profiles during the periparturient period of Holstein-Friesian cows. Twenty-eight multiparous cows were classed according to their BCS (0 to 5 scale) before calving as low (BCS ≤2.5; n = 9), medium (2.75 ≤ BCS ≤ 3.5; n = 10), and high (BCS ≥3.75; n = 9), corresponding to a mean of 2.33, 3.13, and 4.17 points of BCS, and preceding calving intervals of 362, 433, and 640 d, respectively. Cows received the same diets based on preserved grass to allow ad libitum feed intake throughout the study, and lactation diet contained 30% of concentrate (dry-matter basis). Measurements and sampling were performed between wk −4 and 7 relative to calving. No significant effects were observed of BCS group on dry matter intake (kg/d), milk yield, BCS loss, plasma glucose, and insulin concentrations. The high-BCS group had the lowest postpartum energy balance and the greatest plasma concentrations of leptin prepartum, nonesterified fatty acids and β-hydroxybutyrate postpartum, insulin-like growth factor 1, and milk fat content. Milk fat yield was greater for the high- than the low-BCS group (1,681 vs. 1,417 g/d). Low-BCS cows had the greatest concentration of medium-chain fatty acids (e.g., sum of 10:0 to 15:0, and 16:0), and the lowest concentration and secretion of preformed fatty acids (e.g., cis-9 18:1) in milk fat. Milk protein secretion was lowest in the low-BCS group, averaging 924, 1,051, and 1,009 g/d for low-, medium-, and high-BCS groups, respectively. Plasma 3-methylhistidine was greater in wk 1 and 2 postpartum compared with other time points, indicating mobilization of muscle protein. Plasma creatinine tended to be lower and the 3-methylhistidine: creatinine ratio was greater in low- compared with medium- and high-BCS cows, suggesting less muscle mass but more intense mobilization of muscle protein in lean cows. High-BCS cows were metabolically challenged during early lactation due to intense mobilization of body fat. Conversely, limited availability of body fat in low-BCS cows was associated with increased plasma indicators of body protein mobilization during the first weeks of lactation, and lower milk protein secretion. These results should be confirmed using an experimental approach where calving BCS variation would be controlled by design.