Using Thermal Signature to Evaluate Heat Stress Levels in Laying Hens with a Machine-Learning-Based Classifier

Infrared thermography has been investigated in recent studies to monitor body surface temperature and correlate it with animal welfare and performance factors. In this context, this study proposes the use of the thermal signature method as a feature extractor from the temperature matrix obtained from regions of the body surface of laying hens (face, eye, wattle, comb, leg, and foot) to enable the construction of a computational model for heat stress level classification. In an experiment conducted in climate-controlled chambers, 192 laying hens, 34 weeks old, from two different strains (Dekalb White and Dekalb Brown) were divided into groups and housed under conditions of heat stress (35 °C and 60% humidity) and thermal comfort (26 °C and 60% humidity). Weekly, individual thermal images of the hens were collected using a thermographic camera, along with their respective rectal temperatures. Surface temperatures of the six featherless image areas of the hens' bodies were cut out. Rectal temperature was used to label each infrared thermography data as "Danger" or "Normal", and five different classifier models (Random Forest, Random Tree, Multilayer Perceptron, K-Nearest Neighbors, and Logistic Regression) for rectal temperature class were generated using the respective thermal signatures. No differences between the strains were observed in the thermal signature of surface temperature and rectal temperature. It was evidenced that the rectal temperature and the thermal signature express heat stress and comfort conditions. The Random Forest model for the face area of the laying hen achieved the highest performance (89.0%). For the wattle area, a Random Forest model also demonstrated high performance (88.3%), indicating the significance of this area in strains where it is more developed. These findings validate the method of extracting characteristics from infrared thermography. When combined with machine learning, this method has proven promising for generating classifier models of thermal stress levels in laying hen production environments.

Evaluating broiler welfare and behavior as affected by growth rate and stocking density

This study evaluated the welfare and behaviors of Cobb 700 broilers as affected by growth rate (GR) and stocking density (SD). Slower-growth (weight gain < 50 g/d) and medium-growth (weight gain = 50-60 g/d) broilers were produced by providing 57.1% and 78.6% of the feed intake listed in the Cobb 700 production manual for standard (fed ad libitum) broilers (weight gain > 60 g/d). Broilers at all 3 GRs were reared at 2 SDs of 30 and 40 kg/m2. Broiler welfare indicators, including gait score, tibia strength, feather coverage, and footpad condition were evaluated when birds reached 1, 2, and 3 kg of body weight. The activity index was determined by overhead cameras and image processing, and the time spent at feeders was recorded using the radio-frequency identification (RFID) systems. The results show that it took 45 d for standard, 52 d for medium-growth, and 62 d for slower-growth broilers to reach a 3 kg market body weight. Feed conversion ratios (FCR, kg/kg) were 1.57 for standard, 1.67 for medium-growth, and 1.80 for slower-growth broilers. Growth rate and SD had an interaction effect on feather cleanliness (P = 0.03), and belly feather coverage (P = 0.02). Slower-growth broilers were more active and had better feather coverage and gait scores than medium-growth and standard broilers (all P < 0.01) but may feel hungry and depressed, medium-growth broilers spent the most time at the feeder among the 3 growth groups (P = 0.02), and standard broilers showed the best production performance. Broilers at 30 kg/m2 showed better bone strength (P = 0.04), and footpad condition (P < 0.01) compared to those at 40 kg/m2. In conclusion, reducing GR and SD may slightly improve broiler leg health at the high expense of compromised production performance and prolonged production cycles.

Resource choice during ontogeny enhances both the short- and longer-term welfare of laying hen pullets

We hypothesised that resource choice during early life contributes to both current and longer-term beneficial effects on animal welfare. We investigated this hypothesis in a longitudinal cross-over experiment with laying hen pullets (Gallus gallus domesticus) reared in pens with one or four litter and perch types, respectively (n = 8 pens/treatment, all providing ample and identical litter and perch space). After 4 weeks (chick period), half the pens were modified to provide the opposite treatment (juvenile period). After 11 more weeks, all groups were moved to novel, identical laying pens (adult period; Week 16-27). In support of our hypothesis, the opportunity to choose between multiple litter and perch variants was associated with higher levels of positively-valenced behaviours, including play as chicks and dustbathing as juveniles and adults, and lower levels of negatively-valenced behaviours, including feather pecking as chicks and juveniles and aggressive pecking as adults. Resource choice in the juvenile period also led to better juvenile and adult plumage condition, and greater growth as adults. We conclude that the opportunity to choose among different litter and perch types, instead of having only one type of each, had both short- and longer-term positive effects on the birds' affective states and physical condition.

Feather Damage Monitoring System Using RGB-Depth-Thermal Model for Chickens

Feather damage is a continuous health and welfare challenge among laying hens. Infrared thermography is a tool that can evaluate the changes in the surface temperature, derived from an inflammatory process that would make it possible to objectively determine the depth of the damage to the dermis. Therefore, the objective of this article was to develop an approach to feather damage assessment based on visible light and infrared thermography. Fusing information obtained from these two bands can highlight their strengths, which is more evident in the assessment of feather damage. A novel pipeline was proposed to reconstruct the RGB-Depth-Thermal maps of the chicken using binocular color cameras and a thermal infrared camera. The process of stereo matching based on binocular color images allowed for a depth image to be obtained. Then, a heterogeneous image registration method was presented to achieve image alignment between thermal infrared and color images so that the thermal infrared image was also aligned with the depth image. The chicken image was segmented from the background using a deep learning-based network based on the color and depth images. Four kinds of images, namely, color, depth, thermal and mask, were utilized as inputs to reconstruct the 3D model of a chicken with RGB-Depth-Thermal maps. The depth of feather damage can be better assessed with the proposed model compared to the 2D thermal infrared image or color image during both day and night, which provided a reference for further research in poultry farming.

Research Note: Is infrared thermography an appropriate method for early detection and objective quantification of plumage damage in white and brown feathered laying hens?

For the standardized assessment of plumage damage in laying hens, imaging techniques can be used in addition to visual plumage scoring (PS). In this study, the diagnostic accuracy of infrared thermography (IRT) was analyzed in white-feathered (WL) and brown-feathered laying hens (BL) with PS as a reference. In 28 flocks, a 3-level PS and IRT were performed 8 times for the dorsal neck, back, and belly plumage. A total of 3,600 records for WL and 7,600 records for BL were available for both PS and IRT in each of the 3 body regions. Receiver operating characteristic (ROC) analyses were used to investigate diagnostic accuracy. High-accuracy detection was found for severe plumage damage on the back (WL—sensitivity: 96.0%, specificity: 98.3%; BL—sensitivity: 96.1%, specificity: 98.9%) and belly plumage (WL—sensitivity: 96.3%, specificity: 95.7%; BL—sensitivity: 95.3%, specificity: 97.2%), but insufficient accuracy for distinguishing between intact plumage and moderate plumage damage in all 3 body regions (sensitivity: 31.7–71.5%; specificity: 70.4–98.1%). The area under the curve (AUC) of the ROC graphs differed significantly between BL and WL for the back and belly plumage (P ≤ 0.05). We concluded that IRT is a suitable tool to objectively detect severe plumage damage but not for early detection of incipient plumage loss.

Role of dietary gamma-aminobutyric acid in broiler chickens raised under high stocking density

The present study was conducted to evaluate the effects of dietary gamma-aminobutyric acid (GABA) in broiler chickens raised in high stocking density (HSD) on performance and physiological responses. A total of 900 male broiler chicks (Ross 308) at 1 d old were assigned in a 2 × 2 factorial arrangement to 4 treatments (10 replicates per treatment) with stocking density, 7.5 birds/m² (low stocking density; LSD) or 15 birds/m² (HSD), and dietary GABA, 0 or 100 mg/kg. Chickens raised in HSD exhibited a decrease in body weight gain in all phases (P < 0.05) and feed intake in starter and whole phases (P < 0.01), and an increase in feed conversion ratio in the finisher phase (P < 0.01) compared with LSD-raised chickens. However, dietary GABA did not affect growth performance nor interacted with stocking density on production variables. The HSD vs. LSD increased relative liver weight on d 35 whereas dietary GABA increased relative liver weight and decreased relative bursa weight on d 21. Both stocking density and dietary GABA affected yield and quality of breast and leg muscles. Dietary GABA increased (P < 0.05) width of tibia on d 35 and interacted (P = 0.054) with stocking density on breaking stocking density on d 35. The HSD vs. LSD group lowered (P < 0.05) feather coverage scores. Significant interaction between stocking density and GABA on surface temperature of shank on d 21 was noted (P = 0.024). Dietary GABA exhibited an opposite effect on the concentrations of cecal short-chain fatty acids depending on stocking density leading to a moderate to significant interaction. Stocking density decreased alpha-1-acid glycoprotein whereas dietary GABA decreased heterophil-to-lymphocyte ratio and corticosterone in blood or serum samples. Serum biochemical parameters were altered by stocking density or dietary GABA. It is concluded that dietary GABA alleviated stress indices including corticosterone and heterophil-to-lymphocyte ratio, but failed to reverse stocking density-induced growth depression.

Effects of heat stress on pullet cloacal and body temperature

One measure of the thermal status of poultry is cloacal temperature measured with a cloacal thermometer; however, this method requires handling the bird, is invasive, and can be stressful. Infrared thermography is an alternative means for assessing bird thermal status. The objective of this study was to investigate the body temperature response of pullets subjected to different environmental air temperatures during the growing phase and to evaluate the relationship between the cloacal temperature and the body parts surface temperature. A total of 648 chicks (Lohmann LSL Lite) were used in 2 different phases, phase I (day 1 through 6 wk of age) and phase II (week 7 through 17). During phase I, chicks were reared at 1 of 3 different thermal environments: thermal comfort (35°C–19°C), mild heat stress (38°C–22°C), or mild cold stress (28°C–17°C). In phase II, pullets were randomly redistributed to 1 of 4 daytime temperature treatments: 20°C; 25°C; 30°C; and 35°C, all with night time temperature of 20°C. Cloacal temperature and body surface temperature for 8 parts (head, eye, comb, chest, back, wing, leg, head area, and body area) were obtained weekly from 4 to 2 birds per treatment, respectively, during phase II. There were no effects for the interactions between the 2 experimental phases for cloacal and body parts surface temperature. There was a strong correlation (P < 0.001) between cloacal temperature and each body part temperature; cloacal temperature followed a quadratic response to environmental air temperature treatments. Pullets subjected to 35°C/20°C and 30°C/20°C had the highest body parts temperatures compared with the other 2 treatments (P < 0.05). The leg surface temperature was greatest in all treatments, and the chest the lowest. Regression between cloacal and body parts temperature had a 95% predictive accuracy of better than 0.4°C, suggesting a useful alternative to direct cloacal temperature measurement.

Smartphone-Based Device in Exotic Pet Medicine

This article reviews the use of the smartphone in exotic pet medicine. The mobile app is the most instinctive use of the smartphone; however, there are very limited software dedicated to the exotic pet specifically. With an adapter, the smartphone can be attached to a regular endoscope and acts as a small endoscopic unit. Additional devices, such as infrared thermography or ultrasound, can be connected to the smartphone through the micro-USB port. The medical use of the smartphone is still in its infancy in veterinary medicine but can bring several solutions to the exotic pet practitioner and improve point-of-care evaluation.

Towards a quantitative indicator of feather disruption following the cleansing of oiled birds

A computer-based imaging method for determining feather microstructure coherency following a cleansing treatment, was developed, calibrated and trialled on Mallard Duck (Anas platyrhyhchos) feathers. The feathers were initially contaminated with a light crude oil and then cleansed by either detergent (Deacon 90) treatment or, alternatively, by magnetic particle technology (MPT) using iron powder. The imaging method provides a single quantitative parameter for the coherence of feather microstructure and the results confirm that MPT treatment imparts less disruption to the feather microstructure than detergent treatment. It is proposed that this imaging method can be developed and implemented for the assessment of feather disruption and possibly damage, either for the trialling of different treatment protocols, or as a tool during the rehabilitation process, along with other such indicators, to give a more comprehensive assessment of feather condition than is currently available.

Effects of light-emitting diode light v. fluorescent light on growing performance, activity levels and well-being of non-beak-trimmed W-36 pullets

More energy-efficient, readily dimmable, long-lasting and more affordable light-emitting diode (LED) lights are increasingly finding applications in poultry production facilities. Despite anecdotal evidence about the benefits of such lighting on bird performance and behavior, concrete research data were lacking. In this study, a commercial poultry-specific LED light (dim-to-blue, controllable correlated color temperature (CCT) from 4500 to 5300 K) and a typical compact fluorescent light (CFL) (soft white, CCT=2700 K) were compared with regards to their effects on growing performance, activity levels, and feather and comb conditions of non-beak-trimmed W-36 pullets during a 14-week rearing period. A total of 1280-day-old pullets in two successive batches, 640 birds each, were used in the study. For each batch, pullets were randomly assigned to four identical litter-floor rooms equipped with perches, two rooms per light regimen, 160 birds per room. Body weight, BW uniformity (BWU), BW gain (BWG) and cumulative mortality rate (CMR) of the pullets were determined every 2 weeks from day-old to 14 weeks of age (WOA). Activity levels of the pullets at 5 to 14 WOA were delineated by movement index. Results revealed that pullets under the LED and CFL lights had comparable BW (1140±5 g v. 1135±5 g, P=0.41), BWU (90.8±1.0% v. 91.9±1.0%, P=0.48) and CMR (1.3±0.6% v. 2.7±0.6%, P=0.18) at 14 WOA despite some varying BWG during the rearing. Circadian activity levels of the pullets were higher under the LED light than under the CFL light, possibly resulting from differences in spectrum and/or perceived light intensity between the two lights. No feather damage or comb wound was apparent in either light regimen at the end of the rearing period. The results contribute to understanding the impact of emerging LED lights on pullets rearing which is a critical component of egg production.

Technology and Poultry Welfare

Consideration of animal welfare is essential to address the consumers’ demands and for the long term sustainability of commercial poultry. However, assessing welfare in large poultry flocks, to be able to detect potential welfare risks and to control or minimize its impact is difficult. Current developments in technology and mathematical modelling open new possibilities for real-time automatic monitoring of animal welfare and health. New technological innovations potentially adaptable to commercial poultry are appearing, although their practical implementation is still being defined. In this paper, we review the latest technological developments with potential to be applied to poultry welfare, especially for broiler chickens and laying hens. Some of the examples that are presented and discussed include the following: sensors for farm environmental monitoring, movement, or physiological parameters; imaging technologies such as optical flow to detect gait problems and feather pecking; infrared technologies to evaluate birds’ thermoregulatory features and metabolism changes, that may be indicative of welfare, health and management problems. All these technologies have the potential to be implemented at the commercial level to improve birds’ welfare and to optimize flock management, therefore, improving the efficiency of the system in terms of use of resources and, thus, long term sustainability.

Effect of light-emitting diode vs. fluorescent lighting on laying hens in aviary hen houses: Part 1 - Operational characteristics of lights and production traits of hens

Light-emitting diode (LED) lights are becoming more affordable for agricultural applications. Despite many lab-scale studies concerning impact of LED on poultry, little research has been documented under field production conditions, especially for laying hens. This 15-month field study was carried out to evaluate the effects of LED vs. fluorescent (FL) lights on laying hens (Dekalb white breed) using 4 (2 pairs) aviary hen houses each at a nominal capacity of 50,000 hens. The evaluation was done regarding operational characteristics of the lights and hen production traits. The results show that spatial distribution of the LED light was less uniform than that of the FL light. Light intensity of the LED light decreased by 27% after 3,360 h use but remained quite steady from 3,360 to 5,760 h use. Eleven out of 762 (1.44%) LED lamps (new at onset of the study) in the 2 houses failed during the 15-month experiment period. The neck area of the LED lamp was hottest, presumably the primary reason for the lamp failure as cracks were noticed in the neck region of all failed LED lamps. No differences were observed in egg weight, hen-day egg production, feed use, and mortality rate between LED and FL regimens. However, hens under the FL had higher eggs per hen housed and better feed conversion than those under the LED during 20 to 70 wk production (P < 0.05). Hens under the LED tended to have less feather uniformity and insulation than those under the FL (P < 0.05). Moreover, hens under the LED showed a larger median avoidance distance than those under the FL at 36 wk age (P < 0.05), indicating that hens under the LED were more alert; but no difference at 60 wk age. More comparative research to quantify behavioral and production responses of different breeds of hens to LED vs. FL lighting seems warranted.