Under intensive rearing conditions, the welfare of broiler chickens may be at risk depending on genotype and sex, due to their different growth rates. The practice of quantitative feed restriction may also impact on welfare. This study aimed to evaluate behaviour and corticosterone content in plasma and faeces at different ages using 896 one-day-old chicks housed in 32 pens, allocated to 8 groups, i.e., 2 genotypes (standard vs. high breast yield) × 2 sex × 2 feeding plans (ad libitum vs. restricted, AL vs. FR). The feeding system affected the percentage of standing (9.84% vs. 11.7% in AL vs. FR; p ≤ 0.001), feeding (7.51% vs. 8.17%; p ≤ 0.01) and sitting/lying (67.0% vs. 64.1%; p ≤ 0.001), and the faeces corticosterone content (12.2 vs. 13.6 ng/g in AL vs. FR; p ≤ 0.10). Sex affected the percentage of pecking other chickens, standing and comfort behaviours. Changes in behaviour were recorded between high and standard breast yield genotypes with faeces corticosterone which tended to be higher in the former (p ≤ 0.10). Significant interactions between the main factors and age were observed. Major changes in behaviour were due to feed restriction, which stimulated activity during restriction.

Image analysis using machine learning (ML) algorithms could provide a measure of animal welfare by measuring comfort behaviours and undesired behaviours. Using a PLF technique based on images, the present study aimed to test a machine learning tool for measuring the number of hens on the ground and identifying the number of dust-bathing hens in an experimental aviary. In addition, two YOLO (You Only Look Once) models were compared. YOLOv4-tiny needed about 4.26 h to train for 6000 epochs, compared to about 23.2 h for the full models of YOLOv4. In validation, the performance of the two models in terms of precision, recall, harmonic mean of precision and recall, and mean average precision (mAP) did not differ, while the value of frame per second was lower in YOLOv4 compared to the tiny version (31.35 vs. 208.5). The mAP stands at about 94% for the classification of hens on the floor, while the classification of dust-bathing hens was poor (28.2% in the YOLOv4-tiny compared to 31.6% in YOLOv4). In conclusion, ML successfully identified laying hens on the floor, whereas other PLF tools must be tested for the classification of dust-bathing hens.

Growth performance and meat quality were assessed in 238 chicks of both sexes belonging to a commercial crossbreed (Ross 308), and 2 Italian local breeds (Bionda Piemontese—BP and Robusta Maculata—RM). The chickens were kept in 2 rooms at standard environmental conditions or under heat stress (+4.7°C on average) until slaughtering (42 d of age for Ross 308 and 99 d for RM and BP chickens). The Ross chickens showed the highest final live weight, feed intake, and daily weight gain, and the best feed conversion ratio compared to the local breeds (P < 0.001), with RM performing better than BP chickens. Thus, Ross chickens had the heaviest carcasses, the highest slaughter, and breast yields followed by RM and BP chickens (P < 0.001). At the pectoralis major ( p. major ) muscle, Ross chickens showed the highest pH, lightness, and yellowness, besides the highest cooking losses, whereas BP showed the highest redness (P < 0.001). Ross meat had higher water and ether extract contents, and lower crude protein content compared to BP and RM (P < 0.001), whereas no differences among genotypes were measured for the fatty acid profile. At the sensory analysis, Ross breasts had a higher juiciness compared to BP ones, besides a lower score for “brothy and chickeny/meaty” and a higher one for “wet feathers” compared to local breeds (0.05 < P < 0.001). The increase of the room temperature decreased growth performance and cold carcass weight (P < 0.001) compared to standard conditions, whereas the rate of α-linolenic acid in the meat increased (P < 0.01). The effect of a high environmental temperature on growth performance and slaughter and meat quality traits was more pronounced in Ross compared to BP and RM chickens (0.05 < P <0.001; significant interaction genotype × temperature). In conclusions, local chicken breeds showed lower performance and slaughter yield compared to the commercial genotype, but more favorable meat quality traits and higher resilience to the environmental heat-stress.

The present study evaluated the effect of digestible energy (DE) and crude protein (CP) levels on growth, digestive efficiency, slaughter yield and meat quality in growing rabbits of two genotypes (Grimaud, G vs. Hyla, H). A total of 384 crossbred rabbits (192 G and 192 H), half males and half females, were divided into eight experimental groups according to a bi-factorial arrangement (2 genotypes × 4 diets; 48 animals/group) and reared in individual cages. From 33 to 64 days of age, rabbits were fed four diets obtained by combining two DE levels (high, HE—10.9 MJ/kg vs. low, LE—9.2 MJ/kg, on average) and two CP levels (high, HP—159 g/kg vs. low, LP—144 g/kg, on average). Then, all rabbits received the same fattening diet (10.7 MJ DE/kg; 156 g CP/kg) until slaughtering (77 days of age). Growth performance did not differ between genotypes for the entire trial (on average final live weight 3010 g; daily weight gain 50.5 g/d), but H rabbits showed a faster growth during the post-weaning period (p ≤ 0.01) compared to G rabbits, while exhibiting lower slaughter yield and lower carcass fatness (p ≤ 0.01). As DE level increased, feed intake decreased and feed conversion improved (p < 0.001), while caecal volatile fatty acid concentration increased and caecal pH and N-ammonia decreased (p ≤ 0.01). The reduction in the CP level did not affect performance and carcass traits. No significant interaction was detected between genotype and diet. In conclusion, G rabbits may have an advantage over H rabbits because of the higher slaughter yield. As for the nutritional characteristics of diets for high-producing crossbred rabbits, high energy levels are confirmed to enhance feed efficiency, whereas dietary CP can be reduced to 144 g/kg without negative effects on performance and carcass traits.