The egg has natural barriers that prevent microbiological contamination and promote food safety. The use of non-destructive methods to obtain morphometric measurements of chicken eggs has the potential to replace traditional invasive techniques, offering greater efficiency and accuracy. This paper aims to demonstrate that estimates derived from non-invasive approaches, such as 3D computed tomography (CT) image analysis, can be comparable to conventional destructive methods. To achieve this goal, two widely recognized deep learning architectures, U-Net 3D and Fully Convolutional Networks (FCN) 3D, were modeled to segment and analyze 3D CT images of chicken eggs. A dataset of real CT images was created and labeled, allowing the extraction of important morphometric measurements, including height, width, shell thickness, and volume. The models achieved an accuracy of up to 98.69%, demonstrating their effectiveness compared to results from manual measurements. These findings highlight the potential of CT image analysis, combined with deep learning, as a non-invasive alternative in industrial and research settings. This approach not only minimizes the need for invasive procedures but also offers a scalable and reliable method for egg quality assessment.

A maior parte dos ingredientes destinados a alimentação de animais não ruminantes se constituem de origem vegetal e podem conter, em sua composição, níveis variáveis de polissacarídeos não amiláceos (PNAs). Estes são conhecidos por comprometerem, a depender dos níveis de inclusão do ingrediente, concentrações e tipos nos alimentos, o desempenho e a saúde intestinal de suínos e aves. As carboidrases são enzimas que degradam carboidratos e tem sido utilizada como alternativas para melhorias no aproveitamento de fontes alimentares que contenham grandes quantidades de PNAs, com resultados positivos sobre aproveitamento energético da dieta e diminuindo os efeitos negativos desses compostos. Celulases, xilanases, betaglucases, amilases, galactosidades, dentre outras tem sido suplementadas nas rações desses animais e têm mostrado serem afetivas em melhorar as características morfométricas, estado imunológico e microbiano do intestino, com impactos positivos sobre a saúde intestinal e desempenho. Logo, estre trabalho teve por objetivo revisar os efeitos da utilização e enzimas carboidrases na dieta de aves e seus efeitos sobre a saúde intestinal.

This study investigated the optimal dietary intake of zinc amino acid complex (Zn-AAC) for white-layer pullets, focusing on their productive performance, biochemical profile, organ biometry, and body zinc retention. The study involved 360 Dekalb White pullets (average weight: 433 ± 4.42 g) aged from 6 to 16 weeks and distributed into 6 treatments with 6 replications each. The Zn-AAC inclusion levels ranged from 5 to 75 mg kg^-1. Zinc intake was modeled using a nonlinear equation, Y = ∝ *1- e^-βX, where α is the maximum response, β is the rate at which the response approaches the maximum (P < 0.05). The Zn-AAC supplementation had significant effects on average daily gain (ADG), average daily feed intake (ADFI), and feed convention ratio (FCR) (P < 0.01). Optimal intake levels of Zn-AAC were estimated at 0.234, 0.340, and 0.315 mg bird^-1 day^-1 (5.42, 7.87, and 7.30 mg kg^-1) for ADG, ADFI, and FCR, respectively. The Zn-AAC supplementation affected the Zn body retention in pullets (P < 0.01), with an optimal ingestion at 1.86 mg bird ^-1 day^-1, corresponding to a dietary supplementation of 43.10 mg kg^-1. Additionally, supplementation affected alkaline phosphatase (ALP) activity (P < 0.01) without significant changes in aspartate aminotransferase, albumin, and globulin levels. The optimal Zn-AAC intake level for ALP activity was 1.45 mg bird ^-1 day^-1, corresponding to dietary supplementation of 33.60 mg kg^-1. Based on Zn body retention, we recommend up to 1.86 mg bird ^-1 day^-1 of Zn-AAC, which is equivalent to 43.10 mg kg^-1.

Aim of study: To assess the performance of the giant freshwater prawn Macrobrachium rosenbergii (De Man, 1879) during the nursery phase under different culture systems (water exchange ‑ WES and biofloc ‑ BFS) and varying crude protein levels, using high‑density culture conditions (2,500 post‑larvae m‑³). Area of study: This study was conducted at the Federal Rural University of Pernambuco, in Brazil. Material and methods: The experimental design followed a 2 x 2 factorial arrangement, in which the initial variable corresponded to the type of rearing system, while the second one referred to the dietary crude protein content (35% and 40%), yielding in the combinations WES 35, WES 40, BFS 35, and BFS 40. Main results: The results demonstrated that the BFS 35 combination exhibited the lowest basic variable production cost and a substantial reduction in water footprint, ten times lower than the WES combinations. Furthermore, the BFS 35 system achieved a notable improvement in net benefits (2,876 USD 1000 m‑³), which was approximately twice that of the WES 35 (1,441 USD 1000 m⁻³) and nearly three times that of the WES 40 (1,006 USD 1000 m⁻³). Research highlights: The BFS 35 system can significantly reduce both the water footprint and the crude protein content in commercial feed, while simultaneously enhancing economic returns. These results suggest that the biofloc system with a 35% protein level is a viable and more sustainable option for the nursery phase of M. rosenbergii, offering a promising alternative to traditional systems.

This paper presents EggQuality-UFRPE, a multidisciplinary dataset comprising 2,150 chicken egg instances with 29 features, collected through manual measurements using advanced instrumentation. It addresses the scarcity of open-access empirical data in animal science, supporting multidisciplinary research with computer disciplines, such as data science and machine learning. A descriptive analysis is included, reporting mean, median, dispersion metrics, missing data proportions, and Pearson correlation coefficients among features. These statistics reveal the dataset’s internal consistency and support exploratory modeling. Despite limitations, such as a single hen strain, the dataset enables applications ranging from regression and predictive modeling to synthetic data generation and multimodal learning, promoting integration between computational and animal sciences.