Improve the accuracy of chicken leg disease assessment by combination of gait score and X-ray scan

Zheng, Jumei; Liu, Dawei; Zhang, Gaomeng; Ding, Jiqiang; He, Zhengxiao; Li, Qinghe; Liu, Ranran; Wen, Jie; Zhao, Guiping

doi:10.1016/j.japr.2023.100339

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, X-ray technology can complete the scan within seconds after the broiler is simply fixed, without the need for additional operations. It is often employed for assessing the physiological condition of animal organisms [16][17][18][19]. In addition, many phenotypic traits of most organisms can also be measured or analyzed from X-ray images [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Zhu,

Li,

Yang

et al. 2024

Animals

View full text Add to dashboard Cite

Accurately estimating the breast muscle weight of broilers is important for poultry production. However, existing related methods are plagued by cumbersome processes and limited automation. To address these issues, this study proposed an efficient method for predicting the breast muscle weight of broilers. First, because existing deep learning models struggle to strike a balance between accuracy and memory consumption, this study designed a multistage attention enhancement fusion segmentation network (MAEFNet) to automatically acquire pectoral muscle mask images from X-ray images. MAEFNet employs the pruned MobileNetV3 as the encoder to efficiently capture features and adopts a novel decoder to enhance and fuse the effective features at various stages. Next, the selected shape features were automatically extracted from the mask images. Finally, these features, including live weight, were input to the SVR (Support Vector Regression) model to predict breast muscle weight. MAEFNet achieved the highest intersection over union (96.35%) with the lowest parameter count (1.51 M) compared to the other segmentation models. The SVR model performed best (R2 = 0.8810) compared to the other prediction models in the five-fold cross-validation. The research findings can be applied to broiler production and breeding, reducing measurement costs, and enhancing breeding efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Zhu,

Li,

Yang

et al. 2024

Animals

View full text Add to dashboard Cite

show abstract

“…As technology for in vivo imaging has become faster, more accurate, and more affordable, it has become a more viable option for monitoring and characterizing disease states and phenotypes. Research on the use of dual-energy X-ray absorptiometry (DXA) imaging (Hester et al, 2004), X-ray imaging (Zheng et al, 2023), computerized tomography (CT) scanning (Aguado et al, 2015), and ultrasound (Mutalib et al, 1996) in poultry has been reported and is being expanded upon almost yearly. In the present study, we utilized a small, self-shielding DXA and X-ray machine to visualize and characterize the leg quarters of broilers.…”

Section: Introductionmentioning

confidence: 99%

Potential non-invasive detection of lesions in broiler femur heads: application of the DXA imaging system

Ramser,

Greene,

Wideman

et al. 2024

Front. Physiol.

View full text Add to dashboard Cite

Leg health is a significant economic and welfare concern for the poultry industry. Current methods of detection rely on visual assessment of the legs and gait scores and bone scoring during necropsy for full characterization. Additionally, the current scoring of femurs only examines the external surface of the femoral head. Through the use of the dual-energy X-ray absorptiometry (DXA) imaging system, we show the presence of a necrotic region in the femurs that would otherwise be considered healthy based on the current evaluation procedures. Importantly, these lesions were present in almost 60% (22 of 37) of femurs that scored normal for femoral head necrosis (FHN). Additionally, these femurs showed greater bone mineral content (BMC) relative to weight compared to their counterparts with no lucent lesions (6.95% ± 0.20% vs. 6.26% ± 0.25; p = 0.038). Identification of these lesions presents both a challenge and an opportunity. These subclinical lesions are likely to be missed in routine scoring procedures for FHN and can inadvertently impact the characterization of the disease and genetic selection programs. Furthermore, this imaging system can be used for in vivo, ex vivo, and embryonic (egg) studies and, therefore, constitutes a potential non-invasive method for early detection of bone lesions in chickens and other avian species.

show abstract

Metabolomic analysis reveals the molecular mechanism related to leg abnormality in broilers

Zheng,

Zhang,

Tang

et al. 2024

Animal Research and One Health

View full text Add to dashboard Cite

Rapid body weight gain in broilers overloads the metabolic system of the organism, resulting in leg abnormalities, which seriously affects animal welfare and industry economics. In this study, broilers with normal and deformed leg bones were examined. Serum biochemical indices showed that the serum calcium to phosphorus ratio was extremely decreased in leg deformed group. In addition, abnormal serum lipid levels suggested a disruption in lipid metabolism. Based on widely targeted metabonomic analysis of serum and cartilage tissues, a total of nine differential metabolites (DMs) significantly associated with leg abnormalities and serum calcium and phosphorus levels were screened, including carnitine C16:0, carnitine C18:1, 3‐hydroxymethyl‐L‐tyrosine, cis‐4‐hydroxy‐D‐proline, cis‐L‐3‐hydroxyproline, trans‐4‐hydroxy‐L‐proline, and so on. Pathway analysis revealed that fatty acid degradation and arachidonic acid metabolism were enriched. Analysis of DMs in these two pathways showed that prostaglandin D2, prostaglandin J2, prostaglandin A2, 15‐keto prostaglandin F2α, and Δ12‐prostaglandin J2 significantly differed between the normal and abnormal groups. It was hypothesized that these important metabolic pathways and metabolites were involved in the metabolic regulation of leg abnormalities.

show abstract

Improve the accuracy of chicken leg disease assessment by combination of gait score and X-ray scan

Cited by 3 publications

References 35 publications

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Potential non-invasive detection of lesions in broiler femur heads: application of the DXA imaging system

Metabolomic analysis reveals the molecular mechanism related to leg abnormality in broilers

Contact Info

Product

Resources

About