Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 21;14(16):2421.
doi: 10.3390/ani14162421.

Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits

Jiacheng Wei  1 , Yan Wu  1 , Xi Tang  1 , Jinxiu Liu  1 , Yani Huang  1 , Zhenfang Wu  2 , Xinyun Li  3 , Zhiyan Zhang  1
Affiliations

Deep Learning-Based Automated Approach for Determination of Pig Carcass Traits

Jiacheng Wei et al. Animals (Basel). .

Abstract

Pig carcass traits are among the most economically significant characteristics and are crucial for genetic selection in breeding and enhancing the economic efficiency. Standardized and automated carcass phenotyping can greatly enhance the measurement efficiency and accuracy, thereby facilitating the selection and breeding of superior pig carcasses. In this study, we utilized phenotypic images and data from 3912 pigs to propose a deep learning-based approach for the automated determination of pig carcass phenotypic traits. Using the YOLOv8 algorithm, our carcass length determination model achieves an average accuracy of 99% on the test set. Additionally, our backfat segmentation model, YOLOV8n-seg, demonstrates robust segmentation performance, with a Mean IoU of 89.10. An analysis of the data distribution comparing manual and model-derived measurements revealed that differences in the carcass straight length are primarily concentrated between -2 cm and 4 cm, while differences in the carcass diagonal length are concentrated between -3 cm and 2 cm. To validate the method, we compared model measurements with manually obtained data, achieving coefficients of determination (R2) of 0.9164 for the carcass straight length, 0.9325 for the carcass diagonal length, and 0.7137 for the backfat thickness, indicating high reliability. Our findings provide valuable insights into automating carcass phenotype determination and grading in pig production.

Keywords: automated phenotyping of pigs; backfat thickness; carcass length; deep learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Example of carcass straight length and carcass oblique length.
Figure 2
Figure 2
Example of a carcass length determination model.
Figure 3
Figure 3
Comparative analysis of model determination and manual measurement of carcass length before and after image filtering. (a,b) Unfiltered carcass straight length and carcass slant length data; (c,d) filtered carcass straight length and carcass oblique length data.
Figure 4
Figure 4
Data distribution of the differences in carcass lengths obtained using manual measurement and model determinations before and after image filtering. (a) Data distribution of the differences in carcass straight lengths before and after filtration; (b) data distribution of the differences in carcass oblique lengths before and after filtration.
Figure 5
Figure 5
Example of segmentation results of the automatic backfat segmentation model.
Figure 6
Figure 6
Results of the comparative analysis between the mean backfat thickness obtained using the model and the five-point mean fat thickness obtained by manual measurement.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Roongsitthichai A., Tummaruk P. Importance of backfat thickness to reproductive performance in female pigs. Thai Vet. Med. 2014;44:171–178. doi: 10.56808/2985-1130.2557. - DOI
    1. Więcek J., Warda A., Blicharski T., Sońta M., Zalewska A., Rekiel A., Batorska M. The effect of backfat thickness determined in vivo in breeding gilts on their reproductive performance and longevity. Anim. Sci. Pap. Rep. 2023;41:293–304. doi: 10.2478/aspr-2023-0013. - DOI
    1. Miar Y., Plastow G., Bruce H., Moore S., Manafiazar G., Kemp R., Charagu P., Huisman A., van Haandel B., Zhang C., et al. Genetic and phenotypic correlations between performance traits with meat quality and carcass characteristics in commercial crossbred pigs. PLoS ONE. 2014;9:e110105. doi: 10.1371/journal.pone.0110105. - DOI - PMC - PubMed
    1. Zeng H., Zhong Z., Xu Z., Teng J., Wei C., Chen Z., Zhang W., Ding X., Li J., Zhang Z. Meta-analysis of genome-wide association studies uncovers shared candidate genes across breeds for pig fatness trait. BMC Genom. 2022;23:786. doi: 10.1186/s12864-022-09036-z. - DOI - PMC - PubMed
    1. Gozalo-Marcilla M., Buntjer J., Johnsson M., Batista L., Diez F., Werner C.R., Chen C.Y., Gorjanc G., Mellanby R.J., Hickey J.M., et al. Genetic architecture and major genes for backfat thickness in pig lines of diverse genetic backgrounds. Genet. Sel. Evol. GSE. 2021;53:76. doi: 10.1186/s12711-021-00671-w. - DOI - PMC - PubMed

LinkOut - more resources