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

被引:0
作者
Zhu, Rui [1 ]
Li, Jiayao [1 ]
Yang, Junyan [1 ]
Sun, Ruizhi [1 ,2 ]
Yu, Kun [3 ]
机构
[1] China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China
[2] Minist Agr, Anim Husb, Sci Res Base Integrated Technol Precis Agr, Beijing 100083, Peoples R China
[3] China Agr Univ, Coll Anim Sci & Technol, Beijing 100193, Peoples R China
来源
ANIMALS | 2024年 / 14卷 / 04期
关键词
weight prediction; deep learning; machine learning; X-ray; precision farming; CARCASS CHARACTERISTICS;
D O I
10.3390/ani14040628
中图分类号
S8 [畜牧、 动物医学、狩猎、蚕、蜂];
学科分类号
0905 ;
摘要
Simple Summary The breast muscle weight of broilers is a key indicator in poultry production. The accurate and nondestructive measurement of broiler breast muscle weight can improve breeding and the precision management level of broiler farms. Therefore, this study proposed an efficient method for predicting the breast muscle weight of broilers in vivo which can automatically predict broiler breast muscle weight. The experimental results demonstrate the method's accuracy and superiority. The proposed method streamlines the data collection process, improves measurement efficiency, and provides crucial data support for broiler breeding and precision management.Abstract 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.
引用
收藏
页数:21
相关论文
共 53 条
[1]   An Effective Recursive Technique for Multi-Class Classification and Regression for Imbalanced Data [J].
Alam, Tahira ;
Ahmed, Chowdhury Farhan ;
Zahin, Sabit Anwar ;
Khan, Muhammad Asif Hossain ;
Islam, Maliha Tashfia .
IEEE ACCESS, 2019, 7 :127615-127630
[2]  
Basak D., 2007, Neural Inform. Process.-Lett. Reviews, V11, P203, DOI DOI 10.1007/978-1-4302-5990-94
[3]   Albumentations: Fast and Flexible Image Augmentations [J].
Buslaev, Alexander ;
Iglovikov, Vladimir I. ;
Khvedchenya, Eugene ;
Parinov, Alex ;
Druzhinin, Mikhail ;
Kalinin, Alexandr A. .
INFORMATION, 2020, 11 (02)
[4]   Lung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid Registration [J].
Candemir, Sema ;
Jaeger, Stefan ;
Palaniappan, Kannappan ;
Musco, Jonathan P. ;
Singh, Rahul K. ;
Xue, Zhiyun ;
Karargyris, Alexandros ;
Antani, Sameer ;
Thoma, George ;
McDonald, Clement J. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2014, 33 (02) :577-590
[5]  
Canziani A., 2016, arXiv, DOI DOI 10.48550/ARXIV.1605.07678
[6]  
Chen J., 2021, arXiv, DOI 10.48550/arXiv.2102.04306
[7]   In vivo prediction of abdominal fat and breast muscle in broiler chicken using live body measurements based on machine learning [J].
Chen, Jin-Tian ;
He, Peng-Guang ;
Jiang, Jin-Song ;
Yang, Ye-Feng ;
Wang, Shou-Yi ;
Pan, Cheng-Hao ;
Zeng, Li ;
He, Ye-Fan ;
Chen, Zhong-Hao ;
Lin, Hong-Jian ;
Pan, Jin-Ming .
POULTRY SCIENCE, 2023, 102 (01)
[8]   Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].
Chen, Liang-Chieh ;
Zhu, Yukun ;
Papandreou, George ;
Schroff, Florian ;
Adam, Hartwig .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851
[9]   MCC-Net: A class attention-enhanced multi-scale model for internal structure segmentation of rice seedling stem [J].
Chen, Minhui ;
Liao, Juan ;
Zhu, Dequan ;
Zhou, Huiyu ;
Zou, Yu ;
Zhang, Shun ;
Liu, Lu .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2023, 207
[10]   Automatic segmentation of cattle rib-eye area in ultrasound images using the UNet plus plus deep neural network [J].
de Melo, Maximilian Jaderson ;
Goncalves, Diogo Nunes ;
Bonin Gomes, Marina de Nadai ;
Faria, Gedson ;
Silva, Jonathan de Andrade ;
Marques Ramos, Ana Paula ;
Osco, Lucas Prado ;
Garcia Furuya, Michelle Tais ;
Marcato Junior, Jose ;
Goncalves, Wesley Nunes .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 195