您好,欢迎访问广东省农业科学院 机构知识库!

A deep learning-based approach for fully automated segmentation and quantitative analysis of muscle fibers in pig skeletal muscle

文献类型: 外文期刊

作者: Yao, Zekai 1 ; Wo, Jingjie 4 ; Zheng, Enqin 2 ; Yang, Jie 2 ; Li, Hao 1 ; Li, Xinxin 1 ; Li, Jianhao 1 ; Luo, Yizhi 1 ; Wang, Ting 2 ; Fan, Zhenfei 2 ; Zhan, Yuexin 2 ; Yang, Yingshan 2 ; Wu, Zhenfang 2 ; Yin, Ling 4 ; Meng, Fanming 1 ;

作者机构: 1.Guangdong Acad Agr Sci, Inst Anim Sci, State Key Lab Swine & Poultry Breeding Ind, Guangdong Key Lab Anim Breeding & Nutr, Guangzhou 510640, Peoples R China

2.South China Agr Univ, Coll Anim Sci, Guangzhou 510642, Peoples R China

3.South China Agr Univ, Natl Engn Res Ctr Breeding Swine Ind, Guangzhou 510642, Peoples R China

4.South China Agr Univ, Coll Math & Informat, Guangzhou 510642, Peoples R China

5.Yunfu Subctr Guangdong Lab Lingnan Modern Agr, Yunfu 527400, Peoples R China

6.Guangdong Acad Agr Sci, Inst Facil Agr, Guangzhou 510640, Peoples R China

7.South China Agr Univ, Guangdong Prov Key Lab Agroanim Genom & Mol Breedi, Guangzhou 510642, Peoples R China

关键词: Pigs; Skeletal muscle; Deep learning; Image segmentation; Quantitative analysis

期刊名称:MEAT SCIENCE ( 影响因子:7.1; 五年影响因子:6.6 )

ISSN: 0309-1740

年卷期: 2024 年 213 卷

页码:

收录情况: SCI

摘要: Muscle fiber properties exert a significant influence on pork quality, with cross-sectional area (CSA) being a crucial parameter closely associated with various meat quality indicators, such as shear force. Effectively identifying and segmenting muscle fibers in a robust manner constitutes a vital initial step in determining CSA. This step is highly intricate and time-consuming, necessitating an accurate and automated analytical approach. One limitation of existing methods is their tendency to perform well on high signal-to-noise ratio images of intact, healthy muscle fibers but their lack of validation on more complex image datasets featuring significant morphological changes, such as the presence of ice crystals. In this study, we undertake the fully automatic segmentation of muscle fiber microscopic images stained with myosin adenosine triphosphate (mATPase) activity using a deep learning architecture known as SOLOv2. Our objective is to efficiently derive accurate measurements of muscle fiber size and distribution. Tests conducted on actual images demonstrate that our method adeptly handles the intricate task of muscle fiber segmentation, yielding quantitative results amenable to statistical analysis and displaying reliability comparable to manual analysis.

  • 相关文献
作者其他论文 更多>>