首页 > 过刊浏览>2025年第44卷第2期 >134-144. DOI:10.13300/j.cnki.hnlkxb.2025.02.014
PDF HTML阅读 XML下载 导出引用 引用提醒
基于改进Mask-Scoring R-CNN的肌纤维自动分割与表型计算方法研究
作者:
作者单位:

1.华南农业大学数学与信息学院，广州 510642;2.国家生猪种业工程技术研究中心，广州 510642;3.猪禽种业全国重点实验室，广州 510640;4.华南农业大学动物科学学院，广州 510642

通讯作者:

尹令，E-mail：yin_ling@scau.edu.cn

中图分类号:

TP391

基金项目:

国家自然科学基金项目（32172780）；国家重点研发项目（2023YFD1300202）沃靖杰，E-mail：823549589@qq.com


Automatic segmentation of muscle fiber and methods of calculating phenotype based on improved Mask-Scoring R-CNN
Author:
Affiliation:

1.College of Mathematics and Informatics，South China Agricultural University，Guangzhou 510642，China;2.National Engineering Research Center for Swine Breeding Industry，Guangzhou 510642，China;3.State Key Laboratory of Swine and Poultry Breeding Industry，Guangzhou 510640，China;4.College of Animal Science，South China Agricultural University，Guangzhou 510642，China

  • 摘要
    • |
  • 图/表
    • |
  • 访问统计
    • |
  • 参考文献 [33]
    • |
  • 相似文献 [20]
    • |
  • 引证文献
    • | |
  • 文章评论
    摘要:

    为解决人工手动分割与半自动分割的精度及效率问题以及通用分割模型在面对各种噪声干扰时的表现不足，提出改进Mask-Scoring R-CNN的实例分割模型，实现对肌纤维细胞的高效分割。在Mask-Scoring R-CNN模型中引入CBAM（convolutional block attention module）注意力机制，并对其进行改进，强化模型对特征信息的提取与表达，从而提升分割效果与模型在肌纤维分割任务中的泛化能力。改进Mask-Scoring R-CNN模型在103张测试集的测试结果显示，表型数据测定值的均方根误差均比原模型更小，肌纤维总数均方根误差从2.08降至1.26，面积均方根误差从212.21 μm2降低至181.36 μm2，平均直径均方根误差从2.87 μm降低至1.47 μm。试验结果表明改进后的模型能有效应对含噪声的肌纤维图像，在常见的噪声环境下依然能够准确分割出每个肌纤维。

    Abstract:

    A model for instance segmentation based on improved Mask-Scoring R-CNN was proposed and the efficient segmentation of myofibroblast cells was realized to solve the problems of manual and semi-automatic segmentation with accuracy and efficiency and the inadequate performance of general models for segmentation in encountering various interferences of noisy images.The Convolutional Block Attention Module （CBAM） attention mechanism was introduced into the Mask-Scoring R-CNN model to improve the model.The extraction and expression of feature information by the improved model was enhanced to improve the performance of segmentation and the generalization capability of the model in tasks of segmentation.The results of testing the improved Mask-Scoring R-CNN model on a dataset of 103 test images showed that the root mean square error （RMSE） of phenotype measurement value was smaller than that of the original model，with the RMSE of the total number of myofibers decreased from 2.08 to 1.26，the RMSE of area reduced from 212.21 μm2 to 181.36 μm2，and the RMSE of average diameter decreased from 2.87 μm to 1.47 μm.It is indicated that the improved model can effectively deal with noisy images of myofiber and accurately segment each myofiber even in common noisy environments.

    图1 各种情况下的肌纤维图片Fig.1 Fiber images of various conditions
    图2 两类不同颜色肌纤维对比Fig.2 Comparison of two types of muscle fibers in different colors
    图3 改进的CBAM注意力机制模块Fig.3 Improved CBAM attention mechanism module
    图4 感兴趣区域提取模块Fig.4 RoI extraction
    图5 基于Mask-Scoring R-CNN的图像分割模块Fig.5 Image segmentation based on Mask-Scoring R-CNN
    图6 肌纤维表型数据计算流程Fig.6 Calculation of muscle fiber phenotype data
    图8 不同分割模型对肌纤维细胞图像分割结果Fig.8 Segmentation results of muscle fiber cell images using different segmentation models
    图7 不同分割模型对肌纤维细胞图像分割结果Fig.7 The segmentation results of different segmentation models on the image of muscle fiber cells
    表 1 CBAM模块改进前后性能对比Table 1 The performance comparison before and after the improvement of the CBAM module
    表 2 不同分割模型的性能对比Table 2 The performance comparison of different segmentation models
    参考文献
    [1] 张文秀,朱振才,张永合,等.基于残差块和注意力机制的细胞图像分割方法[J].光学学报,2020,40(17):76-83. ZHANG W X,ZHU Z C,ZHANG Y H,et al.Cell image segmentation method based on residual block and attention mechanism[J].Acta optica sinica,2020,40(17):76-83 (in Chinese with English abstract).
    [2] 朱琳琳,韩璐,杜泓,等.基于U-Net网络的多主动轮廓细胞分割方法研究[J].红外与激光工程,2020,49(S1):151-159.ZHU L L,HAN L,DU H,et al.Multi-active contour cell segmentation method based on U-Net network[J].Infrared and laser engineering,2020,49(S1):151-159 (in Chinese with English abstract).
    [3] 姚超,倪福川,李国亮.基于深度学习的图像分割在畜禽养殖中的应用研究进展[J].华中农业大学学报,2023,42(3):39-46.YAO C,NI F C,LI G L.Research progress on application of image segmentation based on deep learning in poultry and livestock farming[J].Journal of Huazhong Agricultural University,2023,42(3):39-46(in Chinese with English abstract).
    [4] 邓颖,吴华瑞,朱华吉.基于实例分割的柑橘花朵识别及花量统计[J].农业工程学报,2020,36(7):200-207.DENG Y,WU H R,ZHU H J.Recognition and counting of Citrus flowers based on instance segmentation[J].Transactions of the CSAE,2020,36(7):200-207(in Chinese with English abstract).
    [5] 陈燕,李想,曹勉,等.基于语义分割与实例分割的玉米茎秆截面参数测量方法[J].农业机械学报,2023,54(6):214-222.CHEN Y,LI X,CAO M,et al.Measurement of maize stem cross section parameters based on semantic segmentation and instance segmentation[J].Transactions of the CSAM,2023,54(6):214-222(in Chinese with English abstract).
    [6] 宋余庆,杨东川,徐立章,等.基于DBSE-Net的大田稻穗图像分割[J].农业工程学报,2022,38(13):202-209.SONG Y Q,YANG D C,XU L Z,et al.Segmenting field rice panicle images using DBSE-Net[J].Transactions of the CSAE,2022,38(13):202-209(in Chinese with English abstract).
    [7] DE SOUSA REIS V C,FERREIRA I M,DURVAL M C,et al.Measuring water holding capacity in pork meat images using deep learning[J/OL].Meat science,2023,200:109159[2023-10-18].https://doi.org/10.1016/j.meatsci.2023.109159.
    [8] XIE L,QIN J,RAO L,et al.Accurate prediction and genome-wide association analysis of digital intramuscular fat content in longissimus muscle of pigs[J].Animal genetics,2021,52(5):633-644.
    [9] CHEN D,WU P X,WANG K,et al.Combining computer vision score and conventional meat quality traits to estimate the intramuscular fat content using machine learning in pigs[J/OL].Meat science,2022,185:108727[2023-10-18].https://doi.org/10.1016/j.meatsci.2021.108727.
    [10] VALOUS N A,MENDOZA F,SUN D W,et al.Supervised neural network classification of pre-sliced cooked pork ham images using quaternionic singular values[J].Meat science,2010,84(3):422-430.
    [11] IQBAL A,VALOUS N A,MENDOZA F,et al.Classification of pre-sliced pork and Turkey ham qualities based on image colour and textural features and their relationships with consumer responses[J].Meat science,2010,84(3):455-465.
    [12] MAYEUF-LOUCHART A,HARDY D,THOREL Q,et al.MuscleJ:a high-content analysis method to study skeletal muscle with a new Fiji tool[J/OL].Skeletal muscle,2018,8(1):25[2023-10-18].https://doi.org/10.1186/s13395-018-0171-0.
    [13] BABCOCK L W,HANNA A D,AGHA N H,et al.MyoSight-semi-automated image analysis of skeletal muscle cross sections[J/OL].Skeletal muscle,2020,10(1):33[2023-10-18].https://doi.org/10.1186/s13395-020-00250-5.
    [14] ENCARNACION-RIVERA L,FOLTZ S,HARTZELL H C ,et al.Myosoft:an automated muscle histology analysis tool using machine learning algorithm utilizing Fiji/ImageJ software[J/OL].PLoS One,2020,15(3):e0229041[2023-10-18].https://doi.org/10.1371/journal.pone.0229041.
    [15] MATARNEH S K,SILVA S L,GERRARD D E.New insights in muscle biology that alter meat quality[J].Annual review of animal biosciences,2021,9:355-377.
    [16] CHARLES J,KISSANE R,HOEHFURTNER T,et al.From fibre to function:are we accurately representing muscle architecture and performance？ [J].Biological reviews of the Cambridge philosophical society ,2022,97(4):1640-1676.
    [17] SMITH L R,BARTON E R.SMASH - semi-automatic muscle analysis using segmentation of histology:a MATLAB application[J/OL].Skeletal muscle,2014,4(1):21[2023-10-18].https://doi.org/10.1186/2044-5040-4-21.
    [18] WANG Z Z.A semi-automatic method for robust and efficient identification of neighboring muscle cells[J].Pattern recognition,2016,53:300-312.
    [19] KASTENSCHMIDT J M,ELLEFSEN K L,MANNAA A H,et al.QuantiMus:a machine learning-based approach for high precision analysis of skeletal muscle morphology[J/OL].Frontiers in physiology,2019,10:1416[2023-10-18].https://doi.org/10.3389/fphys.2019.01416.
    [20] LI Y,YANG Z,WANG Y M,et al.A neural network approach to analyze cross-sections of muscle fibers in pathological images[J].Computers in biology and medicine,2019,104:97-104.
    [21] WEN Y,MURACH K A,VECHETTI I J Jr,et al.MyoVision:software for automated high-content analysis of skeletal muscle immunohistochemistry[J].Journal of applied physiology,2017,124(1):40-51.
    [22] WOO S,PARK J,LEE J Y, et al.CBAM:convolutional block attention module[C]// 2018 European conference on computer vision(ECCV),September 8-14,2018.Munich,Germany.Munich:Springer,2018:3-19.
    [23] HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on computer vision and pattern recognition,June 18-23,2018.Salt Lake City,UT.IEEE,2018:7132-7141.
    [24] JADERBERG M,SIMONYAN K,ZISSERMAN A,et al.Spatial transformer networks[C]//NeurIPS 2015 advances in neural information processing systems,December 7-12,2015,Montreal,Canada.Montreal:NeurIPS,2015,28:2017-2025.
    [25] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]// 2016 IEEE conference on computer vision and pattern recognition(CVPR),June 27-30,2016.Las Vegas,USA.Las Vegas:IEEE,2016:770-778.
    [26] HE K M,ZHANG X Y,REN S Q,et al.Identity mappings in deep residual networks[C]// 2016 European conference on computer vision(ECCV),October 11-14,2016.Amsterdam,Netherlands.Amsterdam:Springer,2016:630-645.
    [27] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]// 2017 IEEE conference on computer vision and pattern recognition(CVPR),July 21-26,2017.Honolulu,USA.Honolulu:IEEE,2017:2117-2125.
    [28] HUANG Z J,HUANG L C,GONG Y C,et al.Mask-scoring R-CNN[C]// 2019 IEEE/CVF conference on computer vision and pattern recognition(CVPR),June 16-20,2019.Long Beach,USA.Long Beach:IEEE,2019:6409-6418.
    [29] HE K M,GKIOXARI G,DOLLAR P,et al.Mask-R-CNN[C]// 2017 IEEE international conference on computer vision(ICCV),October 22-29,2017.Venice,Italy.Venice:IEEE,2017:2961-2969.
    [30] WANG X L,KONG T,SHEN C H,et al.SOLO:segmenting objects by locations[C]// 2020 European conference on computer vision(ECCV),August 23-28,2020.Glasgow,UK.Glasgow:Springer,2020:649-665.
    [31] WANG X L,ZHANG R F,KONG T,et al.Solov2:dynamic and fast instance segmentation[C]// 2020 Advances in neural information processing systems(NeurIPS),December 6-12,2020.NeurIPS,2020,33:17721-17732.
    [32] KIRILLOV A,WU Y X,HE K M,et al.PointRend:image segmentation As rendering[C]// 2020 IEEE/CVF conference on computer vision and pattern recognition(CVPR),June 14-19,2020.Seattle,USA.IEEE,2020:9799-9808.
    [33] WANG Q L,WU B G,ZHU P F,et al．ECA-net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR),June 13-19,2020．Seattle,USA．IEEE,2020:11531-11539．
    引证文献
引用本文

沃靖杰,田绪红,尹令,杨杰,姚泽锴,蔡更元.基于改进Mask-Scoring R-CNN的肌纤维自动分割与表型计算方法研究[J].华中农业大学学报,2025,44(2):134-144

复制
分享
文章指标
  • 点击次数:9
  • 下载次数: 15
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-10-18
  • 在线发布日期: 2025-04-02
文章二维码

联系我们

电话： 027-87287437，027-87287364
邮政编码： 430070
E-mail：hnlkxb@mail.hzau.edu.cn
地址： 武汉市洪山区狮子山街1号

期刊订阅 Email Alert 国际标准刊号：ISSN 1000-2421 国外邮发代号：BM 3816 国内刊号：CN 42-1181/S 国内发行代号：38-120

华中农业大学学报（自然科学版） ® 2025 版权所有   技术支持：北京勤云科技发展有限公司