Optics and Precision Engineering, Volume. 31, Issue 18, 2765(2023)

Polyp image segmentation based on multi-scale ResNeSt-50 aggregation network and message passing

Ping XIA1...2, Guangyi ZHANG1,2, Bangjun LEI1,2,*, Yaobing ZOU1,2, and Tinglong TANG12 |Show fewer author(s)
Author Affiliations
  • 1Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering, Three Gorges University, Yichang443002, China
  • 2College of Computer and Information Technology, Three Gorges University, Yichang44300, China
  • show less
    Figures & Tables(20)
    Model of this paper
    Split-attention in ResNeSt Block
    ResNeSt-50 encoding structure of this paper
    RFB and dense aggregation module
    Message propagation of confidence level
    Segmentation result of testing on the ETIS-LaribPolypDB dataset
    Segmentation result of testing on the Kvasir-SEG[34] dataset
    Segmentation result of testing small lesion on ETIS-LaribPolypDB[1]dataset
    Comparison of the effect of the model used in this paper and PraNet model in segmenting minimal lesions
    Segmentation result of testing on the ETIS-LaribPolypDB[1]dataset
    • Table 1. Five datasets used in this paper

      View table
      View in Article

      Table 1. Five datasets used in this paper

      数据集Kvasir-SEG34CVC-ClinicDB33ColonDB35ETIS-LaribPolypDB 1CVC-30036
      数 量1 00061238019660
      图像大小500+×500+384×288574×5001 225×966574×500
    • Table 2. Allocation of training dataset and test dataset of experiment

      View table
      View in Article

      Table 2. Allocation of training dataset and test dataset of experiment

      训练集测试集
      实验AKvasir-SEG(900),CVC-ClinicDB(550)Kvasir-SEG(100)
      实验BKvasir-SEG(900),CVC-ClinicDB(550)CVC-ClinicDB(62)
      实验CKvasir-SEG(900),CVC-ClinicDB(550)ColonDB(380)
      实验DKvasir-SEG(900),CVC-ClinicDB(550)ETIS-LaribPolypDB (196)
      实验EKvasir-SEG(900),CVC-ClinicDB(550)CVC-300(60)
    • Table 3. Ablation experiment of ResNeSt-50 module(training on Kvasir-SEG and ClinicDB dataset)

      View table
      View in Article

      Table 3. Ablation experiment of ResNeSt-50 module(training on Kvasir-SEG and ClinicDB dataset)

      模 型测试集mDicemIoUSmeasureMAE
      模型aColonDB0.5120.4440.7120.061
      模型b0.6080.5230.7600.052
      模型c0.6760.6060.7990.043
      模型d0.7570.675n/an/a
      模型a

      ETIS-

      LaribPolypDB

      0.3980.3350.6840.036
      模型b0.5220.4470.7380.026
      模型c0.6140.5470.7810.028
      模型d0.7060.628n/an/a
    • Table 4. Effect of multi-scale training on model segmentation

      View table
      View in Article

      Table 4. Effect of multi-scale training on model segmentation

      mDicemIoUSmeasureMAE
      未采用多尺度训练0.8880.8270.9080.031
      使用多尺度训练0.9130.8580.9250.023
    • Table 5. Effect of RAdam optimizer on model segmentation

      View table
      View in Article

      Table 5. Effect of RAdam optimizer on model segmentation

      EpochmDicemIoUSmeasureMAE
      Adam200.9040.8510.9200.027
      RAdam300.9130.8580.9250.023
    • Table 6. Trained on CVC-ClinicDB33,Kvasir-SEG34dataset, compare the test results on Kvasir-SEG34dataset

      View table
      View in Article

      Table 6. Trained on CVC-ClinicDB33,Kvasir-SEG34dataset, compare the test results on Kvasir-SEG34dataset

      mDicemIoUSmeasureMAE
      本文编码-解码器0.9130.8580.9250.023
      本文编码-解码器+TTA0.9150.8610.9250.023
      本文模型0.9160.8630.9210.023
    • Table 7. Trained on the CVC-ClinicDB33,Kvasir-SEG34dataset, respectively compare the test results on ColonDB35,ETIS-LaribPolypDB1,CVC-30036

      View table
      View in Article

      Table 7. Trained on the CVC-ClinicDB33,Kvasir-SEG34dataset, respectively compare the test results on ColonDB35,ETIS-LaribPolypDB1,CVC-30036

      ColonDB35ETIS-LaribPolypDB1CVC-30036
      mDicemIoUmDicemIoUmDicemIoU
      本文编码-解码器0.7570.6750.7060.6280.8580.781
      本文编码-解码器 +TTA0.7830.7000.7640.6860.8690.797
      本文模型0.7860.7030.7700.6910.8710.798
    • Table 8. Trained on CVC-ClinicDB33,Kvasir-SEG34dataset, compare the test results on Kvasir-SEG34dataset

      View table
      View in Article

      Table 8. Trained on CVC-ClinicDB33,Kvasir-SEG34dataset, compare the test results on Kvasir-SEG34dataset

      mDicemIoUSmeasureMAE
      U-Net90.8180.7460.8580.055
      U-Net++100.8210.7430.8620.048
      ResUnet++110.7340.639n/an/a
      SFA380.7230.6110.7820.075
      PraNet120.8980.8400.9150.030
      本文方法0.9160.8630.9210.023
    • Table 9. Trained on CVC-ClinicDB,Kvasir-SEGdataset, compare the test results on ETIS-LaribPolypDBdataset

      View table
      View in Article

      Table 9. Trained on CVC-ClinicDB,Kvasir-SEGdataset, compare the test results on ETIS-LaribPolypDBdataset

      mDicemIoUSmeasureMAE
      U-Net90.0550.0460.5170.021
      U-Net++100.0930.0780.5450.018
      SFA380.0120.0060.4250.130
      ResUnet++110.0160.0090.5000.011
      PraNet120.0990.0730.5150.074
      本文方法0.4870.4010.7340.003
    • Table 10. Trained on the CVC-ClinicDB33,Kvasir-SEG34dataset, respectively compare the test results on ColonDB35,ETIS-LaribPolypDB1,CVC-30036dataset

      View table
      View in Article

      Table 10. Trained on the CVC-ClinicDB33,Kvasir-SEG34dataset, respectively compare the test results on ColonDB35,ETIS-LaribPolypDB1,CVC-30036dataset

      ColonDB35ETIS-LaribPolypDB1CVC-30036
      mDiceMIoUmDiceMIoUmDiceMIoU
      U-Net90.5120.4440.3980.3350.710.627
      U-Net++100.4830.4100.4010.3440.7070.624
      ResUnet++11n/an/an/an/an/an/a
      SFA380.4690.3470.2970.2170.4670.329
      PraNet120.7090.6400.6280.5670.8710.797
      本文方法0.7860.7030.7700.6910.8710.798
    Tools

    Get Citation

    Copy Citation Text

    Ping XIA, Guangyi ZHANG, Bangjun LEI, Yaobing ZOU, Tinglong TANG. Polyp image segmentation based on multi-scale ResNeSt-50 aggregation network and message passing[J]. Optics and Precision Engineering, 2023, 31(18): 2765

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Information Sciences

    Received: Mar. 30, 2023

    Accepted: --

    Published Online: Oct. 12, 2023

    The Author Email: LEI Bangjun (Bangjun.Lei@ieee.org)

    DOI:10.37188/OPE.20233118.2765

    Topics