| 163 | 0 | 116 |
| 下载次数 | 被引频次 | 阅读次数 |
进行精确的息肉分割是诊断结肠癌的重要环节，针对目前结肠息肉分割存在分割精度不高、边缘模糊等问题，本文提出一个基于U-Net改进的分割模型。该模型引入了残差连接、通道注意力以及特征增强模块，充分利用通道间的关系信息以及上下文信息来捕捉输入数据中的重要特征，增加了感受野，提高息肉分割精度，同时在训练过程中在二分类交叉熵损失函数的基础上增加IoU(Intersection over Union)损失函数保证训练的稳定性。实验结果表明，改进的U-Net模型在息肉分割的精度以及边缘分割上有一定的提升。
Abstract：Accurate polyp segmentation is an important step in the diagnosis of colon cancer. Aiming at the existing problems of colon polyp segmentation, such as low segmentation accuracy and fuzzy edges, an improved segmentation model based on U-Net was proposed. The model introduces residual connection,channel attention and feature enhancement module,makes full use of the relationship information between channels to capture important features in the input data, increases the receptive field and improves the segmentation accuracy, At the same time, the IoU loss function is added to the binary cross entropy loss function to ensure the stability of training. The experimental results show that the improved U-Net has improved the precision of segmentation for polyp and edge to some extent.
[1] SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].A Cancer Journal for Clinicians, 2021, 71(3):209-249.
[2] LONG J, SHELHAMER E, DARRELL T. Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4):640-651.
[3] RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional networks for biomedical image segmentation[J]. CoRR, 2015, 18(3):234-241.
[4] FOIVOS I, FRANCOIS W, PETER C, et al. ResUNet-a:A deep learning framework for semantic segmentation of remotely sensed data[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2020, 162:94-114.
[5] MAHMUD T, PAUL B, FATTAH S A. Polyp Seg Net:A modified encoder-decoder architecture for automated polyp segmentation from colonoscopy images[J]. Computers in Biology and Medicine, 2021, 128:104119.
[6] ROI N, ISSA N, DROR R, et al. PolypSegNet:Segmentation of polyps based on pyramid vision transformers and residual block for real-time endoscopy imaging[J]. Journal of Pathology Informatics, 2023, 14:100197.
[7] RENE R, ALEXEY B, VLADLEN K.Vision transformers for dense prediction[C]. IEEE International Conference on Computer Vision(CVF), 2021:12179-12188.
[8] WANG W, XIE E, LI X, et al. Pyramid vision transformer:a versatile backbone for dense prediction without convolutions[C]. IEEE International Conference on Computer Vision(CVF), 2021:568-578.
[9] ZHANG Y, LIU H, HU Q. Trans Fuse:Fusing Transformers and CNNs for Medical Image Segmentation[J]. Medical Image Computing and Computer Assisted Intervention,2021,12901:14-24.
[10] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C], IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
[11] WANG Z, ZOU Y, LIU P X. Hybrid Dilation and Attention Residual U-Net for Medical Image Segmentation[J].Computers in Biology and Medicine, 2021, 134(12):104449.
[12] ZHU K, WU J. Residual Attention:A Simple but Effective Method for Multi-Label Recognition[C]. IEEE International Conference on Computer Vision, 2021:184-193.
[13] HU J, SHEN L, SUN G, et al. Squeeze-and-excitation networks[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017:7132-7141.
[14] TOMAR N K, JHA D, BAGCI U, et al. TGANet:text-guided attention for improved polyp segmentation[C].Medical Image Computing and Computer Assisted Intervention(MICCAI), 2023:151-160.
[15] GAO R. Rethink Dilated Convolution for Real-time Semantic Segmentation[J]. Computer Vision and Pattern Recognition, 2021,7:9716-9725.
[16] JHA D, SMEDSRUD P H, RIEGLER M A, et al.Kvasir-SEG:a Segmented Polyp Dataset[C]. IEEE Conference on MultiMedia Modeling, 2020:451-462.
[17] SHOUTEN C, KHNSHGOFTAAR T M, et al. A survey on image data augmentation for deep learning[J]. Journal of Big Data, 2019, 6:1-48.
[18] MICHAEL Y, EVIS S, LEONARDO R, et al. Focus U-Net:A novel dual attention-gated CNN for polyp segmentation during colonoscopy[J]. Computers in Biology and Medicine,2021, 137:104845.
[19] HUANG X, LI Z, ZHANG H, et al. Polyp segmentation network with hybrid channel-spatial attention and pyramid global context guided feature fusion[J]. Computerized Medical Imaging and Graphics, 2022, 98:102072.
[20] LI J, WANG J, LIN F, et al. PRCNet:A parallel reverse convolutional attention network for colorectal polyp segmentation[J]. Biomedical Signal Processing and Control,2024, 95(PA):106336.
基本信息:
DOI：10.14096/j.cnki.cn34-1334/n.2025.03.005
中图分类号:TP18;TP391.41;R735.35
引用信息:
[1]汪琴韵,于瓅.基于改进U-Net模型的结肠息肉分割[J].阜阳师范大学学报(自然科学版),2025,42(01):30-36.DOI:10.14096/j.cnki.cn34-1334/n.2025.03.005.
基金信息:
安徽省重点研究与开发计划项目（202104d07020010）
2025-03-15
2025-03-15