文章详情

题名 · 作者 · 摘要 · 关键词 · DOI · 参考文献

基于MedSAM模型的视网膜血管图像分割

刘雅卉

(浙江中医药大学,浙江 杭州 310053)

栏目:人工智能 · 第 2025 年第 11 期 · 页码:54-58 · 2096-4706(2025)11-0054-05 · 中图分类号:TP391.4;TP18 · 文献标识码:A · DOI:10.19850/j.cnki.2096-4706.2025.11.011

摘要

眼底图像中视网膜血管的分割对于早期发现和诊断眼部疾病至关重要。传统视网膜自动分割方法依赖大量的标注数据进行模型预训练,然而实际应用中视网膜图像数据集规模有限且标注成本较高。该研究应用了一种通用医学图像分割模型Medical Segment Anything Model(MedSAM)进行迁移学习,实现了数据集有限情况下的视网膜准确分割。本研究在主流视网膜眼底图像数据集CHASE_DB1和STARE上进行了评估。实验结果表明,相比于U-Net和U-Net++模型,MedSAM在训练过程中损失能更快收敛至稳定区间,并且分割效果在Dice Score、IoU和PA三项指标上均有领先,展示了优秀的分割性能,为临床诊断提供了强大的工具。

关键词

MedSAM;视网膜;图像分割;医学图像

参考文献

  1. [1] JIANG Y,WU C,WANG G,et al. MFI-Net: A Multi-Resolution Fusion Input Network for Retinal Vessel Segmentation [J/OL].PLoS ONE,2021,16(7):e0253056(2021-07-12).https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0253056.
  2. [2] 张文豪,瞿绍军,颜美丽.基于深度学习的视网膜血管分割研究进展 [J].计算机应用研究,2025,42(5):1299-1311.
  3. [3] WIESTLER B,MENZE B. Deep Learning for Medical Image Analysis: A Brief Introduction [J].Neuro-oncology Advances,2020,2(Supplement_4):IV35-IV41.
  4. [4] MA J,HE Y,LI F,et al. Segment Anything in Medical Images [J].Nature Communications,2024,15(1):654(2023-10-24).https://doi.org/10.1038/s41467-024-44824-z.
  5. [5] KIRILLOV A,MINTUN E,RAVI N,et al. Segment Anything [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Paris:IEEE,2023:4015-4026.
  6. [6] RONNEBERGER O,FISCHER P,BROX T. U-net: Convolutional Networks for Biomedical Image Segmentation [C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015.Munich:Springer International Publishing,2015:234-241.
  7. [7] ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al. Unet++: A Nested U-net Architecture for Medical Image Segmentation [C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support:4th International Workshop,DLMIA 2018.Granada:Springer International Publishing,2018:3-11.
  8. [8] LISKOWSKI P,KRAWIEC K. Segmenting Retinal Blood Vessels with Deep Neural Networks [J].IEEE Transactions on Medical Imaging,2016,35(11):2369-2380.
  9. [9] KHALAF A F,YASSINE I A,FAHMY A S. Convolutional Neural Networks for Deep Feature Learning in Retinal Vessel Segmentation [C]//2016 IEEE International Conference on Image Processing(ICIP).Phoenix:IEEE,2016:385-388.
  10. [10] TAN J H,ACHARYA U R,BHANDARY S V,et al. Segmentation of Optic Disc,Fovea and Retinal Vasculature Using a Single Convolutional Neural Network [J].Journal of Computational Science,2017,20:70-79.
  11. [11] OLIVEIRA A,PEREIRA S,SILVA C A. Retinal Vessel Segmentation Based on Fully Convolutional Neural Networks [J].Expert Systems with Applications,2018,112:229-242.
  12. [12] LI W,ZHANG M,CHEN D. Fundus Retinal Blood Vessel Segmentation Based on Active Learning [C]//2020 International Conference on Computer Information and Big Data Applications(CIBDA).Guiyang:IEEE,2020:264-268.
  13. [13] ATLI I,GEDIK O S. Sine-Net: A Fully Convolutional Deep Learning Architecture for Retinal Blood Vessel Segmentation [J].Engineering Science and Technology,2021,24(2):271-283.
  14. [14] MISHRA S,CHEN D Z,HU X S. A Data-aware Deep Supervised Method for Retinal Vessel Segmentation [C]//2020 IEEE 17th International Symposium on Biomedical Imaging(ISBI).Iowa City:IEEE,2020:1254-1257.
  15. [15] JIN Q,MENG Z,PHAM T D,et al. Dunet: A Deformable Network for Retinal Vessel Segmentation [J].Knowledge-Based Systems,2019,178:149-162.
  16. [16] VASWANI A,SHAZEER N,PARMAR N,et al. Attention Is All You Need [C]//NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc,2017:6000-6010.
  17. [17] OWEN C G,RUDNICKA A R,MULLEN R,et al. Measuring Retinal Vessel Tortuosity in 10-Year-Old Children: Validation of The Computer-Assisted Image Analysis of The Retina(CAIAR)Program [J].Investigative Ophthalmology & Visual Science,2009,50(5):2004-2010.
  18. [18] HOOVER A D,KOUZNETSOVA V,GOLDBAUM M. Locating Blood Vessels in Retinal Images by Piecewise Threshold Probing of A Matched Filter Response [J].IEEE Transactions on Medical Imaging,2000,19(3):203-210.
  19. [19] JIANG Y,ZHANG H,TAN N,et al. Automatic Retinal Blood Vessel Segmentation Based on Fully Convolutional Neural Networks [J].Symmetry,2019,11(9):1112(2019-09-03).https://doi.org/10.3390/sym11091112.

作者简介

刘雅卉(2004—),女,汉族,江西吉安人,本科在读,研究方向:计算机视觉。