Vessel Segmentation in Fundus Images with Multi-Scale Feature Extraction and Disentangled Representation
Source abstract
Abstract
Vessel segmentation in fundus images is crucial for diagnosing eye diseases. The rapid development of deep learning has greatly improved segmentation accuracy. However, the scale of the retinal blood-vessel structure varies greatly, and there is a lot of noise unrelated to blood-vessel segmentation in fundus images, which increases the complexity and difficulty of the segmentation algorithm. Comprehensive consideration of factors like scale variation and noise suppression is imperative to enhance segmentation accuracy and stability. Therefore, we propose a retinal vessel segmentation method based on multi-scale feature extraction and decoupled representation. Specifically, we design a multi-scale feature extraction module at the skip connections, utilizing dilated convolutions to capture multi-scale features and further emphasizing crucial information through channel attention modules. Additionally, to separate useful spatial information from redundant information and enhance segmentation performance, we introduce an image reconstruction branch to assist in the segmentation task. The specific approach involves using a disentangled representation method to decouple the image into content and style, utilizing the content part for segmentation tasks. We conducted experiments on the DRIVE, STARE, and CHASE_DB1 datasets, and the results showed that our method outperformed others, achieving the highest accuracy across all three datasets (DRIVE:0.9690, CHASE_DB1:0.9757, and STARE:0.9765).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Retinal Imaging and Analysis · Digital Imaging for Blood Diseases · Retinal and Optic Conditions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
College of Bioengineering, Chongqing University, Chongqing 400044, China
Funding
National Key Research and Development Program of China · special project of Technological Innovation and Application Development of Chongqing
References (51)
Show source-provided references
1. A deep learning system for detecting diabetic retinopathy across the disease spectrum10.1038/s41467-021-23458-5 ↗
2. DeepDRiD: Diabetic retinopathy—Grading and image quality estimation challenge10.1016/j.patter.2022.100512 ↗
3. Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification10.1109/TMI.2006.879967 ↗
4. Scs-net: A scale and context sensitive network for retinal vessel segmentation10.1016/j.media.2021.102025 ↗
5. A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification10.1016/j.media.2020.101905 ↗
6. Multi-level deep supervised networks for retinal vessel segmentation10.1007/s11548-017-1619-0 ↗
7. TMM-Nets: Transferred Multi-to Mono-Modal Generation for Lupus Retinopathy Diagnosis10.1109/TMI.2022.3223683 ↗
8. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
9. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
10. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
11. ECSU-net: An embedded clustering sliced U-net coupled with fusing strategy for efficient intervertebral disc segmentation and classification10.1109/TIP.2021.3136619 ↗
12. Lightweight attention convolutional neural network for retinal vessel image segmentation10.1109/TII.2020.2993842 ↗
13. Learning disentangled representations in the imaging domain10.1016/j.media.2022.102516 ↗
14. Liu, X., Thermos, S., Chartsias, A., O’Neil, A., and Tsaftaris, S.A. (2021). Disentangled representations for domain-generalized cardiac segmentation. The Statistical Atlases and Computational Models of the Heart, Springer.10.1007/978-3-030-68107-4_19 ↗
15. EAPT: Efficient attention pyramid transformer for image processing10.1109/TMM.2021.3120873 ↗
16. Modified GAN-cAED to minimize risk of unintentional liver major vessels cutting by controlled segmentation using CTA/SPET-CT10.1109/TII.2021.3064369 ↗
17. Dual encoder-based dynamic-channel graph convolutional network with edge enhancement for retinal vessel segmentation10.1109/TMI.2022.3151666 ↗
18. Global Transformer and Dual Local Attention Network via Deep-Shallow Hierarchical Feature Fusion for Retinal Vessel Segmentation10.1109/TCYB.2022.3194099 ↗
19. Li, M., Zhou, S., Chen, C., Zhang, Y., Liu, D., and Xiong, Z. (2022, January 28–31). Retinal vessel segmentation with pixel-wise adaptive filters. Proceedings of the IEEE 19th International Symposium on Biomedical Imaging, Kolkata, India.10.1109/ISBI52829.2022.9761634 ↗
20. Xu, W., Yang, H., Zhang, M., Pan, X., Liu, W., and Yan, S. (2022, January 28–31). Retinal Vessel Segmentation with VAE Reconstruction and Multi-Scale Context Extractor. Proceedings of the IEEE 19th International Symposium on Biomedical Imaging, Kolkata, India.10.1109/ISBI52829.2022.9761563 ↗
21. Huang, X., Liu, M.Y., Belongie, S., and Kautz, J. (2018, January 8–14). Multimodal unsupervised image-to-image translation. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01219-9_11 ↗
22. Disentangled representation learning in cardiac image analysis10.1016/j.media.2019.101535 ↗
23. Meng, Q., Pawlowski, N., Rueckert, D., and Kainz, B. (2019). Representation disentanglement for multi-task learning with application to fetal ultrasound. The Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis, Springer.10.1007/978-3-030-32875-7_6 ↗
24. Disentangled representation learning for octa vessel segmentation with limited training data10.1109/TMI.2022.3193029 ↗
25. Esser, P., Sutter, E., and Ommer, B. (2018, January 18–22). A variational u-net for conditional appearance and shape generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00923 ↗
26. Disentangled representation and cross-modality image translation based unsupervised domain adaptation method for abdominal organ segmentation10.1007/s11548-022-02590-7 ↗
27. Huang, X., and Belongie, S. (2017, January 21–26). Arbitrary style transfer in real-time with adaptive instance normalization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/ICCV.2017.167 ↗
28. Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Jorge Cardoso, M. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. The Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.10.1007/978-3-319-67558-9_28 ↗
29. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
30. Ridge-based vessel segmentation in color images of the retina10.1109/TMI.2004.825627 ↗
31. Measuring retinal vessel tortuosity in 10-year-old children: Validation of the computer-assisted image analysis of the retina (CAIAR) program10.1167/iovs.08-3018 ↗
32. A cross-modality learning approach for vessel segmentation in retinal images10.1109/TMI.2015.2457891 ↗
33. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response10.1109/42.845178 ↗
34. Li, L., Verma, M., Nakashima, Y., Nagahara, H., and Kawasaki, R. (2020, January 1–5). Iternet: Retinal image segmentation utilizing structural redundancy in vessel networks. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.10.1109/WACV45572.2020.9093621 ↗
35. Hard attention net for automatic retinal vessel segmentation10.1109/JBHI.2020.3002985 ↗
36. Retinal vessel segmentation with skeletal prior and contrastive loss10.1109/TMI.2022.3161681 ↗
37. Retinal vessel delineation using a brain-inspired wavelet transform and random forest10.1016/j.patcog.2017.04.008 ↗
38. Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv.10.1109/NAECON.2018.8556686 ↗
39. Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation10.1109/TBME.2018.2828137 ↗
40. Retinal vessel segmentation based on fully convolutional neural networks10.1016/j.eswa.2018.06.034 ↗
41. Retinal vessel segmentation method based on two-stream networks10.3788/AOS202040.0410002 ↗
42. CSU-Net: A context spatial U-Net for accurate blood vessel segmentation in fundus images10.1109/JBHI.2020.3011178 ↗
43. MFI-Net: Multiscale Feature Interaction Network for Retinal Vessel Segmentation10.1109/JBHI.2022.3182471 ↗
44. Liu, Y., Shen, J., Yang, L., Yu, H., and Bian, G. (2023). Wave-Net: A lightweight deep network for retinal vessel segmentation from fundus images. Comput. Biol. Med., 152.10.1016/j.compbiomed.2022.106341 ↗
45. Du, H., Zhang, X., Song, G., Bao, F., Zhang, Y., Wu, W., and Liu, P. (2023). Retinal blood vessel segmentation by using the MS-LSDNet network and geometric skeleton reconnection method. Comput. Biol. Med., 153.10.1016/j.compbiomed.2022.106416 ↗
46. Retinal vessel segmentation by using AFNet10.1007/s00371-022-02456-8 ↗
47. A hybrid deep segmentation network for fundus vessels via deep-learning framework10.1016/j.neucom.2021.03.085 ↗
48. Learning multi-scale deep fusion for retinal blood vessel extraction in fundus images10.1007/s00371-022-02600-4 ↗
49. Li, J., Gao, G., Yang, L., and Liu, Y. (2023). GDF-Net: A multi-task symmetrical network for retinal vessel segmentation. Biomed. Signal Process. Control, 81.10.1016/j.bspc.2022.104426 ↗
50. Zhuang, J. (2018). LadderNet: Multi-path networks based on U-Net for medical image segmentation. arXiv.
51. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.