AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Article Link
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

A Transformer-Assisted Cascade Learning Network for Choroidal Vessel Segmentation

Guangdong Provincial Key Laboratory of Intelligent Information Processing, School of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
Institute of Translational Medicine, Shanghai Jiao Tong University, Shanghai 200240, China
Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China
School of Information Technologies, The University of Sydney, Sydney 2006, Australia
Show Author Information

Abstract

As a highly vascular eye part, the choroid is crucial in various eye disease diagnoses. However, limited research has focused on the inner structure of the choroid due to the challenges in obtaining sufficient accurate label data, particularly for the choroidal vessels. Meanwhile, the existing direct choroidal vessel segmentation methods for the intelligent diagnosis of vascular assisted ophthalmic diseases are still unsatisfactory due to noise data, while the synergistic segmentation methods compromise vessel segmentation performance for the choroid layer segmentation tasks. Common cascaded structures grapple with error propagation during training. To address these challenges, we propose a cascade learning segmentation method for the inner vessel structures of the choroid in this paper. Specifically, we propose Transformer-Assisted Cascade Learning Network (TACLNet) for choroidal vessel segmentation, which comprises a two-stage training strategy: pre-training for choroid layer segmentation and joint training for choroid layer and choroidal vessel segmentation. We also enhance the skip connection structures by introducing a multi-scale subtraction connection module designated as MSC, capturing differential and detailed information simultaneously. Additionally, we implement an auxiliary Transformer branch named ATB to integrate global features into the segmentation process. Experimental results exhibit that our method achieves the state-of-the-art performance for choroidal vessel segmentation. Besides, we further validate the significant superiority of the proposed method for retinal fluid segmentation in optical coherence tomography (OCT) scans on a publicly available dataset. All these fully prove that our TACLNet contributes to the advancement of choroidal vessel segmentation and is of great significance for ophthalmic research and clinical application.

Electronic Supplementary Material

Download File(s)
JCST-2308-13679-Highlights.pdf (197.7 KB)

References

[1]

Nickla D L, Wallman J. The multifunctional choroid. Progress in Retinal and Eye Research, Mar. 2010, 29(2): 144–168. DOI: 10.1016/j.preteyeres.2009.12.002.

[2]

Singh S R, Vupparaboina K K, Goud A, Dansingani K K, Chhablani J. Choroidal imaging biomarkers. Survey of Ophthalmology, 2019, 64(3): 312–333. DOI: 10.1016/j.survophthal.2018.11.002.

[3]

Arrigo A, Bordato A, Romano F, Aragona E, Grazioli A, Bandello F, Parodi M B. Choroidal patterns in retinitis pigmentosa: Correlation with visual acuity and disease progression. Translational Vision Science & Technology, 2020, 9(4): 17. DOI: 10.1167/tvst.9.4.17.

[4]

Spaide R F, Fujimoto J G, Waheed N K, Sadda S R, Staurenghi G. Optical coherence tomography angiography. Progress in Retinal and Eye Research, May 2018, 64: 1–55. DOI: 10.1016/j.preteyeres.2017.11.003.

[5]

Fercher A F, Hitzenberger C K, Kamp G, El-Zaiat S Y. Measurement of intraocular distances by backscattering spectral interferometry. Optics Communications, May 1995, 117(1/2): 43–48. DOI: 10.1016/0030-4018(95)00119-S.

[6]

Lavinsky F, Lavinsky D. Novel perspectives on swept-source optical coherence tomography. International Journal of Retina and Vitreous, 2016, 2(1): Article No. 25. DOI: 10.1186/s40942-016-0050-y.

[7]

Sezer T, Altınışık M, Koytak İ A, Özdemir M H. The choroid and optical coherence tomography. Turkish Journal of Ophthalmology, 2016, 46(1): 30–37. DOI: 10.4274/tjo.10693.

[8]

Liu X X, Bi L, Xu Y P, Feng D G, Kim J, Xu X. Robust deep learning method for choroidal vessel segmentation on swept source optical coherence tomography images. Biomedical Optics Express, 2019, 10(4): 1601–1612. DOI: 10.1364/boe.10.001601.

[9]

Qiu B, Huang Z Y, Liu X et al. Noise reduction in optical coherence tomography images using a deep neural network with perceptually-sensitive loss function. Biomedical Optics Express, 2020, 11(2): 817–830. DOI: 10.1364/boe.379551.

[10]

Zhu L, Li J M, Zhu R L et al. Synergistically segmenting choroidal layer and vessel using deep learning for choroid structure analysis. Physics in Medicine & Biology, 2022, 67(8): 085001. DOI: 10.1088/ 1361-6560/ac5ed7.

[11]

Khaing T T, Okamoto T, Ye C et al. ChoroidNET: A dense dilated U-Net model for choroid layer and vessel segmentation in optical coherence tomography images. IEEE Access, 2021, 9: 150951–150965. DOI: 10.1109/ACCESS.2021.3124993.

[12]

Wang X H, Li R, Chen J Y et al. Choroidal vascularity index (CVI)-Net-based automatic assessment of diabetic retinopathy severity using CVI in optical coherence tomography images. Journal of Biophotonics, Jan. 2023, 16(6): e202200370. DOI: 10.1002/jbio.2022 00370.

[13]
Ren S C, Zhou D Q, He S F, Feng J S, Wang X C. Shunted self-attention via multi-scale token aggregation. In Proc. the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp.10843–10852. DOI: 10.1109/CVPR52688.2022.01058.
[14]

Zhang L, Lee K, Niemeijer M, Mullins R F, Sonka M, Abràmoff M D. Automated segmentation of the choroid from clinical SD-OCT. Investigative Ophthalmology & Visual Science, 2012, 53(12): 7510–7519. DOI: 10.1167/iovs.12-10311.

[15]

Chen Q, Fan W, Niu S J, Shi J J, Shen H L, Yuan S T. Automated choroid segmentation based on gradual intensity distance in HD-OCT images. Optics Express, 2015, 23(7): 8974–8994. DOI: 10.1364/oe.23.008974.

[16]

Hussain M A, Bhuiyan A, Ishikawa H, Theodore Smith R, Schuman J S, Kotagiri R. An automated method for choroidal thickness measurement from enhanced depth imaging optical coherence tomography images. Computerized Medical Imaging and Graphics, Jan. 2018, 63: 41–51. DOI: 10.1016/j.compmedimag.2018.01.001.

[17]
Lin G S, Milan A, Shen C H, Reid I. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.5168–5177. DOI: 10.1109/CVPR.2017.549.
[18]

Zheng G, Jiang Y F, Shi C et al. Deep learning algorithms to segment and quantify the choroidal thickness and vasculature in swept-source optical coherence tomography images. Journal of Innovative Optical Health Sciences, 2021, 14(01): 2140002. DOI: 10.1142/S179354582140 0022.

[19]

Zhang Z X, Liu Q J, Wang Y H. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749–753. DOI: 10.1109/LGRS.2018. 2802944.

[20]

Huang K, Su N, Ma X, Li M C, Yang J D, Yuan S T, Liu Y, Chen Q. Choroidal vessel segmentation in SD-OCT with 3D shape-aware adversarial networks. Biomedical Signal Processing and Control, 2023, 84: 104982. DOI: 10.1016/j.bspc.2023.104982.

[21]
Chen M, Wang J C, Oguz I, VanderBeek B L, Gee J C. Automated segmentation of the choroid in EDI-OCT images with retinal pathology using convolution neural networks. In Proc. the 4th International Workshop on Ophthalmic Medical Image Analysis, Sept. 2017, pp.177–184. DOI: 10.1007/978-3-319-67561-9_20.
[22]

Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481–2495. DOI: 10.1109/TPAMI.2016.2644615.

[23]

Zhang H H, Yang J L, Zhou K et al. Automatic segmentation and visualization of choroid in OCT with knowledge infused deep learning. IEEE Journal of Biomedical and Health Informatics, 2020, 24(12): 3408–3420. DOI: 10.1109/JBHI.2020.3023144.

[24]
Bai H R, Cheng S S, Tang J H, Pan J S. Learning a cascaded non-local residual network for super-resolving blurry images. In Proc. the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Jun. 2021, pp.223–232. DOI: 10.1109/CVPRW53098.2021.00031.
[25]
Zhao X Q, Zhang L H, Lu H C. Automatic polyp segmentation via multi-scale subtraction network. In Proc. the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention, Sept. 2021, pp.120–130. DOI: 10.1007/978-3-030-87193-2_12.
[26]
Yang M K, Yu K S, Zhang C, Li Z, Yang K. DenseASPP for semantic segmentation in street scenes. In Proc. the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp.3684–3692. DOI: 10.1109/CVPR.2018.00388.
[27]
Zhao X P, Pang Y W, Zhang L H, Lu H C, Zhang L. Suppress and balance: A simple gated network for salient object detection. In Proc. the 16th European Conference on Computer Vision, Aug. 2020, pp.35–51. DOI: 10.1007/978-3-030-58536-5_3.
[28]
Zhao X Q, Jia H P, Pang Y W et al. M2SNet: Multi-scale in multi-scale subtraction network for medical image segmentation. arXiv: 2303.10894, 2023. https://arxiv.org/abs/2303.10894, Mar. 2024.
[29]
Li J, Fan J S, Zhang Z X. Towards noiseless object contours for weakly supervised semantic segmentation. In Proc. the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp.16835–16844. DOI: 10.1109/CVPR52688.2022.01635.
[30]
Xu L, Ouyang W L, Bennamoun M et al. Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In Proc. the 2021 IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.6964–6973. DOI: 10.1109/ICCV48922.2021.00690.
[31]
Ding M Y, Lian X C, Yang L J, Wang P, Jin X J, Lu Z W, Luo P. HR-NAS: Searching efficient high-resolution neural architectures with lightweight transformers. In Proc. the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2021, pp.2981–2991. DOI: 10.1109/CVPR46437.2021.00300.
[32]
Liu Z, Lin Y T, Cao Y, Hu H, Wei Y X, Zhang Z, Lin S, Guo B N. Swin transformer: Hierarchical vision transformer using shifted windows. In Proc. the 2021 IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.9992–10002. DOI: 10.1109/ICCV48922.2021.00986.
[33]
Wang W H, Xie E Z, Li X et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proc. the 2021 IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.548–558. DOI: 10.1109/ICCV48922.2021.00061.
[34]
Dosovitskiy A, Beyer L, Kolesnikov A et al. An image is worth 16x16 words: Transformers for image recognition at scale. In Proc. the 9th International Conference on Learning Representations, May 2021.
[35]
Oktay O, Schlemper J, Folgoc L L et al. Attention U-Net: Learning where to look for the pancreas. arXiv: 1804.03999, 2018. https://arxiv.org/abs/1804.03999, Mar. 2024.
[36]
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In Proc. the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2015, pp.234–241. DOI: 10.1007/978-3-319-24574-4_28.
[37]
Wei J, Wang S H, Huang Q M. F3Net: Fusion, feedback and focus for salient object detection. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.12321–12328. DOI: 10.1609/aaai.v34i07.6916.
[38]

Kullback S, Leibler R A. On information and sufficiency. The Annals of Mathematical Statistics, 1951, 22(1): 79–86. DOI: 10.1214/aoms/1177729694.

[39]

Bogunovic H, Venhuizen F, Klimscha S et al. RETOUCH: The retinal OCT fluid detection and segmentation benchmark and challenge. IEEE Trans. Medical Imaging, 2019, 38(8): 1858–1874. DOI: 10.1109/TMI.2019.2901398.

Journal of Computer Science and Technology
Pages 286-304
Cite this article:
Wen Y, Wu Y-L, Bi L, et al. A Transformer-Assisted Cascade Learning Network for Choroidal Vessel Segmentation. Journal of Computer Science and Technology, 2024, 39(2): 286-304. https://doi.org/10.1007/s11390-024-3679-2

310

Views

1

Crossref

1

Web of Science

1

Scopus

0

CSCD

Altmetrics

Received: 15 August 2023
Revised: 31 December 2023
Accepted: 20 January 2024
Published: 30 March 2024
© Institute of Computing Technology, Chinese Academy of Sciences 2024
Return