Abstract
Deep learning has recently received attention as one of the most popular methods for boosting performance in different sectors, including medical image analysis, pattern recognition and classification. Diabetic retinopathy becomes an increasingly popular cause of vision loss in diabetic patients.. Retinal vascular status in fundus images is a reliable biomarker for diabetes, hypertension and many ophthalmic diseases. Therefore, accurate segmentation of retinal vessels is of great significance for the diagnosis of many diseases. However, due to the inherent complexity of the retina itself and the lack of data, it is difficult to obtain the ideal accuracy of the segmentation results of the vascular end. To solve this problem, we propose an innovative multi-dimensional deep convolutional Neural network (MDUNet) to segment the retinal vessels in fundus images. The fusion of cross-dimensional transformation makes full use of the relevance of information between different dimensions. Meanwhile, the self-attention calculation method of cross-window is applied to effectively reduce the computational complexity. MDUNet is proposed to provide a research basis for the application of Transformer structure in the field of medical image segmentation. The proposed method is evaluated on different evaluation metrics such as sensitivity, specificity, and accuracy. Experimental results on six public datasets show that the proposed work MDUNet achieves better vessel segmentation accuracy with a smaller number of parameters compared with classical models such as U-Net, SegNet, and DeepLabv3+.
Similar content being viewed by others
References
Akram MU, Khalid S, Khan SA (2013) Identification and classification of microaneurysms for early detection of diabetic retinopathy. Pattern Recogn 46:107–116
Algorithm Validation | Medical Image Analysis Group (n.d.). https://medimrg.webs.ull.es/research/retinal-imaging/rim-one/
Aslan M F, Ceylan M, Durdu A (2018) Segmentation of Retinal Blood Vessel Using Gabor Filter and Extreme Learning Machines, 2018 International Conference on Artificial Intelligence and Data Processing (IDAP),28–30 September 201
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495
Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder- Decoder with Atrous Separable Convolution for Semantic Image Seg- mentation, in Proc Eur Conf Comput Vision, pp 833–851
Drishti-GS Dataset Webpage (n.d.) http://cvit.iiit.ac.in/projects/mip/drishti-gs/mip-dataset2/Home.php
Fan Z, Lu J, Wei C, Huang H, Cai X, Chen X (2019) A hierarchical image matting model for blood vessel segmentation in fundus images. IEEE Trans Image Process 28:2367–2377
Feng S, Zhuo Z, Pan D, Tian Q (2020) CcNet: a cross-connected convolutional network for segmenting retinal vessels using multi-scale features. Neurocomputing 392:268–276
Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, Barman SA (2012) An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans Biomed Eng 59:2538–2548
Gegundez-Arias ME, Marin-Santos D, Perez-Borrero I, Vasallo-Vazquez MJ (2021) A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-net model. Comput Methods Prog Biomed 205:106081
Jayachandran A, David DS (2018) Textures and intensity histogram based retinal image classification system using hybrid colour structure descriptor. Biomed Pharm J 11(1):577–582
Jayachandran A, Dhanasekaran R (2014) Brain tumor severity analysis using modified multi-texton histogram and hybrid kernel SVM. Int J Imaging Syst Technol 24(1):72–82
Jayachandran A, Dhanasekaran R (2017) Multi class brain tumor classification of MRI images using hybrid structure descriptor and fuzzy logic based RBF kernel SVM. Iran J Fuzzy Syst 14(3):41–54
Jayachandran A, Kharmega Sundararaj G (2016) Abnormality segmentation and classification of multi model brain tumor in MR images using fuzzy based hybrid kernel SVM. Int J Fuzzy Syst 17(3):434–443
Jin Q, Meng Z, Pham TD, Chen Q, Wei L, Su R (2019) DUNet: a deformable network for retinal vessel segmentation. Knowl-Based Syst 178:149–162
Lam BSY, Gao Y, Liew AW (2010) General retinal vessel segmentation using regularization-based multiconcavity modeling. IEEE Trans Med Imaging 29:1369–1381
Lan Y, Xiang Y, Zhang L (2020) An elastic interaction-based loss function for medical image segmentation. Lect Notes Comput Sci (Including Subser Lect Notes Artif Intell Lect Notes Bioinf) LNCS 12265:755–764
Leopold HA, Orchard J, Zelek JS, Lakshminarayanan V (2019) PixelBNN: Augmenting the Pixelcnn with batch normalization and the presentation of a fast architecture for retinal vessel segmentation. J Imaging 5(2): 26. https://doi.org/10.3390/jimaging5020026
Li X, Jiang Y, Li M, Yin S (2021) Lightweight attention convolutional neural network for retinal vessel image segmentation. IEEE Trans Ind Informat 17:1958–1967
Lin YI, Zhang H, Gu Z et al (2019) CE-Net: Context Encoder Network for 2D Medical Image Segmentation. IEEE Trans Med Imaging 38:2281–2292
Mahiba C, Jayachandran A (2019) Severity analysis of diabetic retinopathy in retinal images using hybrid structure descriptor and modified CNNs. Meas 135:762–767
Milletari F et al. (n.d.) V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation, in 2016 Fourth International Conference on 3D Vision (3DV), IEEE
Odstrcilik J, Kolar R, Budai A, Hornegger J, Jan J, Gazarek J, Kubena T, Cernosek P, Svoboda O, Angelopoulou E (2013) Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database. IET Image Process 7(4):373–383
Owen CG, Rudnicka AR, Mullen R, Barman SA, Monekosso D, Whincup PH, Ng J, Paterson C (2009) Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (CAIAR) program. Invest Ophthalmol Vis Sci 50:2004–2010
Palanivel DA, Natarajan S, Gopalakrishnan S (2020) Retinal vessel segmentation using multifractal characterization. Appl Soft Comput J 94:106439
Rezaee K, Haddadnia J, Tashk A (2017) Optimized clinical segmen- tation of retinal blood vessels by using combination of adaptive filtering, fuzzy entropy and skeletonization. Appl Soft Comput 52:937–951
Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation, in Proc Med Image Comput Comput Assist Interv pp 234–241
Samuel PM, Veeramalai T (2021) VSSC net: vessel specific skip chain convolutional network for blood vessel segmentation. Comput Methods Prog Biomed 198:105769
Jayachandran A , Sreekesh Namboodiri T(2020) Multi-class skin lesions classification system using probability map based region growing and DCNN. Int.J Comput Intell Syst 13(1):77–84
Saroj SK, Kumar R, Singh NP (2020) Fréchet PDF based Matched Filter Approach for Retinal Blood Vessels Segmentation, Comput. Methods Programs Biomed. 194
Sathananthavathi V, Indumathi G (2021) Encoder Enhanced Atrous (EEA) Unet architecture for Retinal Blood vessel segmentation. Cogn Syst Res 67:84–95
Soomro TA, Afifi AJ, Gao J, Hellwich O, Zheng L, Paul M (2019) Strided fully convolutional neural network for boosting the sensitivity of retinal blood vessels segmentation. Expert Syst Appl 134:36–52
Staal J, Abramoff MD, Niemeijer M, Viergever MA, Ginneken BV (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23:501–509
Stalin D, David AJ (2020) A new expert system based on hybrid colour and structure descriptor and machine learning algorithms for early glaucoma diagnosis. Multimed Tools Appl 79(7):5213–5224
Szegedy C et al. (2016) Rethinking the inception architecture for computer vision, in Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826
Tang X, Zhong B, Peng J, Hao B, Li J (2020) Multi-scale channel importance sorting and spatial attention mechanism for retinal vessels segmentation. Appl Soft Comput 93:106353
Wang W, Wang W, Hu Z (2019) Retinal vessel segmentation approach based on corrected morphological transformation and fractal dimension. IET Image Process 13:2538–2547
Wu Y, Xia Y, Song Y, Zhang Y, Cai W (2020) NFN+: a novel network followed network for retinal vessel segmentation. Neural Netw 126:153–162
Xiang Y, Gao X, Zou B, Zhu C, Qiu C, Li X (2014) Segmentation of retinal blood vessels based on divergence and bot-hat transform, in Proc IEEE Int Conf Prog Informat Comput, pp 316–320
Yan Z, Yang X, Cheng K-T (2018) Joint segment-level and pixel wise losses for deep learning based retinal vessel segmentation. IEEE Trans Biomed Eng 65:1912–1923
Yan Z, Yang X, Cheng KT (2018) A three-stage deep learning model for accurate. IEEE J Biomed Heal Inf 23:1427–1436
Yan Z, Yang X, Cheng K-T (2019) A three-stage deep learning model for accurate retinal vessel segmentation. IEEE J Biomed Health Inform 23:1427–1436
Yang J, Lou C, Fu J, Feng C (2020) Vessel segmentation using multiscale vessel enhancement and a region based level set model. Comput Med Imaging Graph 85:101783
Yang J, Huang M, Fu J, Lou C, Feng C (2020) Frangi based multi-scale level sets for retinal vascular segmentation. Comput Methods Prog Biomed 197:105752
Yang L, Wang H, Zeng Q, Liu Y, Bian G (2021) A hybrid deep segmentation network for fundus vessels via deep-learning framework. Neurocomputing. 448:168–178
Zhang Z, Yin FS, Liu J, Wong WK, Tan NM, Lee BH, Cheng J, Wong TY (2010) ORIGA-light : An online retinal fundus image database for glaucoma analysis and research, 2010 Annu Int Conf IEEE Eng Med Biol Soc EMBC’10, pp 3065–3068
Zhang J, Dashtbozorg B, Bekkers E, Pluim JPW, Duits R, ter Haar Romeny BM (2016) Robust retinal vessel segmentation via locally adaptive derivative frames in orientation scores. IEEE Trans Med Imaging 35:2631–2644
Acknowledgments
This work was not supported from funding Agencies.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical compliance
Not applicable.
Conflict of interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jayachandran, A., Kumar, S.R. & Perumal, T.S.R. Multi-dimensional cascades neural network models for the segmentation of retinal vessels in colour fundus images. Multimed Tools Appl 82, 42927–42943 (2023). https://doi.org/10.1007/s11042-023-15133-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15133-2