Abstract
Retinal fundus images have been widely utilized for screening Diabetic Retinopathy (DR). The lesion information contained in these images is indispensable for the diagnosis of DR. The acquisition of lesion information depends on the sophisticated lesion segmentation methods. Nevertheless, the existing lesion segmentation methods highly rely on huge computational complexity and massive storage, making it difficult to apply in real-world clinical scenarios. Knowledge distillation (KD) has become an essential tool to reduce the computational complexity of the network. However, the lesion regions being insignificant in fundus images, directly applying the current KD methods cannot adequately transfer sufficient lesion knowledge, which restricts the learning of knowledge distillation. In essence, the challenge is how to enhance the focus of the KD process on lesion regions and to transfer more comprehensive pathological knowledge to the student network. Considering the importance of lesion regions in fundus images and the global semantic relations among lesion regions across various fundus images, we propose a Lesion-aware Knowledge Distillation (LKD) framework focusing on the transfer of lesion knowledge. The key contribution of the proposed framework is the creation of lesion embedding queue from the global training samples, which facilitates the transfer of global pathology knowledge from the teacher network to the student network, thus promoting the acquisition of lesion-related knowledge. Furthermore, we propose a self-paced hard sample learning strategy for knowledge transfer of lesion embedding queue, which additionally improves the efficiency of knowledge transfer. We evaluate LKD on IDRiD and DDR benchmark datasets, the overall performance of the proposed mehtod improves 2.1% AUPR as well as 2.2% DICE and 1.5% AUPR as well as 2.2% DICE compared to the previous best results. A particular improvement of 2.3% and 3.2% in DICE are achieved on the IDRiD dataset for tiny lesions, i.e., MA and HE, respectively. Our code is available at https://github.com/YaqiWangCV/LKD.
Similar content being viewed by others
Data Availability and Access
Data related to the current study are available from the corresponding author on reasonable request.
References
Beli E, Yan Y, Moldovan L, Vieira CP, Gao R, Duan Y, Prasad R, Bhatwadekar A, White FA, Townsend SD et al (2018) Restructuring of the gut microbiome by intermittent fasting prevents retinopathy and prolongs survival in db/db mice. Diabetes 67(9):1867–1879
Kang Q, Yang C (2020) Oxidative stress and diabetic retinopathy: Molecular mechanisms, pathogenetic role and therapeutic implications. Redox Biology 37:101799
Zhou Y, He X, Huang L, Liu L, Zhu F, Cui S, Shao L (2019) Collaborative learning of semi-supervised segmentation and classification for medical images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2079–2088
Sambyal N, Saini P, Syal R, Gupta V (2020) Modified u-net architecture for semantic segmentation of diabetic retinopathy images. Biocybern Biomed Eng 40(3):1094–1109
Guo Y, Peng Y (2022) Carnet: Cascade attentive refinenet for multi-lesion segmentation of diabetic retinopathy images. Complex Intell Syst 8(2):1681–1701
Huang S, Li J, Xiao Y, Shen N, Xu T (2022) Rtnet: Relation transformer network for diabetic retinopathy multi-lesion segmentation. IEEE Trans Med Imaging
Wang H, Cao P, Yang J, Zaiane O (2023) Mca-unet: multi-scale cross co-attentional u-net for automatic medical image segmentation. Health Inf Sci Syst 11(1):10
He T, Shen C, Tian Z, Gong D, Sun C, Yan Y (2019) Knowledge adaptation for efficient semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 578–587
Shu C, Liu Y, Gao J, Yan Z, Shen C (2021) Channel-wise knowledge distillation for dense prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 5311–5320
Liu Y, Chen K, Liu C, Qin Z, Luo Z, Wang J (2019) Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2604–2613
Wang Y, Zhou W, Jiang T, Bai X, Xu Y (2020) Intra-class feature variation distillation for semantic segmentation. In: European Conference on Computer Vision, pp 346–362
Park W, Kim D, Lu Y, Cho M (2019) Relational knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 3967–3976
Yang C, Zhou H, An Z, Jiang X, Xu Y, Zhang Q (2022) Cross-image relational knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 12319–12328
Qin D, Bu J-J, Liu Z, Shen X, Zhou S, Gu J-J, Wang Z-H, Wu L, Dai H-F (2021) Efficient medical image segmentation based on knowledge distillation. IEEE Trans Med Imaging 40(12):3820–3831
Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J (2018) Unet++: A nested u-net architecture for medical image segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp 3–11
Qin X, Zhang Z, Huang C, Dehghan M, Zaiane OR, Jagersand M (2020) U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recognit 106:107404
Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B et al (2018) Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp 234–241
Zheng R, Liu L, Zhang S, Zheng C, Bunyak F, Xu R, Li B, Sun M (2018) Detection of exudates in fundus photographs with imbalanced learning using conditional generative adversarial network. Biomed Opt Express 9(10):4863–4878
Li X, Jiang Y, Li M, Yin S (2021) Lightweight attention convolutional neural network for retinal vessel image segmentation. IEEE Trans Industr Inform 17(3):1958–1967
Guo Y, Peng Y (2022) Multiple lesion segmentation in diabetic retinopathy with dual-input attentive refinenet. Appl Intell 52(12):14440–14464
Paszke A, Chaurasia A, Kim S, Culurciello E (2016) Enet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147
Hinton G, Vinyals O, Dean J et al (2015) Distilling the knowledge in a neural network 2(7). arXiv preprint arXiv:1503.02531
Zhou H, Song L, Chen J, Zhou Y, Wang G, Yuan J, Zhang Q (2021) Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective. arXiv preprint arXiv:2102.00650
Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550
Heo B, Kim J, Yun S, Park H, Kwak N, Choi JY (2019) A comprehensive overhaul of feature distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 1921–1930
Zagoruyko S, Komodakis N (2016) Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928
Fang Z, Wang J, Wang L, Zhang L, Yang Y, Liu Z (2021) Seed: Self-supervised distillation for visual representation. arXiv preprint arXiv:2101.04731
Peng B, Jin X, Liu J, Li D, Wu Y, Liu Y, Zhou S, Zhang Z (2019) Correlation congruence for knowledge distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 5007–5016
Tung F, Mori G (2019) Similarity-preserving knowledge distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 1365–1374
Yang C, An Z, Xu Y (2021) Multi-view contrastive learning for online knowledge distillation. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3750–3754
Wang C, Zhong J, Dai Q, Li R, Yu Q, Fang B (2023) Local structure consistency and pixel-correlation distillation for compact semantic segmentation. Appl Intell 53(6):6307–6323
Sharma S, Lodhi SS, Chandra J (2023) Scl-ikd: intermediate knowledge distillation via supervised contrastive representation learning. Appl Intell 1–22
Xie J, Shuai B, Hu J-F, Lin J, Zheng W-S (2018) Improving fast segmentation with teacher-student learning. arXiv preprint arXiv:1810.08476
Liu Y, Shu C, Wang J, Shen C (2020) Structured knowledge distillation for dense prediction. IEEE transactions on pattern analysis and machine intelligence
Li K, Yu L, Wang S, Heng P-A (2020) Towards cross-modality medical image segmentation with online mutual knowledge distillation. Proceedings of the AAAI Conference on Artificial Intelligence 34:775–783
Bengio Y, Louradour J, Collobert R, Weston J (2019) Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp 41–48
Kumar M, Packer B, Koller D (2010) Self-paced learning for latent variable models. Adv Neural Inf Process Syst 23
Supancic JS, Ramanan D (2013) Self-paced learning for long-term tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2379–2386
Jiang L, Meng D, Mitamura T, Hauptmann AG (2014) Easy samples first: Self-paced reranking for zero-example multimedia search. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp 547–556
Jiang L, Meng D, Yu S-I, Lan Z, Shan S, Hauptmann A (2014) Self-paced learning with diversity. Adv Neural Inf Process Syst 27
Jiang L, Meng D, Zhao Q, Shan S, Hauptmann A (2015) Self-paced curriculum learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 29
Dong X, Zheng L, Ma F, Yang Y, Meng D (2018) Few-example object detection with model communication. IEEE Trans Pattern Anal Mach Intell 41(7):1641–1654
Ma F, Meng D, Xie Q, Li Z, Dong X (2017) Self-paced co-training. In: International Conference on Machine Learning, pp 2275–2284
Ma F, Meng D, Dong X, Yang Y (2020) Self-paced multi-view co-training. J Mach Learn Res
Xiang L, Ding G, Han J (2020) Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, pp 247–263
Jin X, Peng B, Wu Y, Liu Y, Liu J, Liang D, Yan J, Hu X (2019) Knowledge distillation via route constrained optimization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 1345–1354
Wang Y, Zhou W, Jiang T, Bai X, Xu Y (2020) Intra-class feature variation distillation for semantic segmentation. In: European Conference on Computer Vision, pp 346–362
Wang F, Yan J, Meng F, Zhou J (2021) Selective knowledge distillation for neural machine translation. arXiv preprint arXiv:2105.12967
Jiang L, Meng D, Mitamura T, Hauptmann AG (2014) Easy samples first: Self-paced reranking for zero-example multimedia search. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp 547–556
Milletari F, Navab N, Ahmadi S-A (2016) V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp 565–571
Porwal P, Pachade S, Kamble R, Kokare M, Deshmukh G, Sahasrabuddhe V, Meriaudeau F (2018) Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research. Data 3(3):25
Porwal P, Pachade S, Kokare M, Deshmukh G, Son J, Bae W, Liu L, Wang J, Liu X, Gao L et al (2020) Idrid: Diabetic retinopathy-segmentation and grading challenge. Med Image Anal 59:101561
Li T, Gao Y, Wang K, Guo S, Liu H, Kang H (2019) Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf Sci 501:511–522
Jha D, Smedsrud PH, Riegler MA, Johansen D, De Lange T, Halvorsen P, Johansen HD (2019) Resunet++: An advanced architecture for medical image segmentation. In: 2019 IEEE International Symposium on Multimedia (ISM), pp 225–2255
Wang H, Cao P, Wang J, Zaiane OR (2022) Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. Proceedings of the AAAI Conference on Artificial Intelligence 36:2441–2449
Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306
Sivaswamy J, Krishnadas SR, Datt Joshi G, Jain M, Syed Tabish AU (2014) Drishti-gs: Retinal image dataset for optic nerve head(onh) segmentation. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), pp 53–56. https://doi.org/10.1109/ISBI.2014.6867807
Staal J, Abràmoff MD, Niemeijer M, Viergever MA, Van Ginneken B (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4):501–509
Acknowledgements
This research was supported by the National Natural Science Foundation of China (No.62076059) and the Science Project of Liaoning Province (2021-MS-105).
Author information
Authors and Affiliations
Contributions
Yaqi Wang proposed the method and conducted the experiments, analyzed the data, and wrote the manuscript. Qingshan Hou and Peng Cao supervised the project and participated in manuscript revisions. Jinzhu Yang and Osmar R. Zaiane provided critical reviews that helped improve the manuscript.
Corresponding author
Ethics declarations
Ethical and Informed Consent for Data Used
This study does not contain any studies with human participants or animals performed by any of the authors.
Competing 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
Wang, Y., Hou, Q., Cao, P. et al. Lesion-aware knowledge distillation for diabetic retinopathy lesion segmentation. Appl Intell 54, 1937–1956 (2024). https://doi.org/10.1007/s10489-024-05274-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-024-05274-8