Skip to main content
SpringerLink
Log in

Efficient skin lesion segmentation with boundary distillation

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Medical image segmentation models are commonly known for their complex structures, which often render them impractical for use on edge computing devices and compromising efficiency in the segmentation process. In light of this, the industry has proposed the adoption of knowledge distillation techniques. Nevertheless, the vast majority of existing knowledge distillation methods are focused on the classification tasks of skin diseases. Specifically, for the segmentation tasks of dermoscopy lesion images, these knowledge distillation methods fail to fully recognize the importance of features in the boundary regions of lesions within medical images, lacking boundary awareness for skin lesions. This paper introduces pioneering medical image knowledge distillation architecture. The aim of this method is to facilitate the efficient transfer of knowledge from existing complex medical image segmentation networks to a more simplified student network. Initially, a masked boundary feature (MBF) distillation module is designed. By applying random masking to the periphery of skin lesions, the MBF distillation module obliges the student network to reproduce the comprehensive features of the teacher network. This process, in turn, augments the representational capabilities of the student network. Building on the MBF distillation module, this paper employs a cascaded combination approach to integrate the MBF distillation module into a multi-head boundary feature (M2BF) distillation module, further strengthening the student network’s feature learning ability and enhancing the overall image segmentation performance of the distillation model. This method has been experimentally validated on the public datasets ISIC-2016 and PH2, with results showing significant performance improvements in the student network. Our findings highlight the practical utility of the lightweight network distilled using our approach, particularly in scenarios demanding high operational speed and minimal storage usage. This research offers promising prospects for practical applications in the realm of medical image segmentation.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Ge Z, Demyanov S, Chakravorty R et al (2017) Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images. In: Descoteaux M, Maier-Hein L, Franz A et al (eds) Medical image computing and computer assisted intervention – MICCAI 2017. Springer International Publishing, Cham, pp 250–258

    Google Scholar 

  2. Apalla Z, Lallas A, Sotiriou E et al (2017) Epidemiological trends in skin cancer. Dermatol Pract Concept 7:1–6. https://doi.org/10.5826/dpc.0702a01

    Article  PubMed  PubMed Central  Google Scholar 

  3. Wang J, Chen F, Ma Y et al (2023) XBound-Former: toward cross-scale boundary modeling in transformers. IEEE Trans Med Imaging 42:1735–1745. https://doi.org/10.1109/TMI.2023.3236037

    Article  PubMed  Google Scholar 

  4. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical image computing and computer-assisted intervention – MICCAI 2015. Springer International Publishing, Cham, pp 234–241

    Google Scholar 

  5. Farshad A, Yeganeh Y, Gehlbach P, Navab N (2022) Y-Net: a spatiospectral dual-encoder networkfor medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer Nature Switzerland, Cham, pp 582–592

    Google Scholar 

  6. McHugh H, Talou GM, Wang A (2021) 2D Dense-UNet: a clinically valid approach to automated glioma segmentation. In: Crimi A, Bakas S (eds) Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing, Cham, pp 69–80

    Chapter  Google Scholar 

  7. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 2261–2269

    Chapter  Google Scholar 

  8. Qin D, Bu J-J, Liu Z et al (2021) Efficient medical image segmentation based on knowledge distillation. IEEE Trans Med Imaging 40:3820–3831. https://doi.org/10.1109/TMI.2021.3098703

    Article  PubMed  Google Scholar 

  9. Chen J, Lu Y, Yu Q et al (2021) TransUNet: transformers make strong encoders for medical image segmentation. In: ArXiv, abs/2102.04306

  10. Zhang Y, Liu H, Hu Q (2021) TransFuse: fusing transformers and CNNs for medical image segmentation. In: In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I, vol 24. Springer International Publishing, pp 14–24

    Chapter  Google Scholar 

  11. He T, Shen C, Tian Z et al (2019) Knowledge adaptation for efficient semantic segmentation. In: In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 578–587

    Google Scholar 

  12. Liu Y, Chen K, Liu C et al (2019) Structured knowledge distillation for semantic segmentation. In: In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2599–2608

    Google Scholar 

  13. Wang Y, Zhou W, Jiang T et al (2020) Intra-class feature variation distillation for semantic segmentation. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer vision – ECCV 2020. Springer International Publishing, Cham, pp 346–362

    Chapter  Google Scholar 

  14. Hu K, Zhao L, Feng S et al (2022) Colorectal polyp region extraction using saliency detection network with neutrosophic enhancement. Comput Biol Med 147:105760. https://doi.org/10.1016/j.compbiomed.2022.105760

    Article  CAS  PubMed  Google Scholar 

  15. Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39:640–651. https://doi.org/10.1109/TPAMI.2016.2572683

    Article  PubMed  Google Scholar 

  16. Lin B, Guo Y, Lin J et al (2017) Deactivation study of carbon-supported ruthenium catalyst with potassium promoter. Appl Catal Gen 541:1–7. https://doi.org/10.1016/j.apcata.2017.04.020

    Article  CAS  Google Scholar 

  17. Al-masni MA, Al-antari MA, Choi M-T et al (2018) Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Comput Methods Programs Biomed 162:221–231. https://doi.org/10.1016/j.cmpb.2018.05.027

    Article  PubMed  Google Scholar 

  18. Yuan Y, Chao M, Lo Y-C (2017) Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 36:1876–1886. https://doi.org/10.1109/TMI.2017.2695227

    Article  PubMed  Google Scholar 

  19. Li H, He X, Zhou F et al (2019) Dense deconvolutional network for skin lesion segmentation. IEEE J Biomed Health Inform 23:527–537. https://doi.org/10.1109/JBHI.2018.2859898

    Article  PubMed  Google Scholar 

  20. Attia M, Hossny M, Nahavandi S, Yazdabadi A (2017) Skin melanoma segmentation using recurrent and convolutional neural networks. In: In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp 292–296

    Google Scholar 

  21. Wang J, Wei L, Wang L et al (2021) Boundary-aware transformers for skin lesion segmentation. In: de Bruijne M, Cattin PC, Cotin S et al (eds) Medical image computing and computer assisted intervention – MICCAI 2021. Springer International Publishing, Cham, pp 206–216

    Chapter  Google Scholar 

  22. Cao W, Yuan G, Liu Q et al (2023) ICL-Net: global and local inter-pixel correlations learning network for skin lesion segmentation. IEEE J Biomed Health Inform 27:145–156. https://doi.org/10.1109/JBHI.2022.3162342

    Article  PubMed  Google Scholar 

  23. Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. In: ArXiv, abs/1503.02531

  24. Xu K, Rui L, Li Y, Gu L (2020) Feature normalized knowledge distillation for image classification. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer vision – ECCV 2020. Springer International Publishing, Cham, pp 664–680

    Google Scholar 

  25. Zhang L, Song J, Gao A et al (2019) Be your own teacher: improve the performance of convolutional neural networks via self distillation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 3712–3721

  26. Romero A, Ballas N, Kahou SE et al (2015) FitNets: hints for thin deep nets. In: CoRR, abs/1412.6550

  27. Xiao Z, Xing H, Qu R et al (2024) Densely knowledge-aware network for multivariate time series classification. IEEE Trans Syst Man Cybern Syst:1–13. https://doi.org/10.1109/TSMC.2023.3342640

  28. Xiao Z, Xing H, Qu R et al (2024) Self-bidirectional decoupled distillation for time series classification. IEEE Trans Artif Intell:1–11. https://doi.org/10.1109/TAI.2024.3360180

  29. Xiao Z, Xing H, Zhao B et al (2024) Deep contrastive representation learning with self-distillation. IEEE Trans Emerg Top Comput Intell 8:3–15. https://doi.org/10.1109/TETCI.2023.3304948

    Article  Google Scholar 

  30. Xiao Z, Tong H, Qu R et al (2023) CapMatch: semi-supervised contrastive transformer capsule with feature-based knowledge distillation for human activity recognition. IEEE Trans Neural Netw Learn Syst:1–15. https://doi.org/10.1109/TNNLS.2023.3344294

  31. Yang Z, Li Z, Shao M et al (2022) Masked generative distillation. In: In European Conference on Computer Vision. Springer Nature Switzerland, Cham, pp 53–69

    Google Scholar 

  32. Zagoruyko S, Komodakis N (2017) Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: International Conference on Learning. https://doi.org/10.48550/arXiv.1612.03928

  33. Heo B, Kim J, Yun S et al (2019) A comprehensive overhaul of feature distillation. In: In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp 1921–1930

    Chapter  Google Scholar 

  34. Yang Z, Li Z, Jiang X et al (2022) Focal and global knowledge distillation for detectors. In: In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 4643–4652

    Google Scholar 

  35. Shu C, Liu Y, Gao J et al (2021) Channel-wise knowledge distillation for dense prediction. In: In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp 5291–5300

    Chapter  Google Scholar 

  36. Guo C, Szemenyei M, Yi Y et al (2020) SA-UNet: spatial attention U-Net for retinal vessel segmentation. In: In 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 1236–1242

    Google Scholar 

  37. Li X, Jiang Y, Li M, Yin S (2021) Lightweight attention convolutional neural network for retinal vessel image segmentation. IEEE Trans Ind Inform 17:1958–1967. https://doi.org/10.1109/TII.2020.2993842

    Article  Google Scholar 

  38. Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentation. In: ArXiv, abs/1606.02147

  39. Mehta S, Rastegari M, Caspi A et al (2018) ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: In Proceedings of the european conference on computer vision (ECCV), pp 552–568

    Google Scholar 

  40. Romera E, Álvarez JM, Bergasa LM, Arroyo R (2018) ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation. IEEE Trans Intell Transp Syst 19:263–272. https://doi.org/10.1109/TITS.2017.2750080

    Article  Google Scholar 

  41. Zhang X, Zhou X, Lin M, Sun J (2017) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 6848–6856

  42. Iandola FN, Han S, Moskewicz MW et al (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.In: AriXiv, abs/1602.07360

  43. Sandler M, Howard A, Zhu M et al (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 4510–4520

    Chapter  Google Scholar 

  44. Liu X, Peng H, Zheng N et al (2023) EfficientViT: memory efficient vision transformer with cascaded group attention. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 14420–14430

  45. Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J (2018) UNet++: a nested U-Net architecture for medical image segmentation. In: Stoyanov D, Taylor Z, Carneiro G et al (eds) Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer International Publishing, Cham, pp 3–11

    Chapter  Google Scholar 

  46. Liu M, Yin H (2019) Feature pyramid encoding network for real-time semantic segmentation. In: British Machine Vision Conference. https://doi.org/10.48550/arXiv.1909.08599

  47. Wang Y, Wang Y, Cai J et al (2023) SSD-KD: a self-supervised diverse knowledge distillation method for lightweight skin lesion classification using dermoscopic images. Med Image Anal 84:102693. https://doi.org/10.1016/j.media.2022.102693

    Article  PubMed  Google Scholar 

  48. Xu G, Liu Z, Li X, Loy CC (2020) Knowledge distillation meets self-supervision. In: In European conference on computer vision. Springer International Publishing, Cham, pp 588–604

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, 200444, China

    Zaifang Zhang & Boyang Lu

Authors
  1. Zaifang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Boyang Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zaifang Zhang.

Ethics declarations

Competing interests

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, ., Lu, B. Efficient skin lesion segmentation with boundary distillation. Med Biol Eng Comput (2024). https://doi.org/10.1007/s11517-024-03095-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11517-024-03095-y

Keywords

Search

Navigation