Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Light-weight Retinal Layer Segmentation with Global Reasoning (2404.16346v1)

Published 25 Apr 2024 in eess.IV, cs.AI, and cs.CV

Abstract: Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases. However, it is challenging to achieve accurate segmentation due to low contrast and blood flow noises presented in the images. In addition, the algorithm should be light-weight to be deployed for practical clinical applications. Therefore, it is desired to design a light-weight network with high performance for retinal layer segmentation. In this paper, we propose LightReSeg for retinal layer segmentation which can be applied to OCT images. Specifically, our approach follows an encoder-decoder structure, where the encoder part employs multi-scale feature extraction and a Transformer block for fully exploiting the semantic information of feature maps at all scales and making the features have better global reasoning capabilities, while the decoder part, we design a multi-scale asymmetric attention (MAA) module for preserving the semantic information at each encoder scale. The experiments show that our approach achieves a better segmentation performance compared to the current state-of-the-art method TransUnet with 105.7M parameters on both our collected dataset and two other public datasets, with only 3.3M parameters.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. F. K. Horn, C. Y. Mardin, R. Laemmer, D. Baleanu, A. M. Juenemann, F. E. Kruse, and R. P. Tornow, “Correlation between local glaucomatous visual field defects and loss of nerve fiber layer thickness measured with polarimetry and spectral domain oct,” Investigative ophthalmology & visual science, vol. 50, no. 5, pp. 1971–1977, 2009.
  2. F. Pollet-Villard, C. Chiquet, J.-P. Romanet, C. Noel, and F. Aptel, “Structure-function relationships with spectral-domain optical coherence tomography retinal nerve fiber layer and optic nerve head measurements,” Investigative ophthalmology & visual science, vol. 55, no. 5, pp. 2953–2962, 2014.
  3. A. Ajaz, H. Kumar, and D. Kumar, “A review of methods for automatic detection of macular edema,” Biomedical Signal Processing and Control, vol. 69, p. 102858, 2021.
  4. C. Brandl, C. Brücklmayer, F. Günther, M. E. Zimmermann, H. Küchenhoff, H. Helbig, B. H. Weber, I. M. Heid, and K. J. Stark, “Retinal layer thicknesses in early age-related macular degeneration: results from the german augur study,” Investigative ophthalmology & visual science, vol. 60, no. 5, pp. 1581–1594, 2019.
  5. J. A. van de Kreeke, H.-T. Nguyen, J. den Haan, E. Konijnenberg, J. Tomassen, A. den Braber, M. Ten Kate, L. Collij, M. Yaqub, B. van Berckel et al., “Retinal layer thickness in preclinical alzheimer’s disease,” Acta ophthalmologica, vol. 97, no. 8, pp. 798–804, 2019.
  6. D. Huang, E. A. Swanson, C. P. Lin, J. S. Schuman, W. G. Stinson, W. Chang, M. R. Hee, T. Flotte, K. Gregory, and C. A. Puliafito, “Optical coherence tomography,” Science, vol. 254, no. 5035, pp. 1178–1181, 1991.
  7. X. Shu, L. J. Beckmann, and H. F. Zhang, “Visible-light optical coherence tomography: a review,” Journal of biomedical optics, vol. 22, no. 12, p. 121707, 2017.
  8. W. Song, W. Shao, and J. Yi, “Wide-field and micron-resolution visible light optical coherence tomography in human retina by a linear-k spectrometer,” in Bio-Optics: Design and Application.   Optica Publishing Group, 2021, pp. DM2A–4.
  9. W. Song, W. Shao, W. Yi, and J. Yi, “Linear k-domain wide-field and micron-resolution visible light human retinal optical coherence tomography,” in Ophthalmic Technologies XXXII.   SPIE, 2022, p. PC1194102.
  10. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention.   Springer, 2015, pp. 234–241.
  11. A. G. Roy, S. Conjeti, S. P. K. Karri, D. Sheet, A. Katouzian, C. Wachinger, and N. Navab, “Relaynet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks,” Biomedical optics express, vol. 8, no. 8, pp. 3627–3642, 2017.
  12. O. Oktay, J. Schlemper, L. L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N. Y. Hammerla, B. Kainz et al., “Attention u-net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
  13. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  14. F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1251–1258.
  15. X. Ding, Y. Guo, G. Ding, and J. Han, “Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 1911–1920.
  16. S. Wang, L. Yu, X. Yang, C.-W. Fu, and P.-A. Heng, “Patch-based output space adversarial learning for joint optic disc and cup segmentation,” IEEE transactions on medical imaging, vol. 38, no. 11, pp. 2485–2495, 2019.
  17. J. Li, G. Gao, L. Yang, G. Bian, and Y. Liu, “Dpf-net: A dual-path progressive fusion network for retinal vessel segmentation,” IEEE Transactions on Instrumentation and Measurement, 2023.
  18. J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, Y. Wang, L. Lu, A. L. Yuille, and Y. Zhou, “Transunet: Transformers make strong encoders for medical image segmentation,” arXiv preprint arXiv:2102.04306, 2021.
  19. M. Astaraki, Ö. Smedby, and C. Wang, “Prior-aware autoencoders for lung pathology segmentation,” Medical Image Analysis, p. 102491, 2022.
  20. E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez, and P. Luo, “Segformer: Simple and efficient design for semantic segmentation with transformers,” Advances in neural information processing systems, vol. 34, pp. 12 077–12 090, 2021.
  21. B. Chen, T. Niu, W. Yu, R. Zhang, Z. Wang, and B. Li, “A-net: An a-shape lightweight neural network for real-time surface defect segmentation,” IEEE Transactions on Instrumentation and Measurement, 2023.
  22. X. He, Y. Wang, F. Poiesi, W. Song, Q. Xu, Z. Feng, and Y. Wan, “Exploiting multi-granularity visual features for retinal layer segmentation in human eyes,” Frontiers in Bioengineering and Biotechnology, vol. 11, p. 1191803, 2023.
  23. B. Wang, W. Wei, S. Qiu, S. Wang, D. Li, and H. He, “Boundary aware u-net for retinal layers segmentation in optical coherence tomography images,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 8, pp. 3029–3040, 2021.
  24. X. Liu, J. Cao, S. Wang, Y. Zhang, and M. Wang, “Confidence-guided topology-preserving layer segmentation for optical coherence tomography images with focus-column module,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–12, 2020.
  25. K. Hu, D. Liu, Z. Chen, X. Li, Y. Zhang, and X. Gao, “Embedded residual recurrent network and graph search for the segmentation of retinal layer boundaries in optical coherence tomography,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–17, 2021.
  26. M. Gende, V. Mallen, J. de Moura, B. Cordón, E. Garcia-Martin, C. I. Sánchez, J. Novo, and M. Ortega, “Automatic segmentation of retinal layers in multiple neurodegenerative disorder scenarios,” IEEE Journal of Biomedical and Health Informatics, 2023.
  27. M.-H. Guo, C.-Z. Lu, Q. Hou, Z. Liu, M.-M. Cheng, and S.-M. Hu, “Segnext: Rethinking convolutional attention design for semantic segmentation,” arXiv preprint arXiv:2209.08575, 2022.
  28. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs,” IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 4, pp. 834–848, 2017.
  29. J. Fu, J. Liu, H. Tian, Y. Li, Y. Bao, Z. Fang, and H. Lu, “Dual attention network for scene segmentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3146–3154.
  30. J. Li, P. Jin, J. Zhu, H. Zou, X. Xu, M. Tang, M. Zhou, Y. Gan, J. He, Y. Ling, and Y. Su, “Multi-scale gcn-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary oct images,” Biomed. Opt. Express, vol. 12, no. 4, pp. 2204–2220, Apr 2021. [Online]. Available: http://opg.optica.org/boe/abstract.cfm?URI=boe-12-4-2204
  31. H. Li, P. Xiong, H. Fan, and J. Sun, “Dfanet: Deep feature aggregation for real-time semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9522–9531.
  32. C. Yu, J. Wang, C. Peng, C. Gao, G. Yu, and N. Sang, “Bisenet: Bilateral segmentation network for real-time semantic segmentation,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 325–341.
  33. W. Song, S. Zhang, Y. M. Kim, N. Sadlak, M. G. Fiorello, M. Desai, and J. Yi, “Visible light optical coherence tomography of peripapillary retinal nerve fiber layer reflectivity in glaucoma,” Translational vision science & technology, vol. 11, no. 9, pp. 28–28, 2022.
  34. W. Song, S. Zhang, N. Sadlak, M. G. Fiorello, M. Desai, and J. Yi, “Visible and near-infrared optical coherence tomography (vnoct) in normal, suspect, and glaucomatous eyes,” in Ophthalmic Technologies XXXI, vol. 11623.   SPIE, 2021, p. 1162311.
  35. J. Yi and W. Song, “Systems and methods for fiber-based visible and near infrared optical coherence tomography,” Aug. 4 2020, uS Patent 10,732,354.
  36. W. Song, L. Zhou, S. Zhang, S. Ness, M. Desai, and J. Yi, “Fiber-based visible and near infrared optical coherence tomography (vnoct) enables quantitative elastic light scattering spectroscopy in human retina,” Biomedical Optics Express, vol. 9, no. 7, pp. 3464–3480, 2018.
  37. S. J. Chiu, M. J. Allingham, P. S. Mettu, S. W. Cousins, J. A. Izatt, and S. Farsiu, “Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema,” Biomedical optics express, vol. 6, no. 4, pp. 1172–1194, 2015.
  38. K. Vinogradova, A. Dibrov, and G. Myers, “Towards interpretable semantic segmentation via gradient-weighted class activation mapping (student abstract),” in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 10, 2020, pp. 13 943–13 944.
  39. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017.
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets