Abstract
Biomedical image segmentation requires pixel-wise labelling which is extremely time-consuming and the availability of additional training data is highly beneficial for training Deep Learning models. In addition to using Classical Image augmentation, generative adversarial networks have been used to augment the training data. This work is an investigation of the usefulness of generated medical images for Deep Learning segmentation models. An attempt has been made to create a computer-generated retinal image segmentation dataset using various state-of-the-art image generative deep learning models and use that dataset to train a supervised image segmentation model. Our experiments demonstrate that the generated data can be used successfully for medical segmentation tasks and improves the model’s performance over using classical augmentations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Han, C., et al.: GAN-based synthetic brain MR image generation. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) (2018). https://doi.org/10.1109/ISBI.2018.8363678
Bowles, C., et al.: GAN augmentation: augmenting training data using generative adversarial networks (2018). https://doi.org/10.48550/arXiv.1810.10863, https://arxiv.org/abs/1810.10863
Beers, A., et al.: High-resolution medical image synthesis using progressively grown generative adversarial networks (2018). https://doi.org/10.48550/arXiv.1805.03144, https://arxiv.org/abs/1805.03144
Kaji, S., Kida, S.: Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging - radiological physics and technology (2019). https://doi.org/10.1007/s12194-019-00520-y, https://link.springer.com/article/10.1007/s12194-019-00520-y
Platscher, M., Zopes, J., Federau, C.: Image translation for medical image generation: ischemic stroke lesion segmentation. Biomed. Signal Process. Control 72, 103283 (2022). https://doi.org/10.1016/j.bspc.2021.103283
Yan, S., Wang, C., Chen, W., Lyu, J.: Swin transformer-based GAN for multi-modal medical image translation. Front. Oncol. 12, 942511 (2022). https://doi.org/10.3389/fonc.2022.942511
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks (2018). https://doi.org/10.48550/arXiv.1611.07004, https://arxiv.org/abs/1611.07004
Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014). https://doi.org/10.48550/arXiv.1411.1784, https://arxiv.org/abs/1411.1784
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318–327 (2020). https://doi.org/10.1109/TPAMI.2018.2858826
Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data (2020). https://doi.org/10.48550/arXiv.2006.06676, https://arxiv.org/abs/2006.06676
Staal, J., Abramoff, M.D., Niemeijer, M., Viergever, M.A., van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23, 501–509 (2004). https://doi.org/10.1109/tmi.2004.825627
Fraz, M.M., et al.: An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans. Biomed. Eng. 59, 2538–2548 (2012). https://doi.org/10.1109/tbme.2012.2205687
Akram, M.U., Abdul Salam, A., Khawaja, S.G., Naqvi, S.G., Khan, S.A.: RIDB: a dataset of fundus images for retina based person identification. Data Brief 33, 106433 (2020). https://doi.org/10.1016/j.dib.2020.106433
Kauppi, T., et al.: The DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Proceedings of the British Machine Vision Conference 2007 (2007). https://doi.org/10.5244/c.21.15
Budai, A., Bock, R., Maier, A., Hornegger, J., Michelson, G.: Robust vessel segmentation in fundus images. Int. J. Biomed. Imaging 2013, 1–11 (2013). https://doi.org/10.1155/2013/154860
Porwal, P., et al.: Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research. Data 3, 25 (2018). https://doi.org/10.3390/data3030025
Farnell, D.J.J., et al.: Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators (2008). https://research.manchester.ac.uk/en/publications/enhancement-of-blood-vessels-in-digital-fundus-photographs-via-th
Jin, K., et al.: FIVES: a fundus image dataset for artificial intelligence based vessel segmentation. Sci. Data 9, 475 (2022). https://doi.org/10.1038/s41597-022-01564-3
Hoover, A.D., Kouznetsova, V., Goldbaum, M.: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19, 203–210 (2000). https://doi.org/10.1109/42.845178
Heusel, M., et al.: GANs trained by a two time-scale update rule converge to a local nash equilibrium (2019). https://arxiv.org/abs/1706.08500, https://doi.org/10.48550/arXiv.1706.08500. Accessed 12 Jan 2018
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Bhuiya, S., Choudhury, S.R., Aich, G., Maurya, M., Sen, A.: Retinal blood vessel segmentation and analysis using lightweight spatial attention based CNN and data augmentation. In: 2022 IEEE Calcutta Conference (CALCON) (2022). https://doi.org/10.1109/CALCON56258.2022.10060189
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Computer Vision - ECCV 2018, pp. 3–19 (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., Asari, V.K.: Recurrent residual convolutional neural network based on U-net (R2U-net) for medical image segmentation (2018). https://doi.org/10.48550/arXiv.1802.06955
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bhuiya, S., Chakraborty, S., Sadhukhan, S., Mandal, D.P., Bhandari, D. (2023). Generation of Data for Training Retinal Image Segmentation Models. In: Maji, P., Huang, T., Pal, N.R., Chaudhury, S., De, R.K. (eds) Pattern Recognition and Machine Intelligence. PReMI 2023. Lecture Notes in Computer Science, vol 14301. Springer, Cham. https://doi.org/10.1007/978-3-031-45170-6_50
Download citation
DOI: https://doi.org/10.1007/978-3-031-45170-6_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45169-0
Online ISBN: 978-3-031-45170-6
eBook Packages: Computer ScienceComputer Science (R0)