Abstract
Over the past couple of years, Transformers became increasingly popular within the deep learning community. Initially designed for Natural Language Processing tasks, Transformers were then tailored to fit to the Image Analysis field. The self-attention mechanism behind Transformers immediately appeared a promising, although computationally expensive, learning approach. However, Transformers do not adapt as well to tasks involving large images or small datasets. This propelled the exploration of hybrid CNN-Transformer models, which seemed to overcome those limitations, thus sparkling an increasing interest also in the field of medical imaging. Here, a hybrid approach is investigated for Pigment Signs (PS) segmentation in Fundus Images of patients suffering from Retinitis Pigmentosa, an eye disorder eventually leading to complete blindness. PS segmentation is a challenging task due to the high variability of their size, shape and colors and to the difficulty to distinguish between PS and blood vessels, which often overlap and display similar colors. To address those issues, we use the Group Transformer U-Net, a hybrid CNN-Transformer. We investigate the effects, on the learning process, of using different losses and choosing an appropriate parameter tuning. We compare the obtained performances with the classical U-Net architecture. Interestingly, although the results show margins for a consistent improvement, they do not suggest a clear superiority of the hybrid architecture. This evidence raises several questions, that we address here but also deserve to be further investigated, on how and when Transformers are really the best choice to address medical imaging tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adamw optimizer and cosine learning rate annealing with restarts. https://github.com/mpyrozhok/adamwr
Berman, M., Triki, A.R., Blaschko, M.B.: The Lovasz-Softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, pp. 4413–4421. IEEE, June 2018
Brancati, N., Frucci, M., Riccio, D., Di Perna, L., Simonelli, F.: Segmentation of pigment signs in fundus images for retinitis pigmentosa analysis by using deep learning. In: Ricci, E., Rota Bulò, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019. LNCS, vol. 11752, pp. 437–445. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30645-8_40
Dosovitskiy, A., et al.: An image is worth \(16\times 16\) words: transformers for image recognition at scale. arXiv:2010.11929 [cs], June 2021
Han, K., et al.: A survey on vision transformer. arXiv:2012.12556 [cs], August 2021
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. (CSUR) (2021)
Li, Y., et al.: GT U-Net: a U-Net like group transformer network for tooth root segmentation. In: Lian, C., Cao, X., Rekik, I., Xu, X., Yan, P. (eds.) MLMI 2021. LNCS, vol. 12966, pp. 386–395. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87589-3_40
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. arXiv:2201.03545 [cs], March 2022
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 [cs, math], January 2019
Ma, J., et al.: Loss odyssey in medical image segmentation. Med. Image Anal. 71, 102035 (2021)
Park, N., Kim, S.: How do vision transformers work? arXiv:2202.06709 [cs], February 2022
PyTorch learning rate finder. https://github.com/davidtvs/pytorch-lr-finder
The RIPS dataset. https://www.icar.cnr.it/sites-rips-datasetrips/
Sangiovanni, M., Brancati, N., Frucci, M., Di Perna, L., Simonelli, F., Riccio, D.: Segmentation of pigment signs in fundus images with a hybrid approach: a case study. Pattern Recogn. Image Anal. 32(2), 312–321 (2022)
Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464–472. IEEE (2017)
Smith, L.N.: A disciplined approach to neural network hyper-parameters: part 1 - learning rate, batch size, momentum, and weight decay. arXiv:1803.09820 [cs, stat], April 2018
Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 16514–16524. IEEE, June 2021
Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7262–7272 (2021)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sangiovanni, M., Frucci, M., Riccio, D., Di Perna, L., Simonelli, F., Brancati, N. (2022). Exploring a Transformer Approach for Pigment Signs Segmentation in Fundus Images. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds) Image Analysis and Processing. ICIAP 2022 Workshops. ICIAP 2022. Lecture Notes in Computer Science, vol 13374. Springer, Cham. https://doi.org/10.1007/978-3-031-13324-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-13324-4_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13323-7
Online ISBN: 978-3-031-13324-4
eBook Packages: Computer ScienceComputer Science (R0)