Abstract
The U-Net architecture has become the preferred model used for medical image segmentation tasks. Since its inception, several variants have been proposed. An important component of the U-Net architecture is the use of skip-connections, said to carry over image details on its decoder branch at different scales. However, beyond this intuition, not much is known as to what extent skip-connections of the U-Net are necessary, nor what their interplay is in terms of model robustness when they are subjected to different levels of task complexity. In this study, we analyzed these questions using three variants of the U-Net architecture (the standard U-Net, a “No-Skip” U-Net, and an Attention-Gated U-Net) using controlled experiments on varying synthetic texture images and evaluated these findings on three medical image data sets. We measured task complexity as a function of texture-based similarities between foreground and background distributions. Using this scheme, our findings suggest that the benefit of employing skip-connections is small for low-to-medium complexity tasks, and its benefit appears only when the task complexity becomes large. We report that such incremental benefit is non-linear, with the Attention-Gated U-Net yielding larger improvements. Furthermore, we find that these benefits also bring along robustness degradations on clinical data sets, particularly in out-of-domain scenarios. These results suggest a dependency between task complexity and the choice/design of noise-resilient skip-connections, indicating the need for careful consideration while using these skip-connections.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Code to reproduce this is at https://github.com/amithjkamath/to_skip_or_not..
References
Al-Dhabyani, W., Gomaa, M., Khaled, H., Fahmy, A.: Dataset of breast ultrasound images. Data Brief 28, 104863 (2020)
Antonelli, M., et al.: The medical segmentation decathlon. Nature Commun. 13(1), 4128 (2022)
Azad, R., et al.: Medical image segmentation review: the success of u-net. arXiv preprint arXiv:2211.14830 (2022)
Bakas, S., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629 (2018)
Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514–2525 (2018)
Boone, L., et al.: Rood-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI. arXiv preprint arXiv:2203.06060 (2022)
Cardoso, M.J., et al.: Monai: An open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 (2022)
Doshi, N.P., Schaefer, G.: A comprehensive benchmark of local binary pattern algorithms for texture retrieval. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 2760–2763. IEEE (2012)
Galati, F., Ourselin, S., Zuluaga, M.A.: From accuracy to reliability and robustness in cardiac magnetic resonance image segmentation: a review. Appl. Sci. 12(8), 3936 (2022)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)
Hoyer, L., Munoz, M., Katiyar, P., Khoreva, A., Fischer, V.: Grid saliency for context explanations of semantic segmentation. Adv. Neural Inform. Process. Syst. 32 (2019)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: NNU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Kamann, C., Rother, C.: Benchmarking the robustness of semantic segmentation models with respect to common corruptions. Int. J. Comput. Vision 129(2), 462–483 (2021)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Liu, L., Fieguth, P., Wang, X., Pietikäinen, M., Hu, D.: Evaluation of LBP and deep texture descriptors with a new robustness benchmark. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 69–86. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_5
Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recogn. 29(1), 51–59 (1996)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234–241. Springer (2015)
Schlemper, J., et al.: Attention gated networks: learning to leverage salient regions in medical images. Med. Image Anal. 53, 197–207 (2019)
Sheikh, R., Schultz, T.: Feature preserving smoothing provides simple and effective data augmentation for medical image segmentation. In: Martel, A.L., et al. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I, pp. 116–126. Springer International Publishing, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_12
You, S., Reyes, M.: Influence of contrast and texture based image modifications on the performance and attention shift of u-net models for brain tissue segmentation. Front. Neuroimag. 1, 1012639 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kamath, A., Willmann, J., Andratschke, N., Reyes, M. (2023). Do We Really Need that Skip-Connection? Understanding Its Interplay with Task Complexity. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14223. Springer, Cham. https://doi.org/10.1007/978-3-031-43901-8_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-43901-8_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43900-1
Online ISBN: 978-3-031-43901-8
eBook Packages: Computer ScienceComputer Science (R0)