Abstract
Accurately segmenting brain lesions in MRI scans is critical for providing patients with prognoses and neurological monitoring. However, the performance of CNN-based segmentation methods is constrained by the limited training set size. Advanced data augmentation is an effective strategy to improve the model’s robustness. However, they often introduce intensity disparities between foreground and background areas and boundary artifacts, which weakens the effectiveness of such strategies. In this paper, we propose a foreground harmonization framework (ARHNet) to tackle intensity disparities and make synthetic images look more realistic. In particular, we propose an Adaptive Region Harmonization (ARH) module to dynamically align foreground feature maps to the background with an attention mechanism. We demonstrate the efficacy of our method in improving the segmentation performance using real and synthetic images. Experimental results on the ATLAS 2.0 dataset show that ARHNet outperforms other methods for image harmonization tasks, and boosts the down-stream segmentation performance. Our code is publicly available at https://github.com/King-HAW/ARHNet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cardoso, M.J., et al.: MONAI: an open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 (2022)
Chen, S., Dobriban, E., Lee, J.H.: A group-theoretic framework for data augmentation. J. Mach. Learn. Res. 21(1), 9885–9955 (2020)
Cong, W., et al.: Dovenet: deep image harmonization via domain verification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8394–8403 (2020)
Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2918–2928 (2021)
Huo, J., et al.: Mapping: model average with post-processing for stroke lesion segmentation. arXiv preprint arXiv:2211.15486 (2022)
Huo, J., et al.: Brain lesion synthesis via progressive adversarial variational auto-encoder. In: Zhao, C., Svoboda, D., Wolterink, J.M., Escobar, M. (eds.) SASHIMI 2022. LNCS, vol. 13570, pp. 101–111. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16980-9_10
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Liew, S.L., et al.: A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms. Sci. Data 9(1), 320 (2022)
Lim, J.H., Ye, J.C.: Geometric GAN. arXiv preprint arXiv:1705.02894 (2017)
Ling, J., Xue, H., Song, L., Xie, R., Gu, X.: Region-aware adaptive instance normalization for image harmonization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9361–9370 (2021)
Liu, X., et al.: MSDF-net: multi-scale deep fusion network for stroke lesion segmentation. IEEE Access 7, 178486–178495 (2019)
Liu, Y., Zhu, Z., Bai, X.: Wdnet: watermark-decomposition network for visible watermark removal. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3685–3693 (2021)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Oktay, O., et al.: Attention U-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)
Ouyang, X., Cheng, Y., Jiang, Y., Li, C.L., Zhou, P.: Pedestrian-synthesis-GAN: generating pedestrian data in real scene and beyond. arXiv preprint arXiv:1804.02047 (2018)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Pérez-García, F., Sparks, R., Ourselin, S.: Torchio: a python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput. Methods Programs Biomed. 208, 106236 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
Wan, J., Liu, Y., Wei, D., Bai, X., Xu, Y.: Super-BPD: super boundary-to-pixel direction for fast image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9253–9262 (2020)
Wei, W., et al.: Adversarial examples in deep learning: characterization and divergence. arXiv preprint arXiv:1807.00051 (2018)
Zhang, X., et al.: CarveMix: a simple data augmentation method for brain lesion segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 196–205. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_19
Zhang, Y., Wu, J., Liu, Y., Chen, Y., Wu, E.X., Tang, X.: Mi-unet: multi-inputs unet incorporating brain parcellation for stroke lesion segmentation from t1-weighted magnetic resonance images. IEEE J. Biomed. Health Inform. 25(2), 526–535 (2020)
Acknowledgement
This work was supported by Centre for Doctoral Training in Surgical and Interventional Engineering at King’s College London; King’s-China Scholarship Council PhD Scholarship programme (K-CSC); and the Engineering and Physical Sciences Research Council Doctoral Training Partnership (EPSRC DTP) grant EP/T517963/1. This publication represents, in part, independent research commissioned by the Wellcome Innovator Award [218380/Z/19/Z]. The views expressed in this publication are those of the authors and not necessarily those of the Wellcome Trust.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Huo, J., Liu, Y., Ouyang, X., Granados, A., Ourselin, S., Sparks, R. (2024). ARHNet: Adaptive Region Harmonization for Lesion-Aware Augmentation to Improve Segmentation Performance. In: Cao, X., Xu, X., Rekik, I., Cui, Z., Ouyang, X. (eds) Machine Learning in Medical Imaging. MLMI 2023. Lecture Notes in Computer Science, vol 14349. Springer, Cham. https://doi.org/10.1007/978-3-031-45676-3_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-45676-3_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45675-6
Online ISBN: 978-3-031-45676-3
eBook Packages: Computer ScienceComputer Science (R0)