Abstract
Domain generalization (DG) for medical image segmentation due to privacy preservation prefers learning from a single-source domain and expects good robustness on unseen target domains. To achieve this goal, previous methods mainly use data augmentation to expand the distribution of samples and learn invariant content from them. However, most of these methods commonly perform global augmentation, leading to limited augmented sample diversity. In addition, the style of the augmented image is more scattered than the source domain, which may cause the model to overfit the style of the source domain. To address the above issues, we propose an invariant content representation network (ICRN) to enhance the learning of invariant content and suppress the learning of variability styles. Specifically, we first design a gamma correction-based local style augmentation (LSA) to expand the distribution of samples by augmenting foreground and background styles, respectively. Then, based on the augmented samples, we introduce invariant content learning (ICL) to learn generalizable invariant content from both augmented and source-domain samples. Finally, we design domain-specific batch normalization (DSBN) based style adversarial learning (SAL) to suppress the learning of preferences for source-domain styles. Experimental results show that our proposed method improves by 8.74% and 11.33% in overall dice coefficient (Dice) and reduces 15.88 mm and 3.87 mm in overall average surface distance (ASD) on two publicly available cross-domain datasets, Fundus and Prostate, compared to the state-of-the-art DG methods. The code is available at https://github.com/ZMC-IIIM/ICRN-DG.
Similar content being viewed by others
Data Availability
The data used in the study is publicly available and can be downloaded. For more details, please refer to the code link provided in the abstract.
Code Availability
The code link is already included in the abstract, and it will be made publicly available upon publication.
References
Liu Z, Tong L, Chen L, et al. Deep learning based brain tumor segmentation: a survey[J]. COMPLEX INTELL SYST, 9(1): 1001–1026, 2023.
Goceri E. Automated skin cancer detection: where we are and the way to the future. In Proc. telecommunications and signal processing (TSP). IEEE, 48–51, 2021.
Viedma I A, Alonso-Caneiro D, Read S A, et al. Deep learning in retinal optical coherence tomography (OCT): A comprehensive survey. Neurocomputing, 2022.
Göçeri E. Convolutional neural network based desktop applications to classify dermatological diseases. In Proc. image processing, applications and systems (IPAS). IEEE, 138–143, 2020.
Ting D S W, Pasquale L R, Peng L, et al. Artificial intelligence and deep learning in ophthalmology. BRIT J OPHTHALMOL, 103(2): 167–175, 2019.
Wang S, Yu L, Yang X, et al. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans. Med. Imaging, 38(11): 2485–2495, 2019.
Zhang L, Wang X, Yang D, et al. Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans. Med. Imaging, 39(7): 2531–2540, 2020.
Liu Q, Dou Q, Heng P A. Shape-aware meta-learning for generalizing prostate MRI segmentation to unseen domains. In Proc. Medical Image Computing and Computer Assisted Intervention-MICCAI 2020: 23rd International Conference, pp. 475–485, 2020.
Göçeri E, Ünlü M Z, Dicle O. A comparative performance evaluation of various approaches for liver segmentation from SPIR images. Turkish Journal of Electrical Engineering and Computer Sciences, 23(3): 741–768, 2015.
Goceri E. Medical image data augmentation: techniques, comparisons and interpretations. Artificial Intelligence Review, 1–45, 2023.
Bian C, Yuan C, Wang J, et al. Uncertainty-aware domain alignment for anatomical structure segmentation. Med. Image Anal., 64: 101732, 2020.
Pomponio R, Erus G, Habes M, et al. Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan. NeuroImage, 208: 116450, 2020.
Zhou K, Yang Y, Hospedales T, et al. Deep domain-adversarial image generation for domain generalisation. In Proc. AAAI conference on artificial intelligenc, 34(07): 13025–13032e, 2020.
Xu Q, Zhang R, Zhang Y, et al. A fourier-based framework for domain generalization. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14383–14392, 2021.
Patil S S, Ramteke M, Verma M, et al. A Domain-Shift Invariant CNN Framework for Cardiac MRI Segmentation Across Unseen Domains. Journal of Digital Imaging, 36(5): 2148–2163, 2023.
Zhou Z, Qi L, Yang X, et al. Generalizable cross-modality medical image segmentation via style augmentation and dual normalization. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20856–20865, 2022.
Ouyang C, Chen C, Li S, et al. Causality-inspired single-source domain generalization for medical image segmentation. IEEE Trans. Med. Imaging, 42(4): 1095–1106, 2022.
Volpi R, Namkoong H, Sener O, et al. Generalizing to unseen domains via adversarial data augmentation. In Proc. Advances in neural information processing systems, 31, 2018.
Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
Long M, Cao Y, Wang J, et al. Learning transferable features with deep adaptation networks. In Proc. International conference on machine learning, pp. 97–105, 2015.
Xia K, Deng L, Duch W, et al. Privacy-preserving domain adaptation for motor imagery-based brain-computer interfaces. IEEE Trans. Biomed. Eng., 69(11): 3365–3376, 2022.
Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks. J mach. learn. res., 17(1): 2096–2030, 2016.
Guan H, Liu M. Domain adaptation for medical image analysis: a survey. IEEE Trans. Biomed. Eng., 69(3): 1173–1185, 2021.
Liu B, Chen X, Li X, et al. Align and pool for EEG headset domain adaptation (ALPHA) to facilitate dry electrode based SSVEP-BCI. IEEE Trans. Biomed. Eng., 2021, 69(2): 795–806.
Hoffman J, Tzeng E, Park T, et al. Cycada: Cycle-consistent adversarial domain adaptation. In Proc. International conference on machine learning, pp. 1989-1998, 2018.
Li X, Zhang X, Chen X, et al. A Unified User-Generic Framework for Myoelectric Pattern Recognition: Mix-up and Adversarial Training for Domain Generalization and Adaptation. IEEE Trans. Biomed Eng., 2023.
Li D, Yang Y, Song Y Z, et al. Learning to generalize: Meta-learning for domain generalization. In Proc. AAAI conference on artificial intelligence, 32(1), 2018.
Wang B, Lapata M, Titov I. Meta-learning for domain generalization in semantic parsing. arXiv preprint arXiv:2010.11988, 2020.
Motiian S, Piccirilli M, Adjeroh D A, et al. Unified deep supervised domain adaptation and generalization. In Proc. IEEE international conference on computer vision, 5715–5725, 2017.
Gong Y, Lin X, Yao Y, et al. Confidence calibration for domain generalization under covariate shift. In Proc. IEEE/CVF International Conference on Computer Vision, 8958-8967, 2021.
RV A, AP S. Augmenting transfer learning with feature extraction techniques for limited breast imaging datasets. J Digit Imaging, 34(3): 618–629, 2021.
Lemaître G, Martí R, Freixenet J, et al. Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Computers biol. med., 60: 8–31, 2015.
Sinha A, Namkoong H, Volpi R, et al. Certifying some distributional robustness with principled adversarial training. arXiv preprint arXiv:1710.10571, 2017.
Farid H. Blind inverse gamma correction. IEEE trans. image process., 10(10): 1428–1433, 2001.
Sivaswamy J, Krishnadas S, Chakravarty A, et al. A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis. JSM Biomed. Imaging Data Pap., 2(1): 1004, 2015.
Fumero F, Alayón S, Sanchez J L, et al. RIM-ONE: An open retinal image database for optic nerve evaluation. In Proc. international symposium on computer-based medical systems, 1–6, 2011.
GÖÇERİ E. An application for automated diagnosis of facial dermatological diseases. İzmir Katip Çelebi Üniversitesi Sağlık Bilimleri Fakültesi Dergisi, 6(3): 91–99, 2021.
Orlando J I, Fu H, Breda J B, et al. Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med. image anal., 59: 101570, 2020.
Bloch N et al., 2013 challenge: automated segmentation of prostate structures. https://doi.org/10.7937/K9/TCIA.2015.zF0vlOPv, 2015.
Litjens G, Toth R, Van De Ven W, et al. Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med. image anal., 18(2): 359–373, 2014.
Zhou Z, Qi L, Shi Y. Generalizable medical image segmentation via random amplitude mixup and domain-specific image restoration. In Proc. European Conference on Computer Vision. 420–436, 2022.
Qiao F, Peng X. Uncertainty-guided model generalization to unseen domains. In Proc. IEEE/CVF conference on computer vision and pattern recognition, 6790–6800, 2021.
Liu Q, Chen C, Qin J, et al. Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1013–1023, 2021.
Chen Z, Pan Y, Ye Y, et al. Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation. In Proc. Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.
Goceri E. Fully automated and adaptive intensity normalization using statistical features for brain MR images. Celal Bayar University Journal of Science, 14(1): 125–134, 2018.
Goceri E. Evaluation of denoising techniques to remove speckle and Gaussian noise from dermoscopy images. Computers in Biology and Medicine, 152: 106474, 2023.
Funding
This work was supported in part by the Shandong Provincial Natural Science Foundation (Grant No.2022HWYQ-041), the Natural Science Foundation of Jiangsu Province (Grant No.BK20220266), and the National Nature Science Foundation of China (Grant No.62071415).
Author information
Authors and Affiliations
Contributions
Zhiming Cheng: conceptualization, methodology, writing — original draft. Shuai Wang: conceptualization, methodology, analysis, writing — review and editing, supervision, funding acquisition. Yunhan Gao: data curation. Zunjie Zhu: writing — review and editing, supervision. Chenggang Yan: writing — review and editing.
Corresponding author
Ethics declarations
Ethics Approval
This study uses data that are publicly available. The Institute Research Ethics Committee has confirmed that no ethical approval is required.
Consent to Participate
Informed consent was obtained from all individual participants included in the study.
Consent for Publication
The data used in this study were obtained from publicly available datasets. These datasets have been anonymized and do not contain any individual details, images, or videos, thus obviating the need to obtain publication consent from individual participants.
Competing Interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cheng, Z., Wang, S., Gao, Y. et al. Invariant Content Representation for Generalizable Medical Image Segmentation. J Digit Imaging. Inform. med. (2024). https://doi.org/10.1007/s10278-024-01088-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10278-024-01088-9