Domain generalization on medical imaging classification using episodic training with task augmentation

Downey, 2014, The prognostic significance of tumour–stroma ratio in oestrogen receptor-positive breast cancer, Br. J. Cancer, 110, 1744, 10.1038/bjc.2014.69 Heimann, 2009, Comparison and evaluation of methods for liver segmentation from ct datasets, IEEE Trans. Med. Imag., 28, 1251, 10.1109/TMI.2009.2013851 Erickson, 2017, Machine learning for medical imaging, Radiographics, 37, 505, 10.1148/rg.2017160130 Shen, 2017, Deep learning in medical image analysis, Annu. Rev. Biomed. Eng., 19, 221, 10.1146/annurev-bioeng-071516-044442 Epstein, 2003, Iid: independently and indistinguishably distributed, J. Econ. Theor., 113, 32, 10.1016/S0022-0531(03)00121-2 Dundar, 2007, Learning classifiers when the training data is not iid, 2007, 756 Ghafoorian, 2017, Transfer learning for domain adaptation in mri: application in brain lesion segmentation, 516 Q. Dou, C. Ouyang, C. Chen, H. Chen, P.-A. Heng, Unsupervised Cross-Modality Domain Adaptation of Convnets for Biomedical Image Segmentations with Adversarial Loss, arXiv preprint arXiv:1804.10916. Zhang, 2018, Task driven generative modeling for unsupervised domain adaptation: application to x-ray image segmentation, 599 C. Li, Y. Zhang, Z. Liang, W. Ma, Y. Huang, X. Ding, Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/vein Classification, arXiv preprint arXiv:2103.09097. Chen, 2019, Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation, vol. 33, 865 Li, 2018, Domain generalization with adversarial feature learning, 5400 Carlucci, 2019, Domain generalization by solving jigsaw puzzles, 2229 Zhang, 2020, Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation, IEEE Trans. Med. Imag., 39, 2531, 10.1109/TMI.2020.2973595 Yoon, 2019, Generalizable feature learning in the presence of data bias and domain class imbalance with application to skin lesion classification, 365 Dou, 2019, Domain generalization via model-agnostic learning of semantic features, 6447 Q. Liu, C. Chen, J. Qin, Q. Dou, P.-A. Heng, Feddg: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space, arXiv preprint arXiv:2103.06030. Li, 2018, Deep domain generalization via conditional invariant adversarial networks, 624 Finn, 2017, Model-agnostic meta-learning for fast adaptation of deep networks, 1126 Bianconi, 2015, Discrimination between tumour epithelium and stroma via perception-based features, Neurocomputing, 154, 119, 10.1016/j.neucom.2014.12.012 Nava, 2015, Classification of tumor epithelium and stroma in colorectal cancer based on discrete tchebichef moments, 79 Huang, 2017, Epithelium-stroma classification in histopathological images via convolutional neural networks and self-taught learning, 1073 Qi, 2018, Label-efficient breast cancer histopathological image classification, IEEE J. Biomed. Health Inform., 23, 2108, 10.1109/JBHI.2018.2885134 Huang, 2017, Epithelium-stroma classification via convolutional neural networks and unsupervised domain adaptation in histopathological images, IEEE J. Biomed. Health Inform., 21, 1625, 10.1109/JBHI.2017.2691738 Q. Qi, X. Lin, C. Chen, W. Xie, Y. Huang, X. Ding, X. Liu, Y. Yu, Curriculum feature alignment domain adaptation for epithelium-stroma classification in histopathological images, IEEE J. Biomed. Health Inform.2021 25 (4) 1163–1172. Kainmüller, 2007, Shape constrained automatic segmentation of the liver based on a heuristic intensity model, vol. 109, 116 Wimmer, 2009, A generic probabilistic active shape model for organ segmentation, 26 S. D. S. Al-Shaikhli, M. Y. Yang, B. Rosenhahn, Automatic 3d Liver Segmentation Using Sparse Representation of Global and Local Image Information via Level Set Formulation, arXiv preprint arXiv:1508.01521. Dou, 2016, 3d deeply supervised network for automatic liver segmentation from ct volumes, 149 Yang, 2017, Automatic liver segmentation using an adversarial image-to-image network, 507 Long, 2016, Unsupervised domain adaptation with residual transfer networks, 136 Saito, 2018, Maximum classifier discrepancy for unsupervised domain adaptation, 3723 Zhu, 2019, Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources, vol. 33, 5989 Muandet, 2013, Domain generalization via invariant feature representation, 10 Motiian, 2017, Unified deep supervised domain adaptation and generalization, 5716 M. Ilse, J. M. Tomczak, C. Louizos, M. Welling, Diva: Domain Invariant Variational Autoencoders, arXiv preprint arXiv:1905.10427. Li, 2017, Deeper, broader and artier domain generalization, 5542 Li, 2019, Episodic training for domain generalization, 1446 Wang, 2020, Dofe: domain-oriented feature embedding for generalizable fundus image segmentation on unseen datasets, IEEE Trans. Med. Imag., 39, 4237, 10.1109/TMI.2020.3015224 R. Volpi, H. Namkoong, O. Sener, J. Duchi, V. Murino, S. Savarese, Generalizing to Unseen Domains via Adversarial Data Augmentation, arXiv preprint arXiv:1805.12018. Li, 2018, Learning to generalize: meta-learning for domain generalization Balaji, 2018, Metareg: towards domain generalization using meta-regularization, 998 Y. Li, Y. Yang, W. Zhou, T. M. Hospedales, Feature-critic Networks for Heterogeneous Domain Generalization, arXiv preprint arXiv:1901.11448. Gidaris, 2018, Dynamic few-shot visual learning without forgetting, 4367 Snell, 2017, Prototypical networks for few-shot learning, 4077 W.-Y. Chen, Y.-C. Liu, Z. Kira, Y.-C. F. Wang, J.-B. Huang, A Closer Look at Few-Shot Classification, arXiv preprint arXiv:1904.04232. Hadsell, 2006, Dimensionality reduction by learning an invariant mapping, vol. 2, 1735 Beck, 2011, Systematic analysis of breast cancer morphology uncovers stromal features associated with survival, Sci. Transl. Med., 3, 10.1126/scitranslmed.3002564 Linder, 2012, Identification of tumor epithelium and stroma in tissue microarrays using texture analysis, Diagn. Pathol., 7, 1, 10.1186/1746-1596-7-22 Kather, 2019, Predicting survival from colorectal cancer histology slides using deep learning: a retrospective multicenter study, PLoS Med., 16, 10.1371/journal.pmed.1002730 Landman, 2015, Miccai multi-atlas labeling beyond the cranial vault–workshop and challenge A. E. Kavur, M. A. Selver, O. Dicle, M. Barış, N. S. Gezer, CHAOS - combined (CT-MR) Healthy abdominal organ segmentation challenge data (Apr. 2019). doi:10.5281/zenodo.3362844. URL https://doi.org/10.5281/zenodo.3362844. Soler, 2010, 3d image reconstruction for comparison of algorithm database: a patient specific anatomical and medical image database, IRCAD, Strasbourg, France, Tech. Rep., 1, 1 P. Bilic, P. F. Christ, E. Vorontsov, G. Chlebus, H. Chen, Q. Dou, C.-W. Fu, X. Han, P.-A. Heng, J. Hesser, et al., The Liver Tumor Segmentation Benchmark (Lits), arXiv preprint arXiv:1901.04056. Krizhevsky, 2012, Imagenet classification with deep convolutional neural networks, 1097 Maaten, 2008, Visualizing data using t-sne, J. Mach. Learn. Res., 9, 2579