Cancer 84, 219–227 (2017)įrankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. arXiv preprint arXiv:1907.02893 (2019)įocke, C.M., et al.: Interlaboratory variability of ki67 staining in breast cancer. arXiv preprint arXiv:1911.00804 (2019)Īrjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. KeywordsĪlbuquerque, I., Monteiro, J., Darvishi, M., Falk, T.H., Mitliagkas, I.: Generalizing to unseen domains via distribution matching. Moreover, our competitive results are also evaluated on the public dataset over the state-of-the-art DG methods. Compared with known DG methods, our method yields excellent performance in multiclass nucleus recognition of Ki67 IHC images, especially in the lost category cases. Furthermore, an appropriate implementation is attained by applying the pruning method to different parts of the framework. In addition, the model is optimized by fine-tuning on merged domains to eliminate the interference of class mismatching among various domains. Partial model parameters are iteratively pruned according to the domain gap, which is caused by the data converting from a single domain into merged domains during training. In this paper, we propose a novel method to improve DG by searching the domain-agnostic subnetwork in a domain merging scenario. Specifically in the case of Ki67 images, learning invariant representation is at the mercy of the insufficient number of domains and the cell categories mismatching in different domains. Many recent studies have made some efforts on domain generalization (DG), whereas there are still some noteworthy limitations. However, quantitative analysis on multi-source Ki67 images is yet a challenging task in practice due to cross-domain distribution differences, which result from imaging variation, staining styles and lesion types. Ki67 is a significant biomarker in the diagnosis and prognosis of cancer, whose index can be evaluated by quantifying its expression in Ki67 immunohistochemistry (IHC) stained images.
0 Comments
Leave a Reply. |