對於醫學圖像分割的領域自適應已成為一個重要的研究問題，因為訓練和測試圖像通常由不同種類的機器生成，例如 MRI 或 CT 或具有不同規格的同類型機器。 領域自適應的一種有效方法是傅里葉領域自適應，它能夠以低計算成本的方式達到具有競爭力的性能。 然而，傅里葉領域自適應在應用於醫學圖像分割時，會造成錯誤的風格轉換以及雜亂的噪聲特徵。 在這項工作中，我們介紹了一種應用於醫學圖像分割的新型傅里葉風格變換。 有別於原本傅里葉領域自適應中隨機地選擇目標圖像，我們的新方法首先通過使用相似度計算的方式來為傅里葉風格轉換 選擇合適的目標圖像，這可以減少源域和目標域之間的差距。 之後，我們利用分割標籤來尋找具有相同標籤的區域，並在目標圖像中選擇一個重要區域進行 傅里葉風格轉換，這可以通過使用整個目標圖像來避免產生噪聲特徵。 最後，我們採用了熵最小化和類型比例優先級的無源域自適應架構。 這樣的框架對於困難的醫學分割是強健且穩定的。 在兩個醫學數據集上的模擬實驗表明，與原本的傅里葉領域自適應相比，新方法具有更優越的性能。

Domain adaptation for medical image segmentation has become an important
research issue, since training and test images are usually produced by different
types of machines, such as MRI or CT or the same type of machine with different
specifications. One effective approach for domain adaptation is Fourier domain
adaptation, which can achieve a competitive performance with low computational
costs. However, Fourier domain adaptation suffers from wrong transfer style and
noisy features when applying to medical image segmentation. In this work, we
introduced a novel Fourier style transform (FST) for medical image segmentation. Instead of randomly selecting a target image in Fourier domain adaptation,
the new approach first chooses a suitable target image for FST by using a popular quality measure, which can reduce the gaps between the source and target
domains. Afterward, we utilize a segmentation label matching scheme to select a significant area in the target image for FST, which can avoid incur noisy
features by using the whole target image. Finally, we adapt source-free-domainadaptation architecture with entropy minimization and class-ratio priority. Such a framework can be robust to difficult medical segmentation. Simulations reveal that the new approach has superior performance compared with the Fourier
domain adaptation on two medical datasets.

References
[1] M. Bateson, H. Kervadec, J. Dolz, H. Lombaert, and I. Ben Ayed, “Sourcerelaxed domain adaptation for image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention,
pp. 490–499, Springer, 2020.
[2] Y. Yang and S. Soatto, “Fda: Fourier domain adaptation for semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4085–4095, 2020.
[3] X. Zhuang, “Challenges and methodologies of fully automatic whole heart
segmentation: a review,” Journal of healthcare engineering, vol. 4, no. 3,
pp. 371–407, 2013.
[4] X. Zhuang and J. Shen, “Multi-scale patch and multi-modality atlases for
whole heart segmentation of mri,” Medical image analysis, vol. 31, pp. 77–87,
2016.
[5] Q. Liu, Q. Dou, L. Yu, and P. A. Heng, “Ms-net: multi-site network for improving prostate segmentation with heterogeneous mri data,” IEEE transactions on medical imaging, vol. 39, no. 9, pp. 2713–2724, 2020.
[6] K. Saito, Y. Ushiku, and T. Harada, “Asymmetric tri-training for unsupervised domain adaptation,” in International Conference on Machine Learning, pp. 2988–2997, PMLR, 2017.
[7] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley,
S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” Advances in neural information processing systems, vol. 27, 2014.
[8] Q. Dou, C. Ouyang, C. Chen, H. Chen, B. Glocker, X. Zhuang, and P.-A.
Heng, “Pnp-adanet: Plug-and-play adversarial domain adaptation networkwith a benchmark at cross-modality cardiac segmentation,” arXiv preprint
arXiv:1812.07907, 2018.
[9] A. Almahairi, S. Rajeshwar, A. Sordoni, P. Bachman, and A. Courville,
“Augmented cyclegan: Learning many-to-many mappings from unpaired
data,” in International Conference on Machine Learning, pp. 195–204,
PMLR, 2018.
[10] J. Hoffman, E. Tzeng, T. Park, J.-Y. Zhu, P. Isola, K. Saenko, A. Efros,
and T. Darrell, “Cycada: Cycle-consistent adversarial domain adaptation,”
in International conference on machine learning, pp. 1989–1998, Pmlr, 2018.
[11] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “Semantic image segmentation with deep convolutional nets and fully connected
crfs,” arXiv preprint arXiv:1412.7062, 2014.
[12] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for
semantic segmentation,” in Proceedings of the IEEE conference on computer
vision and pattern recognition, pp. 3431–3440, 2015.
[13] L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoderdecoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV),
pp. 801–818, 2018.
[14] G. Csurka, “A comprehensive survey on domain adaptation for visual applications,” Domain adaptation in computer vision applications, pp. 1–35,
2017.
[15] M. Wang and W. Deng, “Deep visual domain adaptation: A survey,” Neurocomputing, vol. 312, pp. 135–153, 2018.
[16] Z. Zheng and Y. Yang, “Unsupervised scene adaptation with memory regularization in vivo,” arXiv preprint arXiv:1912.11164, 2019.
[17] Z. Zheng and Y. Yang, “Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation,” International Journal
of Computer Vision, vol. 129, no. 4, pp. 1106–1120, 2021.
[18] K. Mei, C. Zhu, J. Zou, and S. Zhang, “Instance adaptive self-training for unsupervised domain adaptation,” in European conference on computer vision,
pp. 415–430, Springer, 2020.
[19] M. Bateson, J. Dolz, H. Kervadec, H. Lombaert, and I. B. Ayed, “Constrained domain adaptation for image segmentation,” IEEE Transactions
on Medical Imaging, vol. 40, no. 7, pp. 1875–1887, 2021.
[20] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks
for biomedical image segmentation,” in International Conference on Medical
image computing and computer-assisted intervention, pp. 234–241, Springer,
2015.
[21] P. Kingma Diederik and J. B. Adam, “A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
[22] S. Xie, R. Girshick, P. Doll´ar, Z. Tu, and K. He, “Aggregated residual transformations for deep neural networks,” in Proceedings of the IEEE conference
on computer vision and pattern recognition, pp. 1492–1500, 2017.
[23] M. Frigo and S. G. Johnson, “Fftw: An adaptive software architecture for the
fft,” in Proceedings of the 1998 IEEE International Conference on Acoustics,
Speech and Signal Processing, ICASSP’98 (Cat. No. 98CH36181), vol. 3,
pp. 1381–1384, IEEE, 1998.
[24] Y. Grandvalet and Y. Bengio, “Semi-supervised learning by entropy minimization,” Advances in neural information processing systems, vol. 17, 2004.
[25] J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired image-to-image
translation using cycle-consistent adversarial networks,” in Proceedings of
the IEEE international conference on computer vision, pp. 2223–2232, 2017[26] C. Chen, Q. Dou, H. Chen, J. Qin, and P. A. Heng, “Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature
alignment for medical image segmentation,” IEEE transactions on medical
imaging, vol. 39, no. 7, pp. 2494–2505, 2020.
[27] X. Chen, C. Lian, L. Wang, H. Deng, T. Kuang, S. Fung, J. Gateno, P.-T.
Yap, J. J. Xia, and D. Shen, “Anatomy-regularized representation learning for cross-modality medical image segmentation,” IEEE transactions on
medical imaging, vol. 40, no. 1, pp. 274–285, 2020.
[28] S. Stan and M. Rostami, “Privacy preserving domain adaptation for semantic
segmentation of medical images,” arXiv preprint arXiv:2101.00522, 2021.
[29] D. Tomar, M. Lortkipanidze, G. Vray, B. Bozorgtabar, and J.-P. Thiran, “Self-attentive spatial adaptive normalization for cross-modality domain adaptation,” IEEE Transactions on Medical Imaging, vol. 40, no. 10,
pp. 2926–2938, 2021.
[30] X. Han, L. Qi, Q. Yu, Z. Zhou, Y. Zheng, Y. Shi, and Y. Gao, “Deep symmetric adaptation network for cross-modality medical image segmentation,”
IEEE transactions on medical imaging, vol. 41, no. 1, pp. 121–132, 2021.
[31] Y. Zhang, P. David, H. Foroosh, and B. Gong, “A curriculum domain adaptation approach to the semantic segmentation of urban scenes,” IEEE transactions on pattern analysis and machine intelligence, vol. 42, no. 8, pp. 1823–
1841, 2019.
[32] N. Karani, E. Erdil, K. Chaitanya, and E. Konukoglu, “Test-time adaptable neural networks for robust medical image segmentation,” Medical Image
Analysis, vol. 68, p. 101907, 2021.
[33] D. Wang, E. Shelhamer, S. Liu, B. Olshausen, and T. Darrell, “Tent:
Fully test-time adaptation by entropy minimization,” arXiv preprint
arXiv:2006.10726, 2020.