Transfer learning of medical image segmentation based on optimal transport feature selection

被引：0

作者：

Wang S.-S. ^{[1
]}

Jiang L.-Y. ^{[1
]}

Yang Y.-B. ^{[2
]}

机构：

[1] College of Computer Science and Technology, Jilin University, Changchun

[2] Teaching Assessment Center, Air Force Aviation University, Changchun

来源：

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2022年 / 52卷 / 07期

关键词：

artificial intelligence; feature selection; image segmentation; optimal transport; transfer learning; unsupervised domain adaptation;

D O I：

10.13229/j.cnki.jdxbgxb20210652

中图分类号：

学科分类号：

摘要：

In the unsupervised domain adaptive transfer learning process，domain-independent features lead to the degradation of model segmentation performance，but there is no effective feature selection method for transfer learning segmentation model at present. To solve this problem，a general feature selection module for transfer learning was proposed based on optimal transport，which can be applied to various unsupervised domain adaptive image segmentation models. In this module，the optimal sample subsets of two domains are selected by weighted optimal transport of segmentation accuracy，and then the features of sample subsets are subjected to entropy regularized optimal transport，so as to obtain a descending list of similarity between two domains to remove domain-independent features. The universal feature selection module is applied to three unsupervised domain adaptive models to solve the problem of Covid-19 image segmentation，which improves the model performance to a certain extent. © 2022 Editorial Board of Jilin University. All rights reserved.

引用

页码：1626 / 1638

页数：12

共 27 条

[1]

Huang J, Smola A J, Gretton A, Et al., Correcting sample selection bias by unlabeled data, Advances in Neural Information Processing Systems, 19, pp. 601-608, (2007)

[2]

Ganin Y, Ustinova E, Ajakan H, Et al., Domain-adversarial training of neural networks[J], Advances in Computer Vision and Pattern Recognition, 17, 1, pp. 2096-2130, (2017)

[3]

Xu Xin-zheng, Ding Shi-fei, Shi Zhong-zhi, Et al., New theories and methods of image segmentation, Acta Electronica Sinica, 38, pp. 76-82, (2010)

[4]

He B S, Zhu F, Shi Y G., Medical image segmentation, Advanced Materials Research, 760-762, 4, pp. 1590-1593, (2013)

[5]

Courty N, Flamary R, Tuia D, Et al., Optimal transport for domain adaptation[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 9, pp. 1853-1865, (2017)

[6]

Courty N, Flamary R, Habrard A, Et al., Joint distribution optimal transportation for domain adaptation, Advances in Neural Information Processing Systems, 30, pp. 3731-3740, (2017)

[7]

Tzeng E, Hoffman J, Zhang N, Et al., Deep domain confusion: maximizing for domain invariance

[8]

Ruan C, Wang W, Hu H, Et al., Category-level adversaries for semantic domain adaptation, IEEE Access, 7, pp. 83198-83208, (2019)

[9]

Hoffman J, Tzeng E, Park T, Et al., CyCADA: cycle-consistent adversarial domain adaptation, The 35th International Conference on Machine Learning, pp. 3162-3174, (2018)

[10]

Dou Q, Ouyang C, Chen C, Et al., Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss [C], Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 691-697, (2018)

← 1 2 3 →