Fourier Semi-Supervised Learning Method for Medical Image Segmentation

被引：0

作者：

Wang, Pengju ^{[1
]}

Zhang, Xiao ^{[1
]}

Ji, Zhenyan ^{[1
]}

Yu, Jin ^{[2
]}

Song, Yuezeng ^{[1
]}

机构：

[1] School of Software Engineering, Beijing Jiaotong University, Beijing

[2] Department of Neurology, First Medieal Center, PLA General Hospital, Beijing

来源：

Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications | 2024年 / 47卷 / 03期

关键词：

consistency regularization constraint; Fourier transformation; medical image segmentation; semi-supervised learning;

D O I：

10.13190/j.jbupt.2023-102

中图分类号：

学科分类号：

摘要：

The scarcity of labeled data is a challenging problem that affects the segmentation accuracy of medical images. Aiming to solve this problem, a new semi-supervised learning method based on Fourier transform and consistent constraintis proposed. In the case of a small amount of annotated data, the output of unannotated data via Fourier transform interpolation and model segmentation is spatially consistent with the output of reverse operation, and the consistency regularization constraint for unannotated data is constructed to improve the model performance of fully supervised learning. The experimental results, based on the openly available datasets ofthe automatic cardiac diagnosis challenge, synapse and computed tomography lymph node, demonstratethat the proposed algorithm is superior to baseline methods and can be integrated with existing state-of-the-art semi-supervised medical image segmentation methods to improve their segmentation performances. © 2024 Beijing University of Posts and Telecommunications. All rights reserved.

引用

页码：69 / 74and89

页数：7420

共 23 条

[11]

SHIMIZU A, NARIHIRA T, FURUKAWA D, Et al., Ensemble segmentation using adaboost with application to liver lesion extraction from a CT volume [J/OL], The MIDAS Journal, 36, 1, (2008)

[12]

ZHANG T Q, KANG B, MENG X F, Et al., Intracranial hemorrhage recognition algorithm based on U-Net, Journal of Beijing University of Posts and Telecommunications, 43, 3, pp. 92-98, (2020)

[13]

LIAO Z, XU K, FAN N., Swin transformer assisted prior attention network for medical image segmentation [C], International Conference on Computing and Artificial Intelligence, pp. 491-497, (2022)

[14]

HUANG L T, LIU K X, NIU K, Et al., Automatic mucus plug recognition in CT images of asthma patients based on deep learning [J], Journal of Beijing University of Posts and Telecommunications, 45, 4, pp. 58-63, (2022)

[15]

CHAITANYA K, ERDIL E, KARANI N, Et al., Cont-rastive learning of global and local features for medical image segmentation with limited annotations [C], Advances in neural information processing systems, pp. 12546-12558, (2020)

[16]

LIU Y, WANG W, LUO G, Et al., A contrastive consistency semi-supervised left atrium segmentation model, Computerized Medical Imaging and Graphics, 99, (2022)

[17]

HAN K, LIU L, SONG Y, Et al., An effective semi-supervised approach for liver CT image segmentation, IEEE Journal of Biomedical and Health Informatics, 26, 8, pp. 3999-4007, (2022)

[18]

LAINE S, AILA T., Temporal ensembling for semi-supervised learning, (2017)

[19]

TARVAINEN A, VALPOLA H., Mean teachers are better role models

[20]

weight-averaged consistency targets improve semi-supervised deep learning results [C], Conference and Workshop on Neural Information Processing Systems, pp. 1195-1204, (2017)

← 1 2 3 →