Multi-Stage U-Net Automatic Segmentation of Thyroid Ultrasound Images

被引：0

作者：

Wang, Bo ^{[1
,3
]}

Yuan, Fengqiang ^{[2
]}

Chen, Zongren ^{[1
]}

Hu, Jianhua ^{[1
]}

Yang, Jiahui ^{[1
]}

Liu, Xia ^{[2
,3
]}

机构：

[1] Computer Engineering Technical College(Artificial Intelligence College), Guangdong Polytechnic of Science and Technology, Guangdong, Zhuhai

[2] School of Automation, Harbin University of Science and Technology, Harbin

[3] Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration, Harbin

来源：

Computer Engineering and Applications | 2024年 / 59卷 / 05期

关键词：

image segmentation; multi-stage U-Net; thyroid ultrasound images;

D O I：

10.3778/j.issn.1002-8331.2110-0357

中图分类号：

学科分类号：

摘要：

Thyroid ultrasonography is widely used in the diagnosis of thyroid diseases. To solve the problems of low contrast, blurred edges and serious speckle noise in thyroid ultrasound images, a deep convolutional network model based on multi-stage U-Net is proposed to achieve automatic segmentation of thyroid glands and thyroid nodules. Using U-Net as the basic network framework, this model realizes the deep information extraction of image edge through continuously advanced feature fusion. Meanwhile, a multi-scale residual convolution module is used in the model to further improve the segmentation accuracy. The comparative experimental results show that this model can obtain better segmentation results compared with other methods, which has certain clinical application value. © 2024 Moscow Polytechnic University. All rights reserved.

引用

页码：205 / 212

页数：7

共 26 条

[1]

ZHOU J Q, ZHAN W W., Interpretation of 2020 Chinese guidelines for thyroid imaging reporting and data system (C-TIRADS)for ultrasound, Journal of Diagnostics Concepts & Practice, 19, 4, pp. 350-353, (2020)

[2]

YOKOYAMA N, NAGAYAMA Y, KAKEZONO F, Et al., Determination of the volume of the thyroid gland by a high resolutional ultrasonic scanner, Journal of Nuclear Medicine, 27, 9, (1986)

[3]

CHEN J, YOU H, LI K., A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images, Computer Methods and Programs in Biomedicine, 185, (2020)

[4]

SHELHAMER E, LONG J, DARRELL T., Fully convolutional networks for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 4, pp. 640-651, (2017)

[5]

RONNEBERGER O, FISCHER P, BROX T., U-net: convolutional networks for biomedical image segmentation, Proceedings of International Conference on Medical Image Computing and Computer- assisted Intervention, pp. 334-241, (2015)

[6]

KAUR J, JINDAL A., Comparison of thyroid segmentation algorithms in ultrasound and scintigraphy images, International Journal of Computer Applications, 50, 23, pp. 24-27, (2012)

[7]

KOLLORZ E N K, HAHN D A, LINKE R, Et al., Quantification of thyroid volume using 3D ultrasound imaging, IEEE Transactions on Medical Imaging, 27, 4, pp. 457-466, (2008)

[8]

POUDEL P, ILLANES A, HANSEN C, Et al., Active contours extension and similarity indicators for improved 3D segmentation of thyroid ultrasound images, Medical Imaging 2017: Imaging Informatics for Healthcare, Research, and Applications, pp. 1-8, (2017)

[9]

NUGROHO H A, NUGROHO A, CHORIDAH L., Thyroid nodule segmentation using active contour bilateral filtering on ultrasound images, International Conference on Quality in Research(QiR), pp. 43-46, (2015)

[10]

GUI L, LI C, YANG X., Medical image segmentation based on level set and isoperimetric constraint, Physica Medica, 42, pp. 162-173, (2017)

← 1 2 3 →