多阶U-Net甲状腺超声图像自动分割方法

doi:10.3778/j.issn.1002-8331.2110-0357

摘要/Abstract

摘要： 甲状腺超声图像广泛应用于甲状腺相关疾病的诊断。针对甲状腺超声图像对比度低、边缘模糊以及散斑噪声严重等问题，提出一种基于多阶U-Net的深度卷积网络模型，用于实现甲状腺腺体与甲状腺结节的自动分割。该模型以U-Net为基本网络框架，通过不断进阶的特征融合，以实现图像边缘的信息提取。同时，在模型中使用了一种多尺度残差卷积模块以进一步提升分割精度。对比实验结果表明，该模型相较于其他方法能够获得更好的分割结果，具有一定的临床应用价值。

关键词: 甲状腺超声图像, 图像分割, 多阶U-Net

Abstract: 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.

Key words: thyroid ultrasound images, image segmentation, multi-stage U-Net

王波, 袁凤强, 陈宗仁, 胡建华, 杨家慧, 刘侠. 多阶U-Net甲状腺超声图像自动分割方法[J]. 计算机工程与应用, 2023, 59(5): 205-212.

WANG Bo, YUAN Fengqiang, CHEN Zongren, HU Jianhua, YANG Jiahui, LIU Xia. Multi-Stage U-Net Automatic Segmentation of Thyroid Ultrasound Images[J]. Computer Engineering and Applications, 2023, 59(5): 205-212.

参考文献

[1] 周建桥，詹维伟.2020年中国超声甲状腺影响报告和数据系统（C-TIRADS）指南解读[J].诊断学理论与实践，2020，19（4）：350-353.
ZHOU J Q，ZHAN W W.Interpretation of 2020 Chinese guidelines for thyroid imaging reporting and data system（C-TIRADS）for ultrasound[J].Journal of Diagnostics Concepts & Practice，2020，19（4）：350-353.
[2] YOKOYAMA N，NAGAYAMA Y，KAKEZONO F，et al.Determination of the volume of the thyroid gland by a high resolutional ultrasonic scanner[J].Journal of Nuclear Medicine，1986，27（9）：1475.
[3] CHEN J，YOU H，LI K.A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images[J].Computer Methods and Programs in Biomedicine，2020，185：105329.
[4] SHELHAMER E，LONG J，DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（4）：640-651.
[5] RONNEBERGER O，FISCHER P，BROX T.U-net：convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-assisted Intervention，2015：334-241.
[6] KAUR J，JINDAL A.Comparison of thyroid segmentation algorithms in ultrasound and scintigraphy images[J].International Journal of Computer Applications，2012，50（23）：24-27.
[7] KOLLORZ E N K，HAHN D A，LINKE R，et al.Quantification of thyroid volume using 3D ultrasound imaging[J].IEEE Transactions on Medical Imaging，2008，27（4）：457-466.
[8] POUDEL P，ILLANES A，HANSEN C，et al.Active contours extension and similarity indicators for improved 3D segmentation of thyroid ultrasound images[C]//Medical Imaging 2017：Imaging Informatics for Healthcare，Research，and Applications，2017：1-8.
[9] NUGROHO H A，NUGROHO A，CHORIDAH L.Thyroid nodule segmentation using active contour bilateral filtering on ultrasound images[C]//International Conference on Quality in Research（QiR），2015：43-46.
[10] GUI L，LI C，YANG X.Medical image segmentation based on level set and isoperimetric constraint[J].Physica Medica，2017，42：162-173.
[11] NARAYAN N S，MARZILIANO P，KANAGALINGAM J，et al.Speckle patch similarity for echogenicity-based multiorgan segmentation in ultrasound images of the thyroid gland[J].IEEE J Biomed Health Inform，2017，21（1）：172-183.
[12] POUDEL P，ILLANES A，HANSEN C，et al.Evaluation of commonly used algorithms for thyroid ultrasound images segmentation and improvement using machine learning approaches[J].J Healthcare Eng，2018：1-13.
[13] ZHAO J，ZHENG W，ZHANG L，et al.Segmentation of ultrasound images of thyroid nodule for assisting fine needle aspiration cytology[J].Health Information Science and Systems，2013，1（1）：1-12.
[14] ALRUBAIDI W M H，PENG B，YANG Y，et al.An interactive segmentation algorithm for thyroid nodules in ultrasound images[C]//International Conference on Intelligent Computing.Cham：Springer，2016：107-115.
[15] WUNDERLING T，GOLLA B，POUDEL P，et al.Comparison of thyroid segmentation techniques for 3D ultrasound[C]//Proceedings of SPIE Medical Imaging，2017.
[16] HE X X，GUO B J，LEI Y，et al.3D thyroid segmentation in CT using self-attention convolutional neural network[C]//Proceedings of SPIE Medical Imaging，Houston，Texas，United States，2020.
[17] MA J，WU F，JIANG T，et al，Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks[J].International Journal of Computer Assisted Radiology and Surgery，2017，12（11）：1895-1910.
[18] YING X，YU Z，YU R，et al，Thyroid nodule segmentation in ultrasound images based on cascaded convolutional neural network[C]//International Conference on Neural Information Processing.Cham：Springer，2018：373-384.
[19] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//Proceedings of International Conference on Learning Representations，2015：1-14.
[20] 王波，李梦翔，刘侠.基于改进U-Net网络的甲状腺结节超声图像分割方法[J].电子与信息学报，2022，44（2）：514-522.
WANG B，LI M X，LIU X.Ultrasound image segmentation method of thyroid nodules based on the improved U-Net network[J].Journal of Electronics & Information Technology，2022，44（2）：514-522.
[21] SZEGEDY C，LIU W，JIA Y，et al.Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition，2015.
[22] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[23] ZHOU Z W，MD M，RAHMAN S，et al.UNet++：a nested U-Net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support，2018：3-11.
[24] BADRINARAYANAN V，KENDALL A，CIPOLLA R.Segnet：a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（12）：2481-2495.
[25] SCHLEMPER J，OKTAY O，SCHAAP M，et al.Attention gated networks：learning to leverage salient regions in medical images[J].Medical Image Analysis，2019，53：197-207.
[26] AZAD R，ASADI-AGHBOLAGHI M，FATHY M，et al.Bi-directional ConvLSTM U-Net with densley connected convolutions[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop，Seoul，Korea（South），2019：406-415.