
浏览全部资源
扫码关注微信
1.重庆大学计算机学院模式识别实验室,重庆
2.陆军军医大学(第三军医大学)第二附属医院普通外科,重庆
文 静,E-mail: wj@cqu.edu.cn
收稿日期:2024-09-26,
修回日期:2024-11-02,
纸质出版日期:2025-07-30
移动端阅览
郑水婧,杨君,蔡瑜娇,等.基于小波变换和CNN-Transformer的超声甲状腺结节分割算法研究[J].陆军军医大学学报,2025,47(14):1595-1601.DOI:10.16016/j.2097-0927.202409145.
ZHENG S J,YANG J,CAI Y J,et al.Ultrasound thyroid nodule segmentation algorithm based on wavelet transform and CNN-Transformer[J].J Army Med Univ,2025,47(14):1595-1601.DOI:10.16016/j.2097-0927.202409145.
郑水婧,杨君,蔡瑜娇,等.基于小波变换和CNN-Transformer的超声甲状腺结节分割算法研究[J].陆军军医大学学报,2025,47(14):1595-1601.DOI:10.16016/j.2097-0927.202409145. DOI:
ZHENG S J,YANG J,CAI Y J,et al.Ultrasound thyroid nodule segmentation algorithm based on wavelet transform and CNN-Transformer[J].J Army Med Univ,2025,47(14):1595-1601.DOI:10.16016/j.2097-0927.202409145. DOI:
目的
2
融合小波变换和CNN-Transformer构建甲状腺结节自动分割网络,以提升甲状腺结节超声影像的智能分割效率和精准度。
方法
2
收集2023年5月至2024年2月在陆军军医大学第二附属医院超声科获取的1 371套甲状腺结节超声影像。经过预处理和标准化后,数据按照8∶1∶1的比例划分为训练集、验证集和测试集。以UNet为基础,将CNN与Swin-Transformer并联作为编码器,并在编码器与解码器之间插入小波变换模块,完成甲状腺结节分割网络的构建。使用准确率、IoU和Dice系数指标在收集的内部数据集上评估分割模型性能。
结果
2
本研究最终在收集的1 371套超声甲状腺结节上进行验证,平均Dice系数达到79.63%,IoU达到67.3%。相较于UNet,分割准确度提升1.02%。其甲状腺结节分割结果位置准确,边缘平滑。分割出的甲状腺结节相比于其他方法分割出的结节,在轮廓形态上与医师的手工分割结果吻合度更高。相较于UNet方法,本方法对结节的纹理学习更加充分,规避了结节容易错误分割为周围组织的情况。
结论
2
构建的基于小波变换和CNN-Transformer的分割模型精度优于UNet、Attention-UNet、UNetv2等UNet变种网络以及SAM Med2D分割大模型等先进分割方法,能有效应用于超声甲状腺结节的精确分割,提升医师的工作效率。
Objective To develop an automatic segmentation network for thyroid nodules by integrating wavelet transform and CNN-Transformer in order to improve the efficiency and accuracy of ultrasound image segmentation. Methods A total of 1 371 sets of ultrasound images of thyroid nodules were collected from Department of Ultrasonography of Second Affiliated Hospital of Army Medical University between May 2023 and February 2024. After preprocessing and normalization
the data were divided into training
validation
and testing sets in a ratio of 8∶1∶1. Based on UNet
CNN and Swin-Transformer were used in parallel as the encoder
with a wavelet transform module inserted between the encoder and decoder to construct a thyroid nodule segmentation network. The performance of the segmentation model was evaluated on the collected internal dataset using accuracy
IoU
and Dice coefficient metrics. Results The finally verified 1 371 sets of ultrasonic thyroid nodules had an average Dice coefficient of 79.63% and an IoU of 67.30%. Compared with UNet
the segmentation accuracy was improved by 1.02%. The segmentation model obtained accurate location and smooth edges of thyroid nodules
and the segmentation was more consistent in thyroid nodule edge and morphology with those marked by doctors manually when compared with other segmentations. Compared with UNet
this segmentation method can learn the texture of nodules more fully and avoid the situation that nodules had been incorrectly divided into surrounding tissues. Conclusion Our developed segmentation model based on wavelet transform and CNN-Transformer demonstrates better segmentation accuracy in comparison to conventional UNet variants
such as UNet
Attention-UNet
and UNetv2
and medical segment anything models like SAM Med2D. This segmentation method enables accurate segmentation of ultrasound thyroid nodules
thereby enhancing clinical workflow efficiency through automated precise delineation.
HAUGEN B R , ALEXANDER E K , BIBLE K C , et al . 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American Thyroid Association guidelines task force on thyroid nodules and differentiated thyroid cancer [J]. Thyroid , 2016 , 26 ( 1 ): 1 - 133 . DOI: 10.1089/thy.2015.0020 http://dx.doi.org/10.1089/thy.2015.0020 .
DURANTE C , GRANI G , LAMARTINA L , et al . The diagnosis and management of thyroid nodules: a review [J]. JAMA , 2018 , 319 ( 9 ): 914 - 924 . DOI: 10.1001/jama.2018.0898 http://dx.doi.org/10.1001/jama.2018.0898 .
SAVELONAS M A , IAKOVIDIS D K , LEGAKIS I , et al . Active contours guided by echogenicity and texture for delineation of thyroid nodules in ultrasound images [C]// IEEE Transactions on Information Technology in Biomedicine . IEEE , 2009 : 519 - 527 . DOI: 10.1109/TITB.2008.2007192 http://dx.doi.org/10.1109/TITB.2008.2007192 .
JARDIM S V B , FIGUEIREDO M A T . Automatic contour estimation in fetal ultrasound images [C]// Proceedings 2003 International Conference on Image Processing . IEEE , 2003 . DOI: 10.1109/ICIP.2003.1246869 http://dx.doi.org/10.1109/ICIP.2003.1246869 .
WU S B , ZHU Q S , XIE Y Q . Evaluation of various speckle reduction filters on medical ultrasound images [C]// 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . IEEE , 2013 : 1148 - 1151 . DOI: 10.1109/EMBC.2013.6609709 http://dx.doi.org/10.1109/EMBC.2013.6609709 .
TUCERYAN M , JAIN A K . Texture analysis in handbook of pattern recognition and computer vision [J]. Singapore : World Scientific Publishing , 1993 : 235 - 276 . DOI: 10.1142/9789814343138_0010 http://dx.doi.org/10.1142/9789814343138_0010 .
PEEPLES J , XU W H , ZARE A . Histogram layers for texture analysis [J]. IEEE Trans Artif Intell , 2022 , 3 ( 4 ): 541 - 552 . DOI: 10.1109/TAI.2021.3135804 http://dx.doi.org/10.1109/TAI.2021.3135804 .
RODRIGUEZ M X B , GRUSON A , POLANIA L F , et al . Deep adaptive wavelet network [C]// Workshop on Applications of Computer Vision . IEEE , 2020 . DOI: 10.1109/WACV45572.2020.9093580 http://dx.doi.org/10.1109/WACV45572.2020.9093580 .
CHEN L C , PAPANDREOU G , KOKKINOS I , et al . DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs [J]. IEEE Trans Pattern Anal Mach Intell , 2018 , 40 ( 4 ): 834 - 848 . DOI: 10.1109/TPAMI.2017.2699184 http://dx.doi.org/10.1109/TPAMI.2017.2699184 .
DIAKOGIANNIS F I , WALDNER F , CACCETTA P , et al . ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data [J]. ISPRS J Photogramm Remote Sens , 2020 , 162 : 94 - 114 . DOI: 10.1016/j.isprsjprs.2020.01.013 http://dx.doi.org/10.1016/j.isprsjprs.2020.01.013 .
RONNEBERGER O , FISCHER P , BROX T . U-Net: convolutional networks for biomedical image segmentation [C]// Medical Image Computing and Computer-Assisted Intervention——MICCAI 2015 . Cham : Springer International Publishing , 2015 : 234 - 241 . DOI: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 .
OKTAY O , SCHLEMPER J , FOLGOC L L , et al . Attention U-Net: learning where to look for the pancreas [EB/OL]. ( 2018-04-11 ). https://arxiv.org/abs/1804.03999 https://arxiv.org/abs/1804.03999 .
PENG Y P , SONKA M , CHEN D Z . U-Net v2: rethinking the skip connections of U-Net for medical image segmentation [EB/OL]. ( 2023-11-29 ). https://arxiv.org/abs/2311.17791v2 https://arxiv.org/abs/2311.17791v2 .
CHEN L C , PAPANDREOU G , SCHROFF F , et al . Rethinking atrous convolution for semantic image segmentation [EB/OL]. ( 2017-06-17 ). https://arxiv.org/abs/1706.05587 https://arxiv.org/abs/1706.05587 .
CHENG J , YE J , DENG Z , et al . SAM-Med 2 D[EB/OL]. ( 2023-08-30 ). https://arxiv.org/abs/2308.16184 https://arxiv.org/abs/2308.16184 .
MILLETARI F , NAVAB N , AHMADI S A . V-net: fully convolutional neural networks for volumetric medical image segmentation [C]// 2016 Fourth International Conference on 3D Vision (3DV) . IEEE , 2016 : 565 - 571 . DOI: 10.1109/3DV.2016.79 http://dx.doi.org/10.1109/3DV.2016.79 .
向永嘉 , 吴毅 , 张小勤 , 等 . 基于DenseUnet模型的核磁共振图像下肛提肌的自动分割 [J]. 第三军医大学学报 , 2021 , 43 ( 18 ): 1720 - 1728 . DOI: 10.16016/j.1000-5404.202102089 http://dx.doi.org/10.16016/j.1000-5404.202102089 .
XIANG Y J , WU Y , ZHANG X Q , et al . Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model [J]. J Third Mil Med Univ , 2021 , 43 ( 18 ): 1720 - 1728 . DOI: 10.16016/j.1000-5404.202102089 http://dx.doi.org/10.16016/j.1000-5404.202102089 .
吴哲 , 许杉杉 , 崔慧林 , 等 . 基于Vgg16-Unet模型的MRI图像下前列腺分区智能分割研究 [J]. 陆军军医大学学报 , 2023 , 45 ( 13 ): 1441 - 1449 . DOI: 10.16016/j.2097-0927.202211045 http://dx.doi.org/10.16016/j.2097-0927.202211045 .
WU Z , XU S S , CUI H L , et al . Intelligent segmentation of prostate partitioning in MRI images based on Vgg16-Unet modeling [J]. J Army Med Univ , 2023 , 45 ( 13 ): 1441 - 1449 . DOI: 10.16016/j.2097-0927.202211045 http://dx.doi.org/10.16016/j.2097-0927.202211045 .
AVOLA D , CINQUE L , FAGIOLI A , et al . Multimodal feature fusion and knowledge-driven learning via experts consult for thyroid nodule classification [J]. IEEE Trans Circuits Syst Video Technol , 2022 , 32 ( 5 ): 2527 - 2534 . DOI: 10.1109/TCSVT.2021.3074414 http://dx.doi.org/10.1109/TCSVT.2021.3074414 .
HU Y Z , GUO Y , WANG Y Y , et al . Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model [J]. Med Phys , 2019 , 46 ( 1 ): 215 - 228 . DOI: 10.1002/mp.13268 http://dx.doi.org/10.1002/mp.13268 .
MA J L , WU F , JIANG T A , et al . Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks [J]. Int J Comput Assist Radiol Surg , 2017 , 12 ( 11 ): 1895 - 1910 . DOI: 10.1007/s11548-017-1649-7 http://dx.doi.org/10.1007/s11548-017-1649-7 .
XIE X Z , SHI F Q , NIU J W , et al . Breast ultrasound image classification and segmentation using convolutional neural networks [C]// Advances in Multimedia Information Processing——PCM 2018 . Cham : Springer International Publishing , 2018 : 200 - 211 . DOI: 10.1007/978-3-030-00764-5_19 http://dx.doi.org/10.1007/978-3-030-00764-5_19 .
HE K M , GKIOXARI G , DOLLAR P , et al . Mask R-CNN [J]. IEEE Trans Pattern Anal Mach Intell , 2020 , 42 ( 2 ): 386 - 397 . DOI: 10.1109/tpami.2018.2844175 http://dx.doi.org/10.1109/tpami.2018.2844175 .
BYRA M , JAROSIK P , SZUBERT A , et al . Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network [J]. Biomed Signal Process Control , 2020 , 61 : 102027 . DOI: 10.1016/j.bspc. 2020. 102027 http://dx.doi.org/10.1016/j.bspc.2020.102027 .
YING X , YU Z H , YU R G , et al . Thyroid nodule segmentation in ultrasound images based on cascaded convolutional neural network [C]// Neural Information Processing . Cham : Springer International Publishing , 2018 : 373 - 384 . DOI: 10.1007/978-3-030-04224-0_32 http://dx.doi.org/10.1007/978-3-030-04224-0_32 .
VASWANI A , SHAZEER N M , PARMAR N , et al . Attention is all you need [EB/OL]. ( 2023-08-02 ). https://arxiv.org/abs/1706.03762 https://arxiv.org/abs/1706.03762 .
HUANG X H , DENG Z F , LI D D , et al . MISSFormer: an effective medical image segmentation transformer [EB/OL]. ( 2021-09-15 ). https://arxiv.org/abs/2109.07162v2 https://arxiv.org/abs/2109.07162v2 .
LIN A L , CHEN B Z , XU J Y , et al . DS-TransUNet: dual swin transformer U-Net for medical image segmentation [J]. IEEE Trans Instrum Meas , 2022 , 71 : 4005615 . DOI: 10.1109/TIM.2022.3178991 http://dx.doi.org/10.1109/TIM.2022.3178991 .
AZAD R , JIA Y W , AGHDAM E K , et al . Enhancing medical image segmentation with TransCeption: a multi-scale feature fusion approach [EB/OL]. ( 2023-06-25 ). https://arxiv.org/abs/2301.10847v1 https://arxiv.org/abs/2301.10847v1 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621