增强边缘特征的肺结节分割模型

doi:10.3778/j.issn.1002-8331.2207-0027

摘要/Abstract

摘要： 针对在肺结节分割过程中结节边缘像素点模糊导致模型分割精度低的问题，提出一种用于增强边缘特征的对称双分支结构分割模型GEU-Net（Gabor edge U-Net）。其主干分支使用U-Net来捕获结节整体视觉特征以及全局上下文信息，边缘分支则设计Gabor卷积模块提取结节边缘纹理特征，并通过跳跃连接对主干分支与边缘分支编码器提取到的特征进行融合。此外，提出一种融合交叉熵和Focal Loss的混合损失函数，用于解决两个分支在训练过程中存在的正负类样本不均衡问题。在公开数据集LIDC-IDRI以及LNDb上进行了结节分割实验，实验结果表明，GEU-Net分割模型在两个数据集上的Dice系数分别为92.79%和86.78%、平均交并比分别为87.53%和79.09%、召回率则分别为94.35%和87.43%，与基线算法相比分割性能得到了一定程度的改善。

关键词: 肺结节分割, U-Net, Gabor卷积, 边缘特征增强

Abstract: Aiming at the problem of low segmentation accuracy caused by blurred nodule edge pixels in lung nodule segmentation, a symmetric dual-branch structure segmentation model GEU-Net （Gabor edge U-Net） is proposed to enhance edge features. The main branch uses U-Net to capture the overall visual features of nodules as well as global contextual information, and the edge branch designs a Gabor convolutional module to extract nodule edge texture features, and fuses the features extracted by the main branch and the edge branch encoders through skip connections. In addition, a hybrid loss function that combines cross-entropy and Focal Loss is proposed to solve the problem of unbalanced positive and negative samples in the training process of the two branches. Nodule segmentation experiments are carried out on the public dataset LIDC-IDRI and LNDb, the experimental results show that the Dice coefficients of the GEU-Net segmentation model on the two datasets are 92.79% and 86.78%, respectively, the average intersection ratios are 87.53% and 79.09%, the recall rates are 94.35% and 87.43%, compared with baseline algorithm, the segmentation performance has been improved to a certain extent.

Key words: lung nodules segmentation, U-Net, Gabor convolution, edge feature enhancement

程照雪, 李阳, 周妍, 鲁慧民. 增强边缘特征的肺结节分割模型[J]. 计算机工程与应用, 2023, 59(24): 185-195.

CHENG Zhaoxue, LI Yang, ZHOU Yan, LU Huimin. Lung Nodule Segmentation Model with Enhanced Edge Features[J]. Computer Engineering and Applications, 2023, 59(24): 185-195.

参考文献

[1] SIEGEL R L，MILLER K D，JEMAL A.Cancer statistics，2019[J].CA：A Cancer Journal for Clinicians，2019，69（1）：7-34.
[2] MILLER K D，NOGUEIRA L，MARIOTTO A B，et al.Cancer treatment and survivorship statistics，2019[J].CA：A Cancer Journal for Clinicians，2019，69（5）：363-385.
[3] 王婧璇，林岚，赵思远，等.基于深度学习的肺结节计算机断层扫描影像检测与分类的研究进展[J].生物医学工程学杂志，2019，36（4）：670-676.
WANG J X，LIN L，ZHAO S Y，et al.Research progress on computed tomography image detection and classification of pulmonary nodule based on deep learning[J].Journal of Biomedical Engineering，2019，36（4）：670-676.
[4] 巨娟，林檬，曾祥飞，等.基于CT影像智能分析诊断早期肺癌的最新研究进展[J].中国胸心血管外科临床杂志，2021，28（3）：354-357.
JU J，LIN M，ZENG X F，et al.The latest research progress on early diagnosis of lung cancer according to CT-based computer intelligent analysis[J].Chinese Journal of Clinical Thoracic and Cardiovascular Surgery，2021，28（3）：354-357.
[5] WANG K，ZHANG X B，ZHANG X H，et al.Multi-granularity scale-aware networks for hard pixels segmentation of pulmonary nodules[J].Biomedical Signal Processing and Control，2021，69：102890.
[6] 钟思华，王梦璐，郭兴明，等.基于改进VNet的肺结节分割方法研究[J].仪器仪表学报，2020，41（9）：206-215.
ZHONG S H，WANG M L，GUO X M，et al.Study on the improved VNet network based pulmonary nodule segmentation method[J].Chinese Journal of Scientific Instrument，2020，41（9）：206-215.
[7] LONG J，SHELHAMER E，DARRELL T.Fully convolutional networks for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2015：3431-3440.
[8] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham：Springer，2015：234-241.
[9] 钟思华，郭兴明，郑伊能.改进U-Net网络的肺结节分割方法[J].计算机工程与应用，2020，56（17）：203-209.
ZHONG S H，GUO X M，ZHENG Y N.Improved U-Net network for lung nodule segmentation[J].Computer Engineering and Applications，2020，56（17）：203-209.
[10] KEETHA N V，ANNAVARAPU C S R.U-Det：a modified U-Net architecture with bidirectional feature network for lung nodule segmentation[J].arXiv：2003.09293，2020.
[11] OKTAY O，SCHLEMPER J，FOLGOC L L，et al.Attention U-Net：learning where to look for the pancreas[J].arXiv：1804.03999，2018.
[12] 张淑军，彭中，李辉.SAU-Net：基于U-Net和自注意力机制的医学图像分割方法[J].电子学报，2022，50（10）：2433-2442.
ZHANG S J，PENG Z，LI H.SAU-Net：medical image segmentation method based on U-Net and self-attention[J].Acta Electronica Sinica，2022，50（10）：2433-2442.
[13] ZHOU Z W，SIDDIQUEE M M R，TAJBAKHSH N，et al.A nested U-Net architecture for medical image segmentation[C]//Proceedings of Deep Learning in Medical Image Analysis，2018：3-11.
[14] 黄鸿，吕容飞，陶俊利，等.基于改进U-Net++的CT影像肺结节分割算法[J].光子学报，2021，50（2）：73-83.
HUANG H，LV R F，TAO J L，et al.Segmentation of lung nodules in CT images improved U-Net++[J].Acta Photonica Sinica，2021，50（2）：73-83.
[15] HUANG H M，LIN L F，TONG R F，et al.Unet 3+：a full-scale connected unet for medical image segmentation[C]//IEEE International Conference on Acoustics，Speech and Signal Processing，2020：1055-1059.
[16] 魏祥坡，余旭初，谭熊，等.CNN和三维Gabor滤波器的高光谱图像分类[J].计算机辅助设计与图形学学报，2020，32（1）：90-98.
WEI X P，YU X C，TAN X，et al.Convolutional neural networks and 3D Gabor filtering for hyperspectral image classification[J].Journal of Computer-Aided Design & Computer Graphics，2020，32（1）：90-98.
[17] LUAN S Z，CHEN C，ZHANG B C，et al.Gabor convolutional networks[J].IEEE Transactions on Image Processing，2018，27（9）：4357-4366.
[18] 王振宇，王颖珊，毛瑾玲，等.基于Dense-UNet++的关节滑膜磁共振图像分割[J].波谱学杂志，2022，39（2）：208-219.
WANG Z Y，WANG Y S，MAO J L，et al.Magnetic resonance images segmentation of synovium based on Dense-UNet++[J].Chinese Journal of Magnetic Resonance，2022，39（2）：208-219.
[19] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[20] 林岚，吴玉超，宋爽，等.LIDC/IDRI影像数据库在肺结节计算机辅助诊断中的研究进展[J].医疗卫生装备，2018，39（10）：95-99.
LIN L，WU Y C，SONG S，et al.Lung image database consortium and image database resource initiative：reviewing progresses toward improved computer-aided diagnosis of pulmonary nodule[J].Chinese Medical Equipment Journal，2018，39（10）：95-99.
[21] PEDROSA J，ARESTA G，FERREIRA C，et al.LNDb challenge on automatic lung cancer patient management[J].Medical Image Analysis，2021，70（1）：102027.
[22] 闫欢兰，陆慧娟，叶敏超，等.结合Sobel算子和Mask R-CNN的肺结节分割[J].小型微型计算机系统，2020，41（1）：161-165.
YAN H L，LU H J，YE M C，et al.Lung nodule segmentation combining Sobel operator and Mask R-CNN[J].Journal of Chinese Computer Systems，2020，41（1）：161-165.
[23] SAEID A T，KUMAR A，JOSEPH P C，et al.Deep semantic segmentation of natural and medical images：a review[J].Artificial Intelligence Review，2020，54.
[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.