针对肝包膜特征图的自动化提取方法

doi:10.16180/j.cnki.issn1007-7820.2022.10.007

摘要/Abstract

摘要：

为了自动化提取肝包膜及其上下组织特征图,实现全自动特征学习,文中提出采用频域处理与图像形态学处理的方法对图像进行预处理,并借鉴移动平均法提出二路交叉感受野策略,由感受野映射区域进行特征筛选与分析。通过对数能量函数识别并定位目标区块,从而实现对肝实质病变特征、肝包膜、肌肉脂肪层纹理特征数据提取与分析,并根据数据分析获取肝包膜及其上下组织特征图。根据特征区域的相对位置,提出区块纠错机制对误检区块进行校正,使其更具鲁棒性。实验结果表明,在对肝硬化超声图像中的肝包膜及其上下组织特征图的提取过程中,该提取机制在正常、轻度、中度阶段特征提取均达到100%的准确率,对于重度病情阶段的特征提取准确率达到84.6%。

关键词: 高频超声图像, 肝硬化, 傅里叶变换, 肝包膜, 二路交叉感受野, 对数能量收益函数, 移动平均法, 纠错机制

Abstract:

In order to automatically extract the feature maps of the liver capsule and its upper and lower tissues, and realize automatic feature learning, the study proposes to use frequency domain processing and image morphology processing to preprocess the image, and proposes a two-way cross receptive field strategy based on the moving average method, and feature screening and analysis are carried out through the receptive field mapping area. The logarithmic energy function is used to identify and locate the target block, so as to realize the extraction and analysis of the liver parenchymal lesion features, liver capsule, muscle fat layer texture feature data, and obtain the liver capsule and its upper and lower tissue feature maps according to the data analysis. Based on the relative positions of the proposed feature regions, a block correction mechanism is proposed to correct the mischecked blocks to make them more robust. The experiments show that during the extraction of the liver envelope and its upper and lower tissue feature maps in the ultrasound images of cirrhosis, the present extraction mechanism achieves 100% accuracy in the normal, mild and moderate stages of feature extraction, and 84.6% accuracy is achieved in the severe disease stage.

Key words: high-frequency ultrasound images, cirrhosis, Fourier transform, liver capsule, two-way cross-receptor field, logarithmic energy gain function, moving average method, error correction mechanism

中图分类号:

TN911.73

牛广利,刘翔,宋家琳,汤显. 针对肝包膜特征图的自动化提取方法[J]. 电子科技, 2022, 35(10): 39-44.

NIU Guangli,LIU Xiang,SONG Jialin,TANG Xian. Automated Extraction Method for Liver Capsule Feature Maps[J]. Electronic Science and Technology, 2022, 35(10): 39-44.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

参考文献 18

[1]	翟岳仙, 刘翔, 宋家琳, 等. 基于超声的计算机辅助诊断肝纤维化研究进展[J]. 中国医学影像技术, 2019, 35(7):1107-1110.
	Zhai Yuexian, Liu Xiang, Song Jialin, et al. Research progress of ultrasound-based computer-aided diagnosis of liver fibrosis[J]. Chinese Journal of Medical Imaging Technology, 2019, 35(7):1107-1110.
[2]	刘士远, 萧毅. 基于深度学习的人工智能对医学影像学的挑战和机遇[J]. 中华放射学杂志, 2017, 51(12):899-901.
	Liu Shiyuan, Xiao Yi. Challenges and opportunities of deep learning-based artificial intelligence for medical imaging[J]. Chinese Journal of Radiology, 2017, 51(12):899-901.
[3]	Litjens G, Kooi T, Bejnordi B E, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis, 2017, 42(1):60-88. doi: 10.1016/j.media.2017.07.005
[4]	Setio A A, Ciompi F, Litjens G J, et al. Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1160-1169. doi: 10.1109/TMI.2016.2536809 pmid: 26955024
[5]	Havaei M, Davy A, Wardefarley D, et al. Brain tumor segmentation with deep neural networks[J]. Medical Image Analysis, 2017, 35(1):18-31. doi: 10.1016/j.media.2016.05.004
[6]	周榴, 董怡, 夏威, 等. 基于超声影像组学的原发性肝细胞癌分级预测[J]. 中国医学物理学杂志, 2020, 37(1):59-64.
	Zhou Liu, Dong Yi, Xia Wei, et al. Prediction of grade of hepatocellular carcinoma by radiomics based on ultrasound[J]. Chinese Journal of Medical Physics, 2020, 37(1):59-64.
[7]	吴秀明, 王霞丽, 吕国荣, 等. 计算机辅助系统在诊断乳腺良恶性肿瘤中的应用[J]. 中国医学物理学杂志, 2020, 37(3):374-378.
	Wu Xiuming, Wang Xiali, Lü Guorong, et al. Application of computer-aided detection in ultrasound diagnosis of benign and malignant breast tumors[J]. Chinese Journal of Medical Physics, 2020, 37(3):374-378.
[8]	Criminisi A. Machine learning for medical images analysis[J]. Medical Image Analysis, 2016, 33(1):91-93. doi: 10.1016/j.media.2016.06.002
[9]	Liu X, Song J L, Zhao J W, et al. Extracting and describing liver capsule contour in high-frequency ultrasound image for early HBV cirrhosis diagnosis[C]. Seattle: Proceedings of the IEEE International Conference on Multimedia & Expo, 2016.
[10]	Wang S H, Liu X, Zhao J, et al. Learning to diagnose cirrhosis via combined liver capsule and parenchyma ultrasound image features[C]. Shenzhen: Proceedings of the IEEE International Conference on Bioinformatics & Biomedicine, 2017.
[11]	Liu X, Song J L, Wang S H, et al. Learning to diagnose cirrhosis with liver capsule guided ultrasound image classification[J]. Sensors, 2017, 17(12):149-160. doi: 10.3390/s17010149
[12]	Zhao J, Wang S H, Liu X, et al. Early diagnosis of cirrhosis via automatic location and geometric description of liver capsule[J]. Visual Computer, 2017, 34(1):1677-1689. doi: 10.1007/s00371-017-1441-2
[13]	伏广霞, 刘翔, 宋家琳, 等. 一种基于高频超声图像的肝包膜提取算法研究[J]. 电子科技, 2019, 32(11):33-37.
	Fu Guangxia, Liu Xinag, Song Jialin, et al. A liver capsule extraction algorithm based on high frequency ultrasound images[J]. Electronic Science and Technology, 2019, 32(11):33-37.
[14]	徐齐利. 一种优选移动平均预测模型的Min-Min算法[J]. 计算机应用研究, 2021, 38(6):1744-1747.
	Xu Qili. Min-Min algorithm for optimizing moving average prediction model[J]. Application Research of Computers, 2021, 38(6):1744-1747.
[15]	董田田, 董学士, 张睿, 等. 基于指数加权移动平均法的企业销量预测[J]. 青岛大学学报(自然科学版), 2020, 33(4):50-54.
	Dong Tiantian, Dong Xueshi, Zhang Rui, et al. Enterprise sales forecast based on exponentially weighted moving average method[J]. Journal of Qingdao University (Natural Science Edition), 2020, 33(4):50-54.
[16]	许阳婷. 三种预测模型对南京市水痘发病预测的应用与比较[J]. 华南预防医学, 2021, 47(1):10-14.
	Xu Yangting. Application and comparison of three prediction models for predicting varicella incidence in Nanjing[J]. South China Journal of Preventive Medicine, 2021, 47(1):10-14.
[17]	王彦梅. 基于移动平均法的汽车4S店新车销售需求预测分析[J]. 中国商论, 2019(18):58-59.
	Wang Yanmei. Analysis of new car sales demand forecasting for auto 4S stores based on moving average method[J]. China Journal of Commerce, 2019(18):58-59.
[18]	孟繁坤, 丁蕾, 曲锰, 等. 高频超声观察肝实质形态的改变对慢性肝病肝纤维化分期的价值[J]. 中国医学影像技术, 2006, 22(6):916-918.
	Meng Fankun, Ding Lei, Qu Meng, et al. The value of high-frequency ultrasound for the staging of liver fibrosis in chronic liver disease with morphological changes in liver parenchyma[J]. Chinese Journal of Medical Imaging Technology, 2006, 22(6):916-918.

组别	样本总数	提取正确数	提取正确率	平均准确率
正常组	20	20	100.00%	96.15%
轻度组	18	18	100.00%
中度组	17	17	100.00%
重度组	13	11	84.60%