计算机科学 ›› 2015, Vol. 42 ›› Issue (Z11): 126-130.

• 模式识别与图像处理 • 上一篇    下一篇

基于TI-RADS的甲状腺结节超声图像特征提取技术研究

韩晓涛,杨燕,彭博,陈琴   

  1. 西南交通大学信息科学与技术学院 成都610031,西南交通大学信息科学与技术学院 成都610031,西南交通大学信息科学与技术学院 成都610031,西南交通大学信息科学与技术学院 成都610031
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受四川省科技支撑计划项目(2014SZ0207)资助

Thyroid Nodule Ultrasound Image Feature Extraction Technique Based on TI-RADS

HAN Xiao-tao, YANG Yan, PENG Bo and CHEN Qin   

  • Online:2018-11-14 Published:2018-11-14

摘要: 超声是甲状腺检查的首选影像学方法。甲状腺超声影像的临床分析主要通过医生参考甲状腺影像报告和数据系统(TI-RADS)对超声图像进行特征评价量化, 但特征量化结果与医生的经验、状态等主观因素相关。通过计算机辅助分析方法,可客观定量地分析超声影像特征,减少主观因素对诊断结果的影响。但已有系统多是使用经典的图像纹理特征,这类特征抽象且缺乏明确意义,难以在临床运用。通过对TI-RADS中涉及到的超声征象进行提取并量化, 利用医生在临床诊断中依据经验所使用的视觉特征,设计对应的量化方法,可为甲状腺超声的标准化描述提供基础。根据这些特征,通过统计学习方法建立甲状腺结节良恶性鉴别模型,为临床诊断提供参考建议,该模型的识别正确率达到了100%。

关键词: 图像识别,TI-RADS,特征提取,甲状腺超声图像

Abstract: Ultrasound is the first choice of imaging modality for thyroid examination.Clinical analysis of thyroid ultrasonography is based on quantitatively evaluating the ultrasound image features in the thyroid imaging reporting and data system(TI-RADS).However,the results of quantified features are influenced by doctors’ experience level,status and other related factors.Computer-aided analysis can objectively analyze ultrasound imaging features and reduce the influence of subjective factors on the diagnostic results.But most of the existing systems are based on classic image texture features,which are abstract and absence of explicit meaning,so they are difficult in clinical using.Sonographic features of thyroid nodules which are involved in TI-RADS were extracted and quantified.Based on doctors’ clinical experience,the visual characteristics of the corresponding quantization methods were designed,which provide a basis of standardized description of thyroid ultrasound images.Statistical learning methods were adopted to establish a model of identifying the benign and the malignant thyroid nodules based on these characteristics,which provides reference recommendations for clinical diagnosis.The recognition accuracy of the model reaches 100%.

Key words: Image recognition,TI-RADS,Feature extraction,Thyroid ultrasound image

[1] Horvath E,Majlis S,Rossi R,et al.An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management[J].J Clin Endocrinol Metab,2009,94(5):1748-1751
[2] Park J Y,Lee H J,Jang H W,et al.A proposal for a thyroid ima-ging reporting and data system for ultrasound features of thyroid carcinoma[J].Thyroid,2009,19(11):1257-1264
[3] Hirning T,Zuna I,Schlaps D.Quantification and classification of echographic findings the thyroid gland by computerized b-mode texture analysis[J].Eur J Radiol,1989,9(4):244-247
[4] Skouroliakou C,Lyra M,Antoniou A,et al.Quantitative image analysis in sonograms of the thyroid.gland[J].Nuclear Instruments and Methods in Physics,2006,569:606-609
[5] Savelonas M A,Iakovidis D K,Dimitropoulos N,et al.Computational Characterization of ThyroidTissue in the Radon Domain[C]∥Proc.IEEE Internationa Symposium on Computer-Based Medical Systems.Slovenia,2007:189-192
[6] Keramidas E G,Iakovidis D,Maroulis D,et al.Efficient and Effective Ultrasound Image Analysis Scheme for Thyroid Nodule Detection[J]Lecture Notes in Computer Science,2007,4633:1052-1060
[7] Keramidas E G,Iakovidis D K,Maroulis D,et al.Thyroid texture representation via noise resistant image features [C]∥ 21st IEEE International Symposium on Computer-Based Medical Systems,2008(CBMS’08).IEEE,2008:560-565
[8] Ding Jian-rui.Based on multi-instance learning of superficial organ ultrasound image classification[D].Harbin Institute of Technology,2012
[9] Chang C Y,Tsai M F,Chen S J.Classification of the thyroid nodules using support vector machines[C]∥IEEE International Joint Conference on Neural Networks,2008(IJCNN 2008).IEEE,2008:3093-3098
[10] Chang C Y,Liu H Y,Tseng C H,et al.Automatic Diagnosis of Thyroid Graves’ Disease in Ultrasound Images[C]∥ Ninth International Conference on Hybrid Intelligent Systems,2009(HIS’09).IEEE,2009,1:192-197
[11] Selvathi D,Sharnitha V S.Thyroid classification and segmentation in ultrasound images using machine learning algorithms[C]∥2011 International Conference on Signal Processing,Communication,Computing and Networking Technologies(ICSCCN).IEEE,2011:836-841
[12] Yang Wei.Neoplasms of ultrasonographic features of benign and malignant identification and quantitative analysis [D].Shanghai Jiaotong University,2009
[13] Zhan Wei-wei,Xu Shang-yan.Ultrasonography Progress on thyroid nodules [J].Journal of Medical Ultrasound(Electronic Edition),2013(2):1672-6448
[14] Ma Bu-yun,Parajuly Shyam Sundar,et al.thyroid Imaging Reporting and Data System in ultrasound examination of thyroid nodules[J].Chinese Journal of Bases and Clinics in General Surgery,2011,18(8):898-901
[15] Savelonas M A,Maroulis D E,Iakovidis D K,et al.Computer-Aided Malignancy Risk Assessment of Nodules in Thyroid US Images Utilizing Boundary Descriptors[J].Panhellenic Confe-rence on Informatics,2008:157-160
[16] Guan Qing,Zhang Wei.Image Edge Detection Based on Fractal Dimension[J].Computer Scinece,2015,2(6):296-298
[17] Ito,Chono M,Sekiguchi T,et al.Quantitative evaluation of diagnostic information around the contours in ultrasound images[J].Med.Ultrasonics,2005,32:135-144
[18] Garg H,Jindal A.Segmentation of thyroid gland in ultrasound image using neural network[C]∥2013 Fourth International Conference on Computing,Communications and Networking Technologies(ICCCNT).IEEE,2013:1-5

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!