面向病灶与其表征关联提取的核医学诊断文本挖掘

doi:10.11896/jsjkx.200400062

计算机科学 ›› 2020, Vol. 47 ›› Issue (11A): 524-530.doi: 10.11896/jsjkx.200400062

面向病灶与其表征关联提取的核医学诊断文本挖掘

韩成成^1,2, 林强^1,2, 满正行^1,2, 曹永春^1,2, 王海军³, 王维兰⁴

1 西北民族大学数学与计算机科学学院兰州 730030
2 西北民族大学动态流数据计算与应用实验室兰州 730012
3 甘肃省人民医院核医学科兰州 730020
4 西北民族大学国家教育部民族语言和信息技术重点实验室兰州 730030

出版日期:2020-11-15 发布日期:2020-11-17
通讯作者: 林强(qiang.lin2010@hotmail.com)
作者简介:2307115582@qq.com
基金资助:
西北民族大学中央高校基本科研业务费专项资金资助研究生项目(Yxm2020101);国家自然科学基金项目(61562075);西北民族大学甘肃省一流学科引导专项资金(11080305);国家民委创新团队计划([2018]98)

Mining Nuclear Medicine Diagnosis Text for Correlation Extraction Between Lesions and Their Representations

HAN Cheng-cheng^1,2, LIN Qiang^1,2, MAN Zheng-xing^1,2, CAO Yong-chun^1,2, WANG Hai-jun³, WANG Wei-lan⁴

1 School of Mathematics and Computer Science,Northwest Minzu University,Lanzhou 730030,China
2 Key Laboratory of Streaming Data Computing Technologies and Application,Northwest Minzu University,Lanzhou 730012,China
3 Department of Nuclear Medicine,Gansu Provincial Hospital,Lanzhou 730020,China
4 Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education,Northwest Minzu University,Lanzhou 730030,China

Online:2020-11-15 Published:2020-11-17
About author:HAN Cheng-cheng,born in 1994,postgraduate,is a member of China Computer Federation.Her main research interests include data mining and intelligent information processing.
LIN Qiang,born in 1979,Ph.D,asso-ciate professor,master's supervisor,is a member of China Computer Federation.His main research interests include medical image computing,data stream mining,pervasive computing and intelligent information processing.
Supported by:
This work was supported by the Northwest Minzu University for Central University Basic Scientific Research Operating Expenses Special Fund to Support the Graduate Program (Yxm2020101),National Natural Science Foundation of China (61562075),Gansu Provincial First-class Discipline Program of Northwest Minzu University (11080305) and Program for Innovative Research Team of SEAC ([2018] 98).

摘要/Abstract

摘要： 医学影像是现代临床医学疾病诊治不可或缺的重要组成部分,SPECT是功能影像的主要成像技术,广泛应用于肿瘤骨转移等疾病的诊治。SPECT诊断报告文本包含患者个人信息、图像描述和建议性结果等几个方面的信息。为准确提取SPECT核医学骨显像诊断文本中疾病与其表征之间的关联关系,研究并提出基于数据挖掘的核医学文本关联规则挖掘方法。首先,针对核医学诊断文本可能包含的信息冗余、数据缺失及表述不一致等问题,提出SPECT核医学诊断文本的预处理及统一编码方法;然后,应用经典的关联规则挖掘算法Apriori,提出病灶与表征之间关联的挖掘算法;最后,使用一组源自三甲医院核医学科的真实SPECT核医学诊断文本数据,验证了所提出的方法。结果表明,提出的方法客观提取了疾病与其表征之间的关联,获得的客观性评价指标平均值不低于90%。

关键词: SPECT核医学, 关系规则提取, 文本挖掘, 医学影像, 诊断文本

Abstract: Medical imaging is an indispensable part of the diagnosis and treatment of diseases in modern clinical medicine.SPECT is the main functional imaging technology and has been widely used in the diagnosis and treatment of diseases such as tumor bone metastasis.The SPECT diagnostic text contains several aspects of patients' personal information,image description,and suggested results.In order to accurately extract the association between disease and its representation in the diagnostic text of SPECT nuclear medicine bone imaging,a method of mining association rules of nuclear medicine text based on data mining is proposed.Firstly,a method of SPECT medical diagnostic text preprocessing and uniform coding is proposed to solve the problems of information redundancy,data loss and inconsistent expression.Secondly,the classical association rule mining algorithm Apriori is applied to propose the association mining algorithm between lesions and their representations.Finally,the proposed method is validated with a set of real-world SPECT nuclear medical diagnostic text data from the department of nuclear medicine in a 3a grade hospitals,and the results show that the proposed method is able to objectively extracted the association between the disease and its representation,and the average objectivity is more than 90%.

Key words: Diagnostic text, Extraction of association rules, Medical imaging, SPECT nuclear medicine, Text mining

中图分类号:

TP391

韩成成, 林强, 满正行, 曹永春, 王海军, 王维兰. 面向病灶与其表征关联提取的核医学诊断文本挖掘[J]. 计算机科学, 2020, 47(11A): 524-530. https://doi.org/10.11896/jsjkx.200400062

HAN Cheng-cheng, LIN Qiang, MAN Zheng-xing, CAO Yong-chun, WANG Hai-jun, WANG Wei-lan. Mining Nuclear Medicine Diagnosis Text for Correlation Extraction Between Lesions and Their Representations[J]. Computer Science, 2020, 47(11A): 524-530. https://doi.org/10.11896/jsjkx.200400062

参考文献

[1] VASSILIOU V,ANDREOPOULOS D,FRANGOS S,et al.Bone metastases:assessment of therapeutic response through radiological and nuclear medicine imaging modalities[J].Clinical Oncology (Royal College of Radiologists),2011,23(9):632-645.
[2] ABIKHZER G,GOUREVICH K,KAGNA O,et al.Whole-body bone SPECT in breast cancer patients:the future bone scan protocol[J].Nuclear Medicine Communications,2016,37(3):247-253.
[3] REÁTEGUI R,RATTÉ S.Analysis of Medical Documents with Text Mining and Association Rule Mining[C]//International Conference on Information Technology and Systems.Springer,Cham,2019,1:744-753.
[4] COHEN A M,HERSH W R.A survey of current work in biomedical text mining[J].Briefings in Bioinformatics,2005,6(1):57-71.
[5] WANG H C,ZHAO T J.Research and development of biomedical text mining technology[J].Chinese Journal of Information,2008,22(3):89-98.
[6] MINER G,ELDER IV J,FAST A,et al.Practical text mining and statistical analysis for non-structured text data applications[M].Boston:Academic Press,2012.
[7] WEISS S M,INDURKHYA N,ZHANG T,et al.Text mining:predictive methods for analyzing unstructured information[M].Berlin:Springer Science & Business Media,2010.
[8] CAMPBELL E A,BASS E J,MASINO A J.Temporal condition pattern mining in large,sparse electronic health record data:A case study in characterizing pediatric asthma[J].Journal of the American Medical Informatics Association,2020,27(4):558-566.
[9] MCCOY T H J,HAN L,PELLEGRINI A M,et al.Stratifying risk for dementia onset using large-scale electronic health record data:A retrospective cohort study[J].Alzheimer's and Dementia:the Journal of the Alzheimer's Association,2020,16(3):531-540.
[10] YU P,JIANG T,HAILEY D,et al.The contribution of electronic health records to risk management through accreditation of residential aged care homes in Australia[J].BMC Medical Informatics and Decision Making,2020,20(1):58.
[11] GROENHOF T K J,KOERS L R,BLASSE E,et al.Data mining information from electronic health records produced high yield and accuracy for current smoking status[J].Journal of Clinical Epidemiology,2020,118:100-106.
[12] RISHI V P,THIDA C T,SUE H S,et al.Can Natural Language Processing Improve the Accuracy of Identifying Acute Heart Failure in Electronic Health Records[J].Circulation,2018,138(138):16034.
[13] LIANG Z H,LIU J,OU A H,et al.Deep generative learning for automated EHR diagnosis of traditional Chinese medicine[J].Computer Methods and Programs in Biomedicine,2019,174:17-23.
[14] ZHANG K,WANG W T,XIE Y Q.Research progress of electronic health in China [J].Library Forum,2018,38(8):84-92.
[15] LEI Z Q,SHI H S,LIANG B,et al.Imaging detection and infection prevention and control of novel coronavirus (2019-nCoV) pneumonia [J].Journal of Clinical Radiology,2020,39(1):12-16.
[16] LIU J W.Application of computed tomography in diagnosis of mycoplasma pneumoniae pneumonia in children [J].Chinese Convalesce Medicine,2019,28(3):280-282.
[17] WENG T W,MAO D B,JIN J,et al.Computed tomography (ct) scan media stored blood flow to the score research progress [J].Journal of Geriatric Medicine and Health Care,2019,5:685-688.
[18] FEI Z H,PAN H P,LUO Z Q,et al.Clinical characteristics and magnetic resonance imaging of invasive fungal infection in neonates [J].Journal of Chinese Hospital Infectious Diseases,2019,19:161-165.
[19] ZHU H W.Effect observation of mri in diagnosis of knee joint injury [J].Imaging Research and Medical Application,2019,3(15):167-168.
[20] ZHAO N N.Comparison of ct and mri in pediatric liver tumors [J].Tumor Foundation and Clinical,2019,6:540-541.
[21] NIU Y Y,WANG Y M,CHEN N .Clinical application of nu-clear magnetic resonance combined ultrasound in fetal central ner-vous system malformation [J].Contemporary Medicine,2020,9(26):90-92.

相关文章 15

[1]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[2]	白勇, 张占龙, 熊隽迪. 基于FP-Growth算法和GRNN的电力知识文本挖掘 Power Knowledge Text Mining Based on FP-Growth Algorithm and GRNN 计算机科学, 2021, 48(8): 86-90. https://doi.org/10.11896/jsjkx.210600031
[3]	徐少伟, 秦品乐, 曾建朝, 赵致楷, 高媛, 王丽芳. 基于多级特征和全局上下文的纵膈淋巴结分割算法 Mediastinal Lymph Node Segmentation Algorithm Based on Multi-level Features and Global Context 计算机科学, 2021, 48(6A): 95-100. https://doi.org/10.11896/jsjkx.200700067
[4]	张同明, 张宁. 股票市场投资者情绪指数研究综述 Review of Research on Investor Sentiment Index in Stock Market 计算机科学, 2021, 48(6A): 143-150. https://doi.org/10.11896/jsjkx.201000016
[5]	朱涤尘, 夏换, 杨秀璋, 于小民, 张亚成, 武帅. 基于文本挖掘和决策树分析的中国手游产业发展研究 Research on Mobile Game Industry Development in China Based on Text Mining and Decision Tree Analysis 计算机科学, 2020, 47(6A): 530-534. https://doi.org/10.11896/JsJkx.190700124
[6]	高楠,李利娟,李伟,祝建明. 融合语义特征的关键词提取方法 Keywords Extraction Method Based on Semantic Feature Fusion 计算机科学, 2020, 47(3): 110-115. https://doi.org/10.11896/jsjkx.190700041
[7]	邱先标, 陈笑蓉. 一种基于SA_LDA模型的文本相似度计算方法 Text Similarity Calculation Algorithm Based on SA_LDA Model 计算机科学, 2018, 45(6A): 106-109.
[8]	许卓斌, 郑海山, 潘竹虹. 基于改进自编码器的文本分类算法 Improved Autoencoder Based Classification Algorithm for Text 计算机科学, 2018, 45(6): 208-210. https://doi.org/10.11896/j.issn.1002-137X.2018.06.037
[9]	张巧丽,赵地,迟学斌. 基于深度学习的医学影像诊断综述 Review for Deep Learning Based on Medical Imaging Diagnosis 计算机科学, 2017, 44(Z11): 1-7. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.001
[10]	董苑,钱丽萍. 基于语义词典和词频信息的文本相似度计算 Text Similarity Calculation Based on Semantic Dictionary and Word Frequency Information 计算机科学, 2017, 44(Z11): 422-427. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.090
[11]	朱卫星,徐伟光,何红悦,李雯. 文本数据主题挖掘与关联搜索研究 Research on Text Data Topic Mining and Association Search 计算机科学, 2017, 44(Z11): 411-413. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.087
[12]	汪东升,黄传河,黄晓鹏,倪秋芬. 电信大数据文本挖掘算法及应用 Text Mining Algorithm and Application of Telecom Big Data 计算机科学, 2017, 44(12): 232-238. https://doi.org/10.11896/j.issn.1002-137X.2017.12.042
[13]	池云仙,赵书良,罗燕,高琳,赵骏鹏,李超. 基于词频统计规律的文本数据预处理方法 Text Data Preprocessing Based on Term Frequency Statistics Rules 计算机科学, 2017, 44(10): 276-282. https://doi.org/10.11896/j.issn.1002-137X.2017.10.050
[14]	林涛,高建华,伏雪,马燕,林艳. 面向软件缺陷报告的提取方法 Extraction Approach for Software Bug Report 计算机科学, 2016, 43(6): 179-183. https://doi.org/10.11896/j.issn.1002-137X.2016.06.036
[15]	温浩,温有奎,王民. 基于模式识别的文本知识点深度挖掘方法 Approach to Text Knowledge Depth Mining Based on Pattern Recognition 计算机科学, 2016, 43(3): 279-284. https://doi.org/10.11896/j.issn.1002-137X.2016.03.052

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

面向病灶与其表征关联提取的核医学诊断文本挖掘

Mining Nuclear Medicine Diagnosis Text for Correlation Extraction Between Lesions and Their Representations

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0