放射科随访数据库建立与粗糙集方法辅助诊断胶质瘤分级的应用分析
|
摘要
目的：(1)建立放射科随访数据库,数据库中随访记录的诊断报告予以标准化,使其满足科研及CAD数据挖掘的要求；(2)比较粗糙集、分类回归树及二元Logistic回归法等三种方法依据常规MRI影像特点提取的诊断规则辅助分级诊断胶质瘤的性能,探讨粗糙集方法辅助影像诊断的价值。
材料和方法：(1)利用sql server 2000数据库分别建立ACR编码库及ICD-10编码库对数据库中随访病例的诊断进行编码,实现诊断的标准化。ACR编码库包括解剖表和病理表,表中对每个解剖部位及病理诊断使用数字进行编码,其中解剖编码最长为4位,病理最长为6位；ICD-10编码库包括分类表和诊断编码表,每个表中分类或者诊断用字母+数字进行编码。(2)数据库中建立中枢神经系统肿瘤影像诊断模板,包括病变部位、病灶范围、大小、形态、边缘、水肿、占位效应、出血、钙化、坏死、脑积水、CT密度、MRI信号(包括T1WI、T2WI及Flair)及增强特点(包括常规增强、动脉期强化、静脉期强化、延迟期强化)等共19项中枢神经系统肿瘤常规CT/MRI的影像特征,并建立每项影像特征的标准化选项,用于中枢神经系统肿瘤诊断报告的标准化；(3)利用sql server 2000建立放射科随访数据库数据表存储随访记录,包括随访病例的临床资料(姓名、性别、年龄、病史、手术记录等)、病理资料(病理诊断、病理报告、病理图像)、影像资料(影像检查项目、影像报告、报告医生、核片医生、诊断符合、影像图片及影像相关特征等资料),其中文本部分的记录储存在数据表中,病理及影像图像储存在本地硬盘,通过SQL server 2000建立图像索引与数据记录相关联；(4)使用Visual C++开发数据库客户端程序,实现人机对话式的随访信息维护、记录查询、病种统计、诊断符合率统计、数据导入／导出、ACR编码及ICD-10编码修改及用户权限设置等操作功能；(5)275例确诊胶质瘤病例(低级别胶质瘤151例,高级别胶质瘤124例),术前常规MRI平扫及增强检查,提取包括病灶数目、形态、边缘、水肿、坏死、占位效应、钙化、出血、T1WI、T2WI及增强特点等MRI征象,粗糙集基于Rosetta软件使用遗传算法进行属性约简并产生诊断规则,分类回归树使用CRT算法建立预测胶质瘤分级诊断模型,回归法使用二元Logistic回归法建立回归方程。结果：(1)随访数据库实现设计的各项功能,运行稳定；并且诊断标准化的使用提高了数据检索的精确性；(2)粗糙集、决策树及回归法的诊断准确性分别为84.4%、83.3%、83.6%：敏感度分别为75%、74.2%、79.8%；特异度分别为92.1%、91.3%、86.8%,三种方法的ROC曲线下面积分别为0.92、0.907和0.902, ROC曲线下面积之间无明显差异性。相比其他两种方法,粗糙集可以得到更多确定性诊断规则。结论：(1)放射科随访数据库能够实现随访记录诊断报告的标准化管理,其标准化数据格式可以满足临床科研和数据挖掘的要求。(2)粗糙集具有与其他两种方法一样的诊断性能,但是粗糙集的诊断规则更加明确及清晰,具有更好的临床应用价值。
Objective:(1) Considering the radiological research and CAD, the records in follow-up database of radiology with standard radiological diagnosis and reports was established. (2) To study the value of Rough set principle in assistant radiological diagnosis by compared Rough set with Decision tree and two-binary-Logistic-Regression in the diagnosis of glioma grade based on routine MR examination.
Methods:(1)The ACR code library and ICD-10 library were used to standardized the diagnosis in radiological follow-up database which be build with SQL sever 2000.The ACR code library included anatomical table and pathological table in which the anatomy and pathology was encoded by number. The anatomical codes had 4 ranks and the pathological codes had 6 ranks at most.ICD-10 code library included class table and diagnosis table in which the classes and diagnosis were encoded with alphabet and number.(2)The diagnosis mould of CNS tumor was used to normalize the reports of CNS tumor which included the radiological features in CT and MRI like location, spread, size, shape, margin, edema, mass effect, hemorrhage, necrosis, calcification, hydrocephalus, CT density, MRI intensity (include T1WI, T2WI,Flair),enhancement style (Routine enhancement, enhancement in arterial phase, enhancement in venous phase, enhancement in delay phase). (3) The data tables was build in SQL server 2000 used to store the clinical data (include name, gender, age, history, operation record) and pathological data (pathological diagnosis and picture) and radiological data (include radiological examination method, primitive report, reporter, superior, diagnose accordance, radiological picture, radiological features) of follow-up records among which the pathological pictures and radiological picture were restored in local hardware and connected to the record by table of index.(4)The client program of man-computer interface was developed by using Visual C++ which used to carry out the functions to the database like follow-up record maintainm, inquiry records, statistics of the diagnose accordance rate and entity in database, records import or export, ACR and ICD-10 codes revision, users authoritative. (5)MR images of 275 patients with gliomas (151 low-grade gliomas,124 high-grade gliomas) examined before surgery were collected. The features of MRI with gliomas included numbers, shape, margin, edema, necrosis, mass effect, calcification, hemorrhage, intensity of T1WI and T2WI, enhancement style after administration of contrast agent. The attributes of glioma was reduced by genetic algorithm with software Rosetta and then the diagnostic rules about the grade diagnosis came from reduced attributes. The CR&T algorithm was used to build grade diagnostic model in decision tree. On the other hand the two-binary-Logistic-Regression constructed an equation to predict the grade of glioma.
Result:(1)The follow-up database implement the functions of data entry, data inquiry, statistic analysis, system management and data input/output. And the use of encode made the inquiry of data in the database more accurate. (2) The accuracy, sensitivity, Specificity and the averaged area under the ROC curve for Rough set, Decision tree and two binary Logistic Regression were 84.4%,75%,92.1%,0.92; 83.3%,74.2%,91.3%,0.907 and 83.6%,79.8%,86.8%,0.902 respectively. There were no significant differences among the AUC of ROCs of the three methods. Among all features, mass effect, edema and enhancement style were three important features in differentiate grade of glioma.
Conclusion:(1) The follow-up database made the management of information of follow-up more standard and its data can be used for clinical research and data mining more effectively. (2) All of three methods had good diagnostic performance. The importance of every feature in diagnostic model can get from decision tree and two-binary-Logistic-Regression. For the explicit and valuable and understandable rules, Rough set was more suitable for practice in diagnosis by experts. The Rough set should be study further to improve the accurate and cover rate of rules.
材料和方法：(1)利用sql server 2000数据库分别建立ACR编码库及ICD-10编码库对数据库中随访病例的诊断进行编码,实现诊断的标准化。ACR编码库包括解剖表和病理表,表中对每个解剖部位及病理诊断使用数字进行编码,其中解剖编码最长为4位,病理最长为6位；ICD-10编码库包括分类表和诊断编码表,每个表中分类或者诊断用字母+数字进行编码。(2)数据库中建立中枢神经系统肿瘤影像诊断模板,包括病变部位、病灶范围、大小、形态、边缘、水肿、占位效应、出血、钙化、坏死、脑积水、CT密度、MRI信号(包括T1WI、T2WI及Flair)及增强特点(包括常规增强、动脉期强化、静脉期强化、延迟期强化)等共19项中枢神经系统肿瘤常规CT/MRI的影像特征,并建立每项影像特征的标准化选项,用于中枢神经系统肿瘤诊断报告的标准化；(3)利用sql server 2000建立放射科随访数据库数据表存储随访记录,包括随访病例的临床资料(姓名、性别、年龄、病史、手术记录等)、病理资料(病理诊断、病理报告、病理图像)、影像资料(影像检查项目、影像报告、报告医生、核片医生、诊断符合、影像图片及影像相关特征等资料),其中文本部分的记录储存在数据表中,病理及影像图像储存在本地硬盘,通过SQL server 2000建立图像索引与数据记录相关联；(4)使用Visual C++开发数据库客户端程序,实现人机对话式的随访信息维护、记录查询、病种统计、诊断符合率统计、数据导入／导出、ACR编码及ICD-10编码修改及用户权限设置等操作功能；(5)275例确诊胶质瘤病例(低级别胶质瘤151例,高级别胶质瘤124例),术前常规MRI平扫及增强检查,提取包括病灶数目、形态、边缘、水肿、坏死、占位效应、钙化、出血、T1WI、T2WI及增强特点等MRI征象,粗糙集基于Rosetta软件使用遗传算法进行属性约简并产生诊断规则,分类回归树使用CRT算法建立预测胶质瘤分级诊断模型,回归法使用二元Logistic回归法建立回归方程。结果：(1)随访数据库实现设计的各项功能,运行稳定；并且诊断标准化的使用提高了数据检索的精确性；(2)粗糙集、决策树及回归法的诊断准确性分别为84.4%、83.3%、83.6%：敏感度分别为75%、74.2%、79.8%；特异度分别为92.1%、91.3%、86.8%,三种方法的ROC曲线下面积分别为0.92、0.907和0.902, ROC曲线下面积之间无明显差异性。相比其他两种方法,粗糙集可以得到更多确定性诊断规则。结论：(1)放射科随访数据库能够实现随访记录诊断报告的标准化管理,其标准化数据格式可以满足临床科研和数据挖掘的要求。(2)粗糙集具有与其他两种方法一样的诊断性能,但是粗糙集的诊断规则更加明确及清晰,具有更好的临床应用价值。
Objective:(1) Considering the radiological research and CAD, the records in follow-up database of radiology with standard radiological diagnosis and reports was established. (2) To study the value of Rough set principle in assistant radiological diagnosis by compared Rough set with Decision tree and two-binary-Logistic-Regression in the diagnosis of glioma grade based on routine MR examination.
Methods:(1)The ACR code library and ICD-10 library were used to standardized the diagnosis in radiological follow-up database which be build with SQL sever 2000.The ACR code library included anatomical table and pathological table in which the anatomy and pathology was encoded by number. The anatomical codes had 4 ranks and the pathological codes had 6 ranks at most.ICD-10 code library included class table and diagnosis table in which the classes and diagnosis were encoded with alphabet and number.(2)The diagnosis mould of CNS tumor was used to normalize the reports of CNS tumor which included the radiological features in CT and MRI like location, spread, size, shape, margin, edema, mass effect, hemorrhage, necrosis, calcification, hydrocephalus, CT density, MRI intensity (include T1WI, T2WI,Flair),enhancement style (Routine enhancement, enhancement in arterial phase, enhancement in venous phase, enhancement in delay phase). (3) The data tables was build in SQL server 2000 used to store the clinical data (include name, gender, age, history, operation record) and pathological data (pathological diagnosis and picture) and radiological data (include radiological examination method, primitive report, reporter, superior, diagnose accordance, radiological picture, radiological features) of follow-up records among which the pathological pictures and radiological picture were restored in local hardware and connected to the record by table of index.(4)The client program of man-computer interface was developed by using Visual C++ which used to carry out the functions to the database like follow-up record maintainm, inquiry records, statistics of the diagnose accordance rate and entity in database, records import or export, ACR and ICD-10 codes revision, users authoritative. (5)MR images of 275 patients with gliomas (151 low-grade gliomas,124 high-grade gliomas) examined before surgery were collected. The features of MRI with gliomas included numbers, shape, margin, edema, necrosis, mass effect, calcification, hemorrhage, intensity of T1WI and T2WI, enhancement style after administration of contrast agent. The attributes of glioma was reduced by genetic algorithm with software Rosetta and then the diagnostic rules about the grade diagnosis came from reduced attributes. The CR&T algorithm was used to build grade diagnostic model in decision tree. On the other hand the two-binary-Logistic-Regression constructed an equation to predict the grade of glioma.
Result:(1)The follow-up database implement the functions of data entry, data inquiry, statistic analysis, system management and data input/output. And the use of encode made the inquiry of data in the database more accurate. (2) The accuracy, sensitivity, Specificity and the averaged area under the ROC curve for Rough set, Decision tree and two binary Logistic Regression were 84.4%,75%,92.1%,0.92; 83.3%,74.2%,91.3%,0.907 and 83.6%,79.8%,86.8%,0.902 respectively. There were no significant differences among the AUC of ROCs of the three methods. Among all features, mass effect, edema and enhancement style were three important features in differentiate grade of glioma.
Conclusion:(1) The follow-up database made the management of information of follow-up more standard and its data can be used for clinical research and data mining more effectively. (2) All of three methods had good diagnostic performance. The importance of every feature in diagnostic model can get from decision tree and two-binary-Logistic-Regression. For the explicit and valuable and understandable rules, Rough set was more suitable for practice in diagnosis by experts. The Rough set should be study further to improve the accurate and cover rate of rules.
引文
[1]Gotuald TF, Daniaux M, Stoeger A, et al. The value of the World Wide Web for tele-education in radiology[J]. Tele Med Telecare,2000,6(1):27-30
[2]田盛丰,黄厚宽,石纯一.人工智能与知识工程[M].北京：中国铁道出版社,1999：32-33
[3]黄可鸣.专家系统导论[M].南京：东南大学出版社,1988：45-47
[4]张辉.骨肿瘤诊断知识库的构建应用研究[P],第四军医大学.2004
[5]R.A.Miller,H.E.Pople and J.D.Myers.Internist-I an experimental computer-based diagnostic onsultant for general internal medicine[J].N Engl J Med.1982,307(8):468-476
[6]GO.Barnett,E.P.Hoffer,M.S.Packer etc.DXPLAIN-demostration and discussion of a diagnostic clinical decision support system.Proc Annu Symp Comput Appl Med Care.1991:878-885
[7]谢洪波,于为,李小英等.基于神经网络和模糊理论的心功能辅助诊断专家系统.天津大学学报.2000,33(5)：610-614
[8]李家林,牟永阁,张利群.基于组合神经网络的肺心病辅助诊断系统的实验研究.生物医学工程学杂志.2001,18(4)：573-576
[9]李自双,张显全.针灸专家系统的研制.生物医学工程学杂志.1996,13(4)：323-327
[10]孙哲,黎庶,徐惠绵.数字化乳腺X线计算机辅助诊断系统临床应用价值的初步探讨[J].中华医学杂志,2005,85(24)：1692-5
[11]Katsuragawa S, Doi K, MacMahon H et al. Classification of normal and abnormal lungs with interstital diseases by rule-based method and artificial neural networks[J].J Digital Imag 1997,10:108-114.
[12]李继光,黎庶,徐惠绵等.全数字化乳腺X线成像计算机辅助检测结果的初步临床评估[J].中华放射学杂志,2006,40(2)：729-732
[13]ACR-Index [s]. American College of Radiology,2000
[14]Trumm C,Dugas M,Wirth S,et al.Digital teaching file concept,implementation, and experiences in a university setting[J].Radiology,2005,45(8):724-734
[15]Yam CS, Kruskal J, Sitek A, et al.A Web-based ACR index for radiolocical diagnoses[[J].AJR,2004,183(5);1517-1521.
[16]Clunie,DA. DICOM Structured Reporting, Pixel Med Publishing, Bangor PA, 2000.
[17]Clunie,DA. DICOM Structured Reporting:An Object model as an implementation boundary,2001.
[18]陈鎏,张建国DICOM结构化报告技术[J].红外,2003(11)：23-31
[19]杜先懋,李澄.医学影像存储与传输系统中结构化报告的初步应用研究[J].中华放射学杂志,2005,39(4)：428-431
[20]田军章.基于PACS的结构化报告(SR)模块的设计与实现研究[P].第一军医大学,2006
[21]江桂华,张雪林,田军章等.结构化报告中ACR编码的应用.实用放射学杂志[J].2006,22(3)：360-362
[22]李士勇.模糊控制、神经网络和智能控制论[M].哈尔滨：哈尔滨工业大学出版社,1998
[23]王国胤.Rough集理论与知识获取[M].西安：西安交通大学出版社,2001
[24]陈京明著.数据仓库与数据挖掘技术[M].北京：电子工业出版,2004
[25]朱明.数据挖掘[M].合肥：中国科学技术大学出版社,2002
[26]Wang ML,LamW,Leung KS,et al. Diseoveringknowledge from medieal databases usinge volutionary algorithms[J].IEEE Engineering in Medicine Biology,2000,19(4):45-55
[27]Usama M. Fayyad, Gregory Piatetsky-Shapir, Padhraic Smyth. Knowledge discovery and data mining:Towards a unifying framework. Proc.2nd Int. Conf. on Knowledge Discovery and Data Mining (KDD-96),AAAI Press 1996
[28]Liang Shen, Rangaraj M. Rangayyan et al. Application of Shape Analysis to Mammographic Calcification[J]. IEEE Transacyions on Medical Imaging 1994,13(2):263-274
[29]Rangayyan, R.M. El-Faramawy, N.M. Desautels,et al. Measures of Acutance and Shape for Classification of Breast Tumors[J].IEEE Transactions on Medical Imaging.1997,16(6):799-810
[30]Crelos A,Moshe.S, Evolutionay computation in medicine:an overview,Artiifcial Inteligence in Medicine,2000,19:1-2
[31]Beau bouef T, Petry F,Arora G. Information-theoretic measures of uncertainty for rough sets and rough relational databases [J]. Information Sciences, 1998,109:185-195.
[32]Milan Zorman,Vlii Podgorelec,et al. Finding the right decision tree's induction strategy for a Hard real world problem. Intenrational Journal of Medical Informatics,2001,63:109-121
[33]Igor Kononenko. Machine teaming for medical diagnosis:history, state of the art and perspective [J]. Artificial In telligence in Medicine,2002,23:89-109
[34]Z. Pawlak. Rough Sets. International Journal of Information and Computer Science,1982,11(5)341-356
[35]孙成敏.基于粗糙集的知识发现方法研究[D].吉林,吉林大学,2006.
[36]张学工.关于统计学习理论与支持向量机[J]自动化学报,2000,26(01)：32-42
[37]强永乾,郭佑民,李雪等.应用数据挖掘技术获取周围型肺癌临床和CT诊断规则的初步研究.[J].实用放射学杂志,2007,23(9)：1173-6
[38]Tsumoto S. Automated discovery of po sitive and negative knowledge in clinical databases [J].IEEE Engineerine in Medicine Biology,2000,19(4):56-62
[39]Cios KJ,Teresinska A,KoniecznaS,et al.A knowledge discovey approach to diagnosing Myocardial perfusion.IEEE Engineering in Medicine Biology,2000,19(4):17-25.
[40]马红霞,郭玉林,王秋萍等.分类决策树辅助CT诊断孤立性肺结节的方法学研究[J].中华放射学杂志,2008(42)1：50-55
[41]Wang MI,Lam W,Leung KS,et al.Discovering knowledge form medical databases using evolutionay algorithms.IEEE Engineering in Medicine Biology,2000,19(4):45-55
[42]支持向量机规则提取在大脑胶质瘤诊断中的应用[J].生物医学工程学杂志,2006,(02)：410-2
[43]王勇,张凯,吕扬生DICOM医学图像的存储与管理[[J].北京生物医学工程,2002,21(3)：194-197
[44]ICD-10.疾病和有关健康问题的国际统计分类[s].美国：世界卫生组织,2002.
[45]陈建国.ICD-10与ICD-O的异同辨析[J].中国卫生统计,2005,22(5)：324-326
[46]杨阳,崔蒙SNOMED发展概况与展望,中国中医药信息杂志.2007,14(2)：97-99.
[47]http://www.snomed.org.
[48]American College of Radiology'Index for Radiological Diagnoses.4th ed. Reston, Va:AmericanCollege of Radiology,1992.
[49]http://www.rsna.org/radlex/
[50]Curtis P.Langlotz.RadLex:A NewMethod for Indexing[J]. RadioGraphics,2006, 26(6):1595-1597
[51]B Walczak,DL Massart.Rough sets theory. Chemometrics and Intelligent Laboratory Systems[J].1999.47:1-16
[52]曾黄麟.粗糙集理论及其应用[M],重庆大学出版社,1998
[53]Pawlak Z..Rough sets and their applications. Microcomputer Applications, 1994,Vol.13(2):71-7
[54]Chmielewski MR. et al.The rule induction system LERS-a version for personal computers Foundations of Computing and Decision Sciences,1993,18(3-4): 181-12
[55]Lingras PJ, Yao YY.Data Mining using extensions of the rough set model. Journal of the American society for information science,1998,49(5):415-422.
[56]Quinlan JK. Induction of decision trees, in Readings in Machine Learning[M] T.D. Jude W Shavlik, Editor.1990, Morgan Kaufmann.57-69.
[57]Stefamowski J,Tsoukeas A. On the extension of rough sets under incomplete information.International Journal of Intelligent Systems,2000, 16(1):29-38.
[58]王国胤Rough集理论在不完备信息系统中的扩充.计算机研究与发展.2002.39(10)：1238-1235.
[59]Leung Y, Wu WZ,Zhang WX. Knowledge acquisition in incomplete information systems:A rough set approach.European Journal of Operational Research,2006. 168(1)164-180.
[60]Deja R. Conflict Model with Negotiations. Institute of Computer Science Reports Warsaw University of Technology, Warsaw,1995
[61]史忠植.知识发现[M].北京：清华大学出版社,2002：143-166
[62]刘清Rough集及Rough推理.北京：科学出版社,2001.60-66
[63]J.W.Guan,D.A.Bell.Rough computational methods for information systems.Artifical Intelligence,1998,105(1-2):77-103
[64]A.Skowron,C.Rauszer.The discernibility matrics and function in information system.in:R.Slowinski ed.Intelligent Decision Support Handbook of Application and Advances of the Rough sets Theory. Dordreecht:Kluwer Academic Publishers,1992,331-362
[65]Skoworn A.Boolean Reasoning of Decision Rules Generation.7th International SymPosiumon Methodologies for Intelligent Systems,1993,295-305.
[66]王亚英.基于粗糙集理论的知识发现方法研究(P).上海交通大学,2000
[67]Xiaoshu Hang,Honghua Dai.An Optimal Strategy for Extracting Probabilistic Rules by Combining Rouhg Sets and Genetic Algorithm.DS 2003,LNAI 2843:153-165.
[68]A Ohrn; J. Komorowski,A. Skowron, P. Synak. "The Design and Implementation of a Knowledge Discovery Toolkit Based on Rough Sets-The Rosetta System", in:Rough Sets in Knowledge Discovery,1998, (A. Skowron, L.Polkowski,Eds.), Springer Verlag.
[69]杨劲松, 陆雪官.高分级脑胶质瘤综合治疗的循证医学研究进展[J].中华肿瘤防治杂志,2007,14(13)：1025-8.
[70]Dean BL, Drayer BP and Bird CR, et al. Gliomas:classification with MR imaging[J]. Radiology.1990.174(2):411-5
[71]Asari S, Makabe T and Katayama S, et al. Assessment of the pathological grade of astrocytic gliomas using an MRI score[J]. Neuroradiology.1994,36(4): 308-310
[72]Ma J, Yang J and Geng D. Automatic diagnosis of malignant degree of brain glioma based on Bayesian network[J]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi.2006.23(1):184-8.
[73]Yamashita K, Yoshiura T and Arimura H, et al. Performance evaluation of radiologists with artificial neural network for differential diagnosis of intra-axial cerebral tumors on MR images[J]. AJNR Am J Neuroradiol.2008.29(6): 1153-8.
[74]马红霞,郭玉林,王秋萍等.分类决策树辅助CT诊断孤立性肺结节的方法学研究[J].中华放射学杂志,2008,42(1)：50-55
[75]Mihara F, Numaguchi Y and Rothman M, et al. MR imaging of adult supratentorial astrocytomas:an attempt of semi-automatic grading[J]. Radiat Med.1995,13(1):5-9
[76]Hanley JA, McNeil BJ. A method of comparing the areas under receiver operating characteristic curves derived from the same cases[J]. Radiology.1983. 148(3):839-43.
[77]Watanabe M, Tanaka R and Takeda N. Magnetic resonance imaging and histopathology of cerebral gliomas[J]. Neuroradiology.1992,34(6):463-9
[78]Pronin IN, Holodny AI and Petraikin AV. MRI of high-grade glial tumors: correlation between the degree of contrast enhancement and the volume of surrounding edema[J]. Neuroradiology.1997,39(5):348-50
[79]Korogi Y, Sugahara T and Takahashi M, et al. Differential diagnosis of astrocytic tumors[J]. Nippon Igaku Hoshasen Gakkai Zasshi.1999.59(5):170-5
[80]Wang X, Yang J and Jensen R, et al. Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma[J]. Comput Methods Programs Biomed.2006.83(2):147-56
[81]叶晨洲,杨杰,耿道颖.应用数据挖掘技术从大脑胶质瘤病例中获取诊断知识[J].生物医学工程学杂志,2002,19(3)：426-430
[82]Essig M, Weber MA, von Tengg-Kobligk H, et al. Contrast-enhanced magnetic resonance imaging of central nervous system tumors:agents, mechanisms, and applications[J]. Top Magn Reson Imaging,2007,17(2):89-106
[83]Della Puppa A, Zustovich F and Gardiman M, et al. Haemorrhagic presentation of low-grade glioma in adults[J]. Acta Neurochir (Wien).2007.149(11):1151-5
[84]Ye CZ, Yang J and Geng DY, et al. Fuzzy rules to predict degree of malignancy in brain glioma[J]. Med Biol Eng Comput.2002.40(2):145-52
[85]Pawlak Z..Rough sets and their applications[J]. Microcomputer Applications, 1994,13(2):71-7
[86]张超.分类树中C&RT算法与判别分析的比较及其医学应用[J].数理医药学杂志,2008,21(2)：139-141
[87]Wakulicz-Deja A, Paszek P. Diagnose progressive encephalopathy applying the rough set theory[J]. Int J Med Inform.1997.46(2):119-27.
[88]Urban M, Baszun-Stepaniuk E and Stepaniuk J. Application of the rough set theory in the prognostication of the diabetic nephropathy prevalence. Preliminary communication[J]. Endokrynol Diabetol Chor Przemiany Materii Wieku Rozw.2003.4(2):107-12
[89]Krzysztof Slowinski,D.S. Application of rule induction and rough sets to verification of magnetic resonance diagnosis[J]. Fundamenta Informaticae.2002. 53(3):345-363
[90]王小风,周明全,耿国华.一种基于模糊粗糙集理论的算法及其在医学影像中的应用[J].计算机应用研究,2005,11：222-224
[91]Hassan Y, Tazaki E and Egawa S, et al. Decision making using hybrid rough sets and neural networks[J]. Int J Neural Syst.2003.12(6):435-46.
[92]Jensen R, Shen Q. Semantics-preserving dimensionality reduction:rough and fuzzy-rough based roaches, IEEE Trans. Knowl. Data Eng.2004,16(12): 1457-1471
[1]National Electrical Manufacturers Association. Digital imaging and communications in medicine (DICOM), National Electrical Manufacturers Association:NEMA,2000.
[2]Kurihara Y, Okuhara Y, Naritan Y, et. al.Fast image accessing based on an analysis of the picture archiving and communications system in Kochi Medical School. Computerized medical imaging and Graphics2002,22 (6):439-445.
[3]张凯.基于语义的医学图像数据库系统[p].2003,天津大学
[4]Clunie, DA. DICOM Structured Reporting, Pixel Med Publishing, Bangor PA,2000.
[5]Clunie, DA. DICOM Structured Reporting:An Object model as an implementation boundary,2001.
[6]陈鎏,张建国DICOM结构化报告技术[J].红外,2003(11)：23-31
[7]杜先懋,李澄.医学影像存储与传输系统中结构化报告的初步应用研究[J].中华放射学杂志,2005,39(4)：428431
[8]田军章.基于PACS的结构化报告(SR)模块的设计与实现研究[P].第一军医大学,2006
[9]ICD-10.疾病和有关健康问题的国际统计分类[s].美国：世界卫生组织,2002.
[10]杨阳,崔蒙SNOMED发展概况与展望,中国中医药信息杂志.2007,14(2)：97-99.
[11]http://www.snomed.org.
[12]American College of Radiology'Index for Radiological Diagnoses. 4th ed. Reston, Va:AmericanCollege of Radiology,1992.
[13]ACR-Index [s]. American College of Radiology,2000
[14]http://www. rsna. org/radlex/
[15]Curtis P. Langlotz. RadLex:A NewMethod for Indexing[J]. RadioGraphics,2006,26(6):1595-1597
[16]DICOM3.0 [s]. American, ACR/NEMA,1992
[17]陈啸,宋华.DICOM标准下中文字符表示及编码的研究与实践[J].医疗卫生装备,2006,27(4)：28-19,31
[18]江桂华,张雪林,田军章,等.结构化报告中ACR编码的应用.实用放射学.2006,(22)3：360-362
[19]沈天真,范启勇,钟国康等.集成医疗保健企业(IHE). RSNA,2004.
[20]钟国康.IHE放射学22个成功案例分析[J]中国医学计算机成像杂志,2006,12(5)：309-315
[1]朱凌云,吴宝明.医学数据挖掘的技术、方法及应用[J].生物医学工程学杂志,2003,20(3)：559-562
[2]妮娜.数据库新的应用技术—数据挖掘技术[J].中国电子商务杂志,2003,4：700-72
[3]Wang ML,LamW,Leung KS,et al. Diseovering knowledge from medical databases using evolutionary algorithms[J].IEEE Engineering in Medicine Biology,2000,19(4):45-55
[4]毛国君,段立娟,王实,等.数据挖掘原理与算法[M]清华大学出版社.2005.
[5]K. MS, A. JD. Soft computing in engineering design-A review. Advanced Engineering Informatic,22(2):202-22
[6]Igor Kononenko. Machine teaming for medical diagnosis:history, state of the art and perspective [J]. Artificial In telligence in Medicine,2002,23:89-109
[7]Chengi BW,Luo CM,Chen KH. Using Data Mining to Evaluate Patient-oriented Medical Services for Chronic Senility Outpatients [J]. Quality&Quantity,2006, 40:1079-1087
[8]Lee A, Joynt GM and Ho AM, et al. Tips for teachers of evidence-based medicine: making sense of decision analysis using a decision tree[J]. J Gen Intern Med. 2009.24(5):642-8
[9]Porcel JM, Aleman C and Bielsa S, et al. A decision tree for differentiating tuberculous from malignant pleural effusions. Respir Med.2008.102(8):1159-64
[10]Cios KJ,Teresinska A,KoniecznaS,et al.A knowledge discovey approach to diagnosing Myocardial perfus ion [J]. IEEE Engineering in Medicine Biology,2000, 19(4):17-25.
[11]张超.数据挖掘中分类分析的策略研究及其生物医学应用[P].南方医科大学,2008
[12]Kokol P, Zorman M and Stiglic MM, et al. The limitations of decision trees and automatic learning in real world medical decision making. Stud Health Technol Inform.1999.52 Pt 1:529-33
[13]Crelos A,Moshe.S, Evolutionay computation in medicine:an overview[J]. Artiifcial Inteligence in Medicine,2000,19:l-2
[14]王小平,曹立明.遗传算法——理论、应用与软件实现[M].西安交通大学出版社,2002
[15]Zhai LY,Khoo LP,Fok SC.Feature extraction using rough set theory and genetic algorithms--an application for the simplification of product quality evaluation[J]. Computers and Industrial Engineering archive,2002,43 (4):661-676
[16]Zhou J, Krishnan S, Chong V, et al.Extraction of tongue carcinoma using genetic algorithm-induced fuzzy clustering and artificial neural network from MR images.Conf Proc IEEE Eng Med Biol Soc.2004,3:1790-3.
[17]Gayou O, Das SK, Zhou SM, et al.A genetic algorithm for variable selection in logistic regression analysis of radiotherapy treatment outcomes[J]. Med Phys,2008,35(12):5426-33.
[18]沈利,杨杰,周越.支持向量机的室性早搏检测[J].生物医学工程学杂志,2005,25(1)：78
[19]Emblem KE, Zoellner FG and Tennoe B, et al. Predictive modeling in glioma grading from MR perfusion images using support vector machines[J]. Magn Reson Med.2008.60(4):945-52.
[20]曾黄麟.粗糙集理论及其应用[M],重庆大学出版社,1998
[21]Tsumoto S. Automated discovery of positive and negative knowledge in clinical databases[J].IEEE Engineering in Medicine Biology,2000,19(4):56-6
[22]Hassan Y, Tazaki E and Egawa S, et al. Decision making using hybrid rough sets and neural networks[J]. Int J Neural Syst.2003,12(6):435-46
[23]王小风,周明全,耿国华.一种基于模糊粗糙集理论的算法及其在医学影像中的应用[J].计算机应用研究,2005,1：1222-4
[24]庄传礼,杨萍,李道亮等.基于神经网络和粗糙集规则的提取方法[J].计算机工程,2006,32(20)：191-2,209
[25]马常杰,陈守余.数据库中模糊关联规则挖掘研究进展[J].计算机工程与应用,2003 39(31)：181-183
[26]李军.粗糙集与模糊集的比较.长春理工大学学报[J].2003：25(4)：31-33
[27]黄正华,胡宝清.模糊粗糙集理论研究进展[J].模糊系统与数学,2005,19(4)：125-134
[28]Mustafa Demirci. Genuine sets, various kinds of fuzzy sets and fuzzy rough sets[J]. International Journal of Uncertainty, Fuzziness and Knowledge-Based Sy stems,2003,11 (4):467-494
[29]聂生东,陈瑛,顾顺德等.磁共振颅脑图像快速模糊聚类分割算法研究[J].中国生物医学工程学报.2001(20)：4-24
[30]基于BP神经网络的全身骨SPECT图像分割[J].2007,24(5)：1050-3
[31]Pavlopoulos S, Kyriacou E, Koutsouris D, et al. Fuzzy neural network based texture analysis of ultrasonic images[J]. IEEE Engineering in Medicine Biology, 2000,19 (4):39-47
[32]张一栋,吴锡生.基于伪并行免疫遗传算法和粗糙集的MRI图像分割方法[J]计算机工程与设计,2008,29(11)：2846-2847,2969.
[33]李璟,朱善安,Li Jing等.医学图像分割技术[J].生物医学工程学杂志,2006,23(4)：891-4
[34]Imberman SP, Domanski B, Thompson HW. Using dependency/association rules to find indications for computed tomography in a head trauma dataset [J].Artif Intell Med,2002,26 (1-2):55-68.
[35]Krzysztof Slowinski,DS. Application of rule induction and rough sets to verification of magnetic resonance diagnosis[J]. Fundamenta Informaticae.2002. 53(3):345-363
[36]Wang X, Yang J and Jensen R, et al. Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma[J]. Comput Methods Programs Biomed.2006.83(2):147-56
[37]Ye CZ, Yang J and Geng DY, et al. Fuzzy rules to predict degree of malignancy in brain glioma[J]. Med Biol Eng Comput.2002.40(2):145-52
[38]叶晨洲,杨杰,耿道颖.应用数据挖掘技术从大脑胶质瘤病例中获取诊断知识[J].生物医学工程学杂志,2002,19(3)：426-30
[39]Abdolmaleki P, Mihara F and Masuda K, et al. Neural networks analysis of astrocytic gliomas from MRI appearances[J]. Cancer Lett.1997.118(1):69-78
[40]Yamashita K, Yoshiura T and Arimura H, et al. Performance evaluation of radiologists with artificial neural network for differential diagnosis of intra-axial cerebral tumors on MR images[J]. AJNR Am J Neuroradiol.2008,29(6):1153-8
[2]田盛丰,黄厚宽,石纯一.人工智能与知识工程[M].北京：中国铁道出版社,1999：32-33
[3]黄可鸣.专家系统导论[M].南京：东南大学出版社,1988：45-47
[4]张辉.骨肿瘤诊断知识库的构建应用研究[P],第四军医大学.2004
[5]R.A.Miller,H.E.Pople and J.D.Myers.Internist-I an experimental computer-based diagnostic onsultant for general internal medicine[J].N Engl J Med.1982,307(8):468-476
[6]GO.Barnett,E.P.Hoffer,M.S.Packer etc.DXPLAIN-demostration and discussion of a diagnostic clinical decision support system.Proc Annu Symp Comput Appl Med Care.1991:878-885
[7]谢洪波,于为,李小英等.基于神经网络和模糊理论的心功能辅助诊断专家系统.天津大学学报.2000,33(5)：610-614
[8]李家林,牟永阁,张利群.基于组合神经网络的肺心病辅助诊断系统的实验研究.生物医学工程学杂志.2001,18(4)：573-576
[9]李自双,张显全.针灸专家系统的研制.生物医学工程学杂志.1996,13(4)：323-327
[10]孙哲,黎庶,徐惠绵.数字化乳腺X线计算机辅助诊断系统临床应用价值的初步探讨[J].中华医学杂志,2005,85(24)：1692-5
[11]Katsuragawa S, Doi K, MacMahon H et al. Classification of normal and abnormal lungs with interstital diseases by rule-based method and artificial neural networks[J].J Digital Imag 1997,10:108-114.
[12]李继光,黎庶,徐惠绵等.全数字化乳腺X线成像计算机辅助检测结果的初步临床评估[J].中华放射学杂志,2006,40(2)：729-732
[13]ACR-Index [s]. American College of Radiology,2000
[14]Trumm C,Dugas M,Wirth S,et al.Digital teaching file concept,implementation, and experiences in a university setting[J].Radiology,2005,45(8):724-734
[15]Yam CS, Kruskal J, Sitek A, et al.A Web-based ACR index for radiolocical diagnoses[[J].AJR,2004,183(5);1517-1521.
[16]Clunie,DA. DICOM Structured Reporting, Pixel Med Publishing, Bangor PA, 2000.
[17]Clunie,DA. DICOM Structured Reporting:An Object model as an implementation boundary,2001.
[18]陈鎏,张建国DICOM结构化报告技术[J].红外,2003(11)：23-31
[19]杜先懋,李澄.医学影像存储与传输系统中结构化报告的初步应用研究[J].中华放射学杂志,2005,39(4)：428-431
[20]田军章.基于PACS的结构化报告(SR)模块的设计与实现研究[P].第一军医大学,2006
[21]江桂华,张雪林,田军章等.结构化报告中ACR编码的应用.实用放射学杂志[J].2006,22(3)：360-362
[22]李士勇.模糊控制、神经网络和智能控制论[M].哈尔滨：哈尔滨工业大学出版社,1998
[23]王国胤.Rough集理论与知识获取[M].西安：西安交通大学出版社,2001
[24]陈京明著.数据仓库与数据挖掘技术[M].北京：电子工业出版,2004
[25]朱明.数据挖掘[M].合肥：中国科学技术大学出版社,2002
[26]Wang ML,LamW,Leung KS,et al. Diseoveringknowledge from medieal databases usinge volutionary algorithms[J].IEEE Engineering in Medicine Biology,2000,19(4):45-55
[27]Usama M. Fayyad, Gregory Piatetsky-Shapir, Padhraic Smyth. Knowledge discovery and data mining:Towards a unifying framework. Proc.2nd Int. Conf. on Knowledge Discovery and Data Mining (KDD-96),AAAI Press 1996
[28]Liang Shen, Rangaraj M. Rangayyan et al. Application of Shape Analysis to Mammographic Calcification[J]. IEEE Transacyions on Medical Imaging 1994,13(2):263-274
[29]Rangayyan, R.M. El-Faramawy, N.M. Desautels,et al. Measures of Acutance and Shape for Classification of Breast Tumors[J].IEEE Transactions on Medical Imaging.1997,16(6):799-810
[30]Crelos A,Moshe.S, Evolutionay computation in medicine:an overview,Artiifcial Inteligence in Medicine,2000,19:1-2
[31]Beau bouef T, Petry F,Arora G. Information-theoretic measures of uncertainty for rough sets and rough relational databases [J]. Information Sciences, 1998,109:185-195.
[32]Milan Zorman,Vlii Podgorelec,et al. Finding the right decision tree's induction strategy for a Hard real world problem. Intenrational Journal of Medical Informatics,2001,63:109-121
[33]Igor Kononenko. Machine teaming for medical diagnosis:history, state of the art and perspective [J]. Artificial In telligence in Medicine,2002,23:89-109
[34]Z. Pawlak. Rough Sets. International Journal of Information and Computer Science,1982,11(5)341-356
[35]孙成敏.基于粗糙集的知识发现方法研究[D].吉林,吉林大学,2006.
[36]张学工.关于统计学习理论与支持向量机[J]自动化学报,2000,26(01)：32-42
[37]强永乾,郭佑民,李雪等.应用数据挖掘技术获取周围型肺癌临床和CT诊断规则的初步研究.[J].实用放射学杂志,2007,23(9)：1173-6
[38]Tsumoto S. Automated discovery of po sitive and negative knowledge in clinical databases [J].IEEE Engineerine in Medicine Biology,2000,19(4):56-62
[39]Cios KJ,Teresinska A,KoniecznaS,et al.A knowledge discovey approach to diagnosing Myocardial perfusion.IEEE Engineering in Medicine Biology,2000,19(4):17-25.
[40]马红霞,郭玉林,王秋萍等.分类决策树辅助CT诊断孤立性肺结节的方法学研究[J].中华放射学杂志,2008(42)1：50-55
[41]Wang MI,Lam W,Leung KS,et al.Discovering knowledge form medical databases using evolutionay algorithms.IEEE Engineering in Medicine Biology,2000,19(4):45-55
[42]支持向量机规则提取在大脑胶质瘤诊断中的应用[J].生物医学工程学杂志,2006,(02)：410-2
[43]王勇,张凯,吕扬生DICOM医学图像的存储与管理[[J].北京生物医学工程,2002,21(3)：194-197
[44]ICD-10.疾病和有关健康问题的国际统计分类[s].美国：世界卫生组织,2002.
[45]陈建国.ICD-10与ICD-O的异同辨析[J].中国卫生统计,2005,22(5)：324-326
[46]杨阳,崔蒙SNOMED发展概况与展望,中国中医药信息杂志.2007,14(2)：97-99.
[47]http://www.snomed.org.
[48]American College of Radiology'Index for Radiological Diagnoses.4th ed. Reston, Va:AmericanCollege of Radiology,1992.
[49]http://www.rsna.org/radlex/
[50]Curtis P.Langlotz.RadLex:A NewMethod for Indexing[J]. RadioGraphics,2006, 26(6):1595-1597
[51]B Walczak,DL Massart.Rough sets theory. Chemometrics and Intelligent Laboratory Systems[J].1999.47:1-16
[52]曾黄麟.粗糙集理论及其应用[M],重庆大学出版社,1998
[53]Pawlak Z..Rough sets and their applications. Microcomputer Applications, 1994,Vol.13(2):71-7
[54]Chmielewski MR. et al.The rule induction system LERS-a version for personal computers Foundations of Computing and Decision Sciences,1993,18(3-4): 181-12
[55]Lingras PJ, Yao YY.Data Mining using extensions of the rough set model. Journal of the American society for information science,1998,49(5):415-422.
[56]Quinlan JK. Induction of decision trees, in Readings in Machine Learning[M] T.D. Jude W Shavlik, Editor.1990, Morgan Kaufmann.57-69.
[57]Stefamowski J,Tsoukeas A. On the extension of rough sets under incomplete information.International Journal of Intelligent Systems,2000, 16(1):29-38.
[58]王国胤Rough集理论在不完备信息系统中的扩充.计算机研究与发展.2002.39(10)：1238-1235.
[59]Leung Y, Wu WZ,Zhang WX. Knowledge acquisition in incomplete information systems:A rough set approach.European Journal of Operational Research,2006. 168(1)164-180.
[60]Deja R. Conflict Model with Negotiations. Institute of Computer Science Reports Warsaw University of Technology, Warsaw,1995
[61]史忠植.知识发现[M].北京：清华大学出版社,2002：143-166
[62]刘清Rough集及Rough推理.北京：科学出版社,2001.60-66
[63]J.W.Guan,D.A.Bell.Rough computational methods for information systems.Artifical Intelligence,1998,105(1-2):77-103
[64]A.Skowron,C.Rauszer.The discernibility matrics and function in information system.in:R.Slowinski ed.Intelligent Decision Support Handbook of Application and Advances of the Rough sets Theory. Dordreecht:Kluwer Academic Publishers,1992,331-362
[65]Skoworn A.Boolean Reasoning of Decision Rules Generation.7th International SymPosiumon Methodologies for Intelligent Systems,1993,295-305.
[66]王亚英.基于粗糙集理论的知识发现方法研究(P).上海交通大学,2000
[67]Xiaoshu Hang,Honghua Dai.An Optimal Strategy for Extracting Probabilistic Rules by Combining Rouhg Sets and Genetic Algorithm.DS 2003,LNAI 2843:153-165.
[68]A Ohrn; J. Komorowski,A. Skowron, P. Synak. "The Design and Implementation of a Knowledge Discovery Toolkit Based on Rough Sets-The Rosetta System", in:Rough Sets in Knowledge Discovery,1998, (A. Skowron, L.Polkowski,Eds.), Springer Verlag.
[69]杨劲松, 陆雪官.高分级脑胶质瘤综合治疗的循证医学研究进展[J].中华肿瘤防治杂志,2007,14(13)：1025-8.
[70]Dean BL, Drayer BP and Bird CR, et al. Gliomas:classification with MR imaging[J]. Radiology.1990.174(2):411-5
[71]Asari S, Makabe T and Katayama S, et al. Assessment of the pathological grade of astrocytic gliomas using an MRI score[J]. Neuroradiology.1994,36(4): 308-310
[72]Ma J, Yang J and Geng D. Automatic diagnosis of malignant degree of brain glioma based on Bayesian network[J]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi.2006.23(1):184-8.
[73]Yamashita K, Yoshiura T and Arimura H, et al. Performance evaluation of radiologists with artificial neural network for differential diagnosis of intra-axial cerebral tumors on MR images[J]. AJNR Am J Neuroradiol.2008.29(6): 1153-8.
[74]马红霞,郭玉林,王秋萍等.分类决策树辅助CT诊断孤立性肺结节的方法学研究[J].中华放射学杂志,2008,42(1)：50-55
[75]Mihara F, Numaguchi Y and Rothman M, et al. MR imaging of adult supratentorial astrocytomas:an attempt of semi-automatic grading[J]. Radiat Med.1995,13(1):5-9
[76]Hanley JA, McNeil BJ. A method of comparing the areas under receiver operating characteristic curves derived from the same cases[J]. Radiology.1983. 148(3):839-43.
[77]Watanabe M, Tanaka R and Takeda N. Magnetic resonance imaging and histopathology of cerebral gliomas[J]. Neuroradiology.1992,34(6):463-9
[78]Pronin IN, Holodny AI and Petraikin AV. MRI of high-grade glial tumors: correlation between the degree of contrast enhancement and the volume of surrounding edema[J]. Neuroradiology.1997,39(5):348-50
[79]Korogi Y, Sugahara T and Takahashi M, et al. Differential diagnosis of astrocytic tumors[J]. Nippon Igaku Hoshasen Gakkai Zasshi.1999.59(5):170-5
[80]Wang X, Yang J and Jensen R, et al. Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma[J]. Comput Methods Programs Biomed.2006.83(2):147-56
[81]叶晨洲,杨杰,耿道颖.应用数据挖掘技术从大脑胶质瘤病例中获取诊断知识[J].生物医学工程学杂志,2002,19(3)：426-430
[82]Essig M, Weber MA, von Tengg-Kobligk H, et al. Contrast-enhanced magnetic resonance imaging of central nervous system tumors:agents, mechanisms, and applications[J]. Top Magn Reson Imaging,2007,17(2):89-106
[83]Della Puppa A, Zustovich F and Gardiman M, et al. Haemorrhagic presentation of low-grade glioma in adults[J]. Acta Neurochir (Wien).2007.149(11):1151-5
[84]Ye CZ, Yang J and Geng DY, et al. Fuzzy rules to predict degree of malignancy in brain glioma[J]. Med Biol Eng Comput.2002.40(2):145-52
[85]Pawlak Z..Rough sets and their applications[J]. Microcomputer Applications, 1994,13(2):71-7
[86]张超.分类树中C&RT算法与判别分析的比较及其医学应用[J].数理医药学杂志,2008,21(2)：139-141
[87]Wakulicz-Deja A, Paszek P. Diagnose progressive encephalopathy applying the rough set theory[J]. Int J Med Inform.1997.46(2):119-27.
[88]Urban M, Baszun-Stepaniuk E and Stepaniuk J. Application of the rough set theory in the prognostication of the diabetic nephropathy prevalence. Preliminary communication[J]. Endokrynol Diabetol Chor Przemiany Materii Wieku Rozw.2003.4(2):107-12
[89]Krzysztof Slowinski,D.S. Application of rule induction and rough sets to verification of magnetic resonance diagnosis[J]. Fundamenta Informaticae.2002. 53(3):345-363
[90]王小风,周明全,耿国华.一种基于模糊粗糙集理论的算法及其在医学影像中的应用[J].计算机应用研究,2005,11：222-224
[91]Hassan Y, Tazaki E and Egawa S, et al. Decision making using hybrid rough sets and neural networks[J]. Int J Neural Syst.2003.12(6):435-46.
[92]Jensen R, Shen Q. Semantics-preserving dimensionality reduction:rough and fuzzy-rough based roaches, IEEE Trans. Knowl. Data Eng.2004,16(12): 1457-1471
[1]National Electrical Manufacturers Association. Digital imaging and communications in medicine (DICOM), National Electrical Manufacturers Association:NEMA,2000.
[2]Kurihara Y, Okuhara Y, Naritan Y, et. al.Fast image accessing based on an analysis of the picture archiving and communications system in Kochi Medical School. Computerized medical imaging and Graphics2002,22 (6):439-445.
[3]张凯.基于语义的医学图像数据库系统[p].2003,天津大学
[4]Clunie, DA. DICOM Structured Reporting, Pixel Med Publishing, Bangor PA,2000.
[5]Clunie, DA. DICOM Structured Reporting:An Object model as an implementation boundary,2001.
[6]陈鎏,张建国DICOM结构化报告技术[J].红外,2003(11)：23-31
[7]杜先懋,李澄.医学影像存储与传输系统中结构化报告的初步应用研究[J].中华放射学杂志,2005,39(4)：428431
[8]田军章.基于PACS的结构化报告(SR)模块的设计与实现研究[P].第一军医大学,2006
[9]ICD-10.疾病和有关健康问题的国际统计分类[s].美国：世界卫生组织,2002.
[10]杨阳,崔蒙SNOMED发展概况与展望,中国中医药信息杂志.2007,14(2)：97-99.
[11]http://www.snomed.org.
[12]American College of Radiology'Index for Radiological Diagnoses. 4th ed. Reston, Va:AmericanCollege of Radiology,1992.
[13]ACR-Index [s]. American College of Radiology,2000
[14]http://www. rsna. org/radlex/
[15]Curtis P. Langlotz. RadLex:A NewMethod for Indexing[J]. RadioGraphics,2006,26(6):1595-1597
[16]DICOM3.0 [s]. American, ACR/NEMA,1992
[17]陈啸,宋华.DICOM标准下中文字符表示及编码的研究与实践[J].医疗卫生装备,2006,27(4)：28-19,31
[18]江桂华,张雪林,田军章,等.结构化报告中ACR编码的应用.实用放射学.2006,(22)3：360-362
[19]沈天真,范启勇,钟国康等.集成医疗保健企业(IHE). RSNA,2004.
[20]钟国康.IHE放射学22个成功案例分析[J]中国医学计算机成像杂志,2006,12(5)：309-315
[1]朱凌云,吴宝明.医学数据挖掘的技术、方法及应用[J].生物医学工程学杂志,2003,20(3)：559-562
[2]妮娜.数据库新的应用技术—数据挖掘技术[J].中国电子商务杂志,2003,4：700-72
[3]Wang ML,LamW,Leung KS,et al. Diseovering knowledge from medical databases using evolutionary algorithms[J].IEEE Engineering in Medicine Biology,2000,19(4):45-55
[4]毛国君,段立娟,王实,等.数据挖掘原理与算法[M]清华大学出版社.2005.
[5]K. MS, A. JD. Soft computing in engineering design-A review. Advanced Engineering Informatic,22(2):202-22
[6]Igor Kononenko. Machine teaming for medical diagnosis:history, state of the art and perspective [J]. Artificial In telligence in Medicine,2002,23:89-109
[7]Chengi BW,Luo CM,Chen KH. Using Data Mining to Evaluate Patient-oriented Medical Services for Chronic Senility Outpatients [J]. Quality&Quantity,2006, 40:1079-1087
[8]Lee A, Joynt GM and Ho AM, et al. Tips for teachers of evidence-based medicine: making sense of decision analysis using a decision tree[J]. J Gen Intern Med. 2009.24(5):642-8
[9]Porcel JM, Aleman C and Bielsa S, et al. A decision tree for differentiating tuberculous from malignant pleural effusions. Respir Med.2008.102(8):1159-64
[10]Cios KJ,Teresinska A,KoniecznaS,et al.A knowledge discovey approach to diagnosing Myocardial perfus ion [J]. IEEE Engineering in Medicine Biology,2000, 19(4):17-25.
[11]张超.数据挖掘中分类分析的策略研究及其生物医学应用[P].南方医科大学,2008
[12]Kokol P, Zorman M and Stiglic MM, et al. The limitations of decision trees and automatic learning in real world medical decision making. Stud Health Technol Inform.1999.52 Pt 1:529-33
[13]Crelos A,Moshe.S, Evolutionay computation in medicine:an overview[J]. Artiifcial Inteligence in Medicine,2000,19:l-2
[14]王小平,曹立明.遗传算法——理论、应用与软件实现[M].西安交通大学出版社,2002
[15]Zhai LY,Khoo LP,Fok SC.Feature extraction using rough set theory and genetic algorithms--an application for the simplification of product quality evaluation[J]. Computers and Industrial Engineering archive,2002,43 (4):661-676
[16]Zhou J, Krishnan S, Chong V, et al.Extraction of tongue carcinoma using genetic algorithm-induced fuzzy clustering and artificial neural network from MR images.Conf Proc IEEE Eng Med Biol Soc.2004,3:1790-3.
[17]Gayou O, Das SK, Zhou SM, et al.A genetic algorithm for variable selection in logistic regression analysis of radiotherapy treatment outcomes[J]. Med Phys,2008,35(12):5426-33.
[18]沈利,杨杰,周越.支持向量机的室性早搏检测[J].生物医学工程学杂志,2005,25(1)：78
[19]Emblem KE, Zoellner FG and Tennoe B, et al. Predictive modeling in glioma grading from MR perfusion images using support vector machines[J]. Magn Reson Med.2008.60(4):945-52.
[20]曾黄麟.粗糙集理论及其应用[M],重庆大学出版社,1998
[21]Tsumoto S. Automated discovery of positive and negative knowledge in clinical databases[J].IEEE Engineering in Medicine Biology,2000,19(4):56-6
[22]Hassan Y, Tazaki E and Egawa S, et al. Decision making using hybrid rough sets and neural networks[J]. Int J Neural Syst.2003,12(6):435-46
[23]王小风,周明全,耿国华.一种基于模糊粗糙集理论的算法及其在医学影像中的应用[J].计算机应用研究,2005,1：1222-4
[24]庄传礼,杨萍,李道亮等.基于神经网络和粗糙集规则的提取方法[J].计算机工程,2006,32(20)：191-2,209
[25]马常杰,陈守余.数据库中模糊关联规则挖掘研究进展[J].计算机工程与应用,2003 39(31)：181-183
[26]李军.粗糙集与模糊集的比较.长春理工大学学报[J].2003：25(4)：31-33
[27]黄正华,胡宝清.模糊粗糙集理论研究进展[J].模糊系统与数学,2005,19(4)：125-134
[28]Mustafa Demirci. Genuine sets, various kinds of fuzzy sets and fuzzy rough sets[J]. International Journal of Uncertainty, Fuzziness and Knowledge-Based Sy stems,2003,11 (4):467-494
[29]聂生东,陈瑛,顾顺德等.磁共振颅脑图像快速模糊聚类分割算法研究[J].中国生物医学工程学报.2001(20)：4-24
[30]基于BP神经网络的全身骨SPECT图像分割[J].2007,24(5)：1050-3
[31]Pavlopoulos S, Kyriacou E, Koutsouris D, et al. Fuzzy neural network based texture analysis of ultrasonic images[J]. IEEE Engineering in Medicine Biology, 2000,19 (4):39-47
[32]张一栋,吴锡生.基于伪并行免疫遗传算法和粗糙集的MRI图像分割方法[J]计算机工程与设计,2008,29(11)：2846-2847,2969.
[33]李璟,朱善安,Li Jing等.医学图像分割技术[J].生物医学工程学杂志,2006,23(4)：891-4
[34]Imberman SP, Domanski B, Thompson HW. Using dependency/association rules to find indications for computed tomography in a head trauma dataset [J].Artif Intell Med,2002,26 (1-2):55-68.
[35]Krzysztof Slowinski,DS. Application of rule induction and rough sets to verification of magnetic resonance diagnosis[J]. Fundamenta Informaticae.2002. 53(3):345-363
[36]Wang X, Yang J and Jensen R, et al. Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma[J]. Comput Methods Programs Biomed.2006.83(2):147-56
[37]Ye CZ, Yang J and Geng DY, et al. Fuzzy rules to predict degree of malignancy in brain glioma[J]. Med Biol Eng Comput.2002.40(2):145-52
[38]叶晨洲,杨杰,耿道颖.应用数据挖掘技术从大脑胶质瘤病例中获取诊断知识[J].生物医学工程学杂志,2002,19(3)：426-30
[39]Abdolmaleki P, Mihara F and Masuda K, et al. Neural networks analysis of astrocytic gliomas from MRI appearances[J]. Cancer Lett.1997.118(1):69-78
[40]Yamashita K, Yoshiura T and Arimura H, et al. Performance evaluation of radiologists with artificial neural network for differential diagnosis of intra-axial cerebral tumors on MR images[J]. AJNR Am J Neuroradiol.2008,29(6):1153-8