超声子宫图像全自动识别研究
|
摘要
医学超声图像识别研究始终受到超声图像存在斑点噪声、信噪比低、边缘信息丢失等因素的影响。本文首先针对超声图像识别问题的固有特点，对不均衡类样本问题和数据噪声问题进行研究，提出了一种特征数据预处理机制，并结合多分类器融合提出了一种超声子宫图像识别框架。然后设计并实现了一种快速全自动的超声子宫图像节育环物体识别及定位算法。最后再设计并实现了一种快速全自动的超声图像胎儿性别部位识别及定位算法。
本文研究内容依次包括以下几个方面：
1、研究了不均衡类样本问题，概述了该领域的发展现状，并针对人造少数类样本生成机制进行研究，提出了一种人造样本过采样算法：ADOMS算法。基于UCI特征集开展实验验证工作，实验结果表明与其他相关算法相比，所提ADOMS算法可以更为有效地减轻不均衡类样本环境下分类器分类性能下降情况。
2、研究了数据噪声问题，概述了该领域的发展现状，并提出了一类基于数学形态学思想的形态学去噪算法。基于UCI特征集开展实验验证工作，实验结果表明与其他相关算法相比，所提形态学去噪算法可以更为有效地改善分类器分类性能。
3、提出了一种同时处理不均衡类样本问题和数据噪声问题的串联处理机制，通过实验验证了该串联处理机制在超声子宫图像识别问题上的良好效果。随后结合特征降维进一步提出了一种特征数据预处理机制，并在此基础上结合多分类器融合提出了一种超声子宫图像识别框架。
4、设计并实现了一种快速全自动的超声子宫图像节育环物体识别及定位算法，其包括全自动超声子宫图像分割和特定模式识别框架两大部分，通过感兴趣物体(Obiect of interest，OOI)进行连接。基于由719幅超声子宫图像所组成实验图像库开展算法性能验证工作，实验结果表明所提算法性能优秀，其处理过程完全自动，在普通PC机上平均耗时仅527ms／幅，有环图像识别及定位准确率达81．1％，无环图像识别准确率达94．7％。
5、设计并实现了一种快速全自动的超声图像胎儿性别部位识别及定位算法，其可分为粗分类阶段和细分类阶段两大部分，通过感兴趣像素(Point of interest，POI)进行连接。基于由658幅阳性图像(图中含胎儿性别部位)和500幅阴性图像(图中不含胎儿性别部位)所组成实验图像库开展算法性能验证工作，实验结果表明所提算法性能优秀，其处理过程完全自动，在普通PC机上平均耗时仅为453ms／幅，阳性图像识别及定位准确率达80．9％，阴性图像识别准确率达83．8％。
The research development of medical ultrasound image recognition is still cumbered by the poor quality of ultrasound image, including speckle, low signal-to-noise ratio, lost of edge information, etc. In this dissertation, focusing on the instinctive characteristics of ultrasound image recognition problem, the class imbalance problem and the data noise problem are studied at first, and then an ultrasound uterus image recognition framework is proposed, which is based on the proposed feature data preprocessing mechanism and the multiple classifiers fusion. After that, a fast and automatic ultrasound uterus image recognition algorithm for the intra-uterine device is proposed and realized. At last, a fast and automatic ultrasound image recognition algorithm for fetal genital organ is proposed and realized.
The main researches of this dissertation are listed as following:
1, The related work of dealing with the class imbalance problem is firstly reviewed, and then a proper generation mechanism of synthetic minority class examples is discussed. According to the analysis, a novel oversampling algorithm with synthetic examples, ADOMS, is proposed. The experiments are arranged on the UCI datasets and the experimental results show that comparing with other relative methods, algorithm ADOMS is able to alleviate the deterioration of the classification performance of the classifiers effectively.
2, The related work of dealing with the data noise problem is firstly reviewed, and then based on the concept of mathematic morphology, a series of morphological data cleansing algorithms are proposed. The experiments are arranged on the UCI datasets and the experimental results show that these morphological data cleansing algorithms can effectively improve the classification performance of the classifiers, comparing with other relative methods.
3, A concatenation mechanism is proposed to handle the class imbalance problem and the data noise problem together, and the effect of the proposed concatenation mechanism to the ultrasound uterus image recognition problem is confirmed by the experiments. And then, combing a proposed feature data preprocessing mechanism and the multiple classifiers fusion, an ultrasound uterus image recognition framework is proposed.
4, A fast and automatic ultrasound uterus image recognition algorithm for the intra-uterine device (IUD) is proposed and realized. The algorithm is composed of automatic ultrasound uterus image segmentation and the specific recognition framework, which are connected by object of interest (OOI). Based on 719 ultrasound uterus images, the experiments are carried out. The experimental results show that the proposed algorithm is fully automatic, and the average time-consuming is 527 milliseconds per frame, as well as the accuracy for the uterus image with IUD is 81.1% and the accuracy for the uterus image without IUD is 94.7%.
5, A fast and automatic ultrasound image recognition algorithm for fetal genital organ is proposed and realized. The algorithm is composed of rough classification stage and fine classification stage, which are connected by pixel of interest (POI). Based on 658 positive images (the ultrasound images which containing fetal genital organ) and 500 negative images (the ultrasound images without fetal genital organ), the experiments are carried out. The experimental results show that the proposed algorithm is fully automatic, and the average time-consuming is 453 milliseconds per frame, as well as the accuracy for the positive images is 80.9%, and the accuracy for the negative images is 83.8%.
本文研究内容依次包括以下几个方面：
1、研究了不均衡类样本问题，概述了该领域的发展现状，并针对人造少数类样本生成机制进行研究，提出了一种人造样本过采样算法：ADOMS算法。基于UCI特征集开展实验验证工作，实验结果表明与其他相关算法相比，所提ADOMS算法可以更为有效地减轻不均衡类样本环境下分类器分类性能下降情况。
2、研究了数据噪声问题，概述了该领域的发展现状，并提出了一类基于数学形态学思想的形态学去噪算法。基于UCI特征集开展实验验证工作，实验结果表明与其他相关算法相比，所提形态学去噪算法可以更为有效地改善分类器分类性能。
3、提出了一种同时处理不均衡类样本问题和数据噪声问题的串联处理机制，通过实验验证了该串联处理机制在超声子宫图像识别问题上的良好效果。随后结合特征降维进一步提出了一种特征数据预处理机制，并在此基础上结合多分类器融合提出了一种超声子宫图像识别框架。
4、设计并实现了一种快速全自动的超声子宫图像节育环物体识别及定位算法，其包括全自动超声子宫图像分割和特定模式识别框架两大部分，通过感兴趣物体(Obiect of interest，OOI)进行连接。基于由719幅超声子宫图像所组成实验图像库开展算法性能验证工作，实验结果表明所提算法性能优秀，其处理过程完全自动，在普通PC机上平均耗时仅527ms／幅，有环图像识别及定位准确率达81．1％，无环图像识别准确率达94．7％。
5、设计并实现了一种快速全自动的超声图像胎儿性别部位识别及定位算法，其可分为粗分类阶段和细分类阶段两大部分，通过感兴趣像素(Point of interest，POI)进行连接。基于由658幅阳性图像(图中含胎儿性别部位)和500幅阴性图像(图中不含胎儿性别部位)所组成实验图像库开展算法性能验证工作，实验结果表明所提算法性能优秀，其处理过程完全自动，在普通PC机上平均耗时仅为453ms／幅，阳性图像识别及定位准确率达80．9％，阴性图像识别准确率达83．8％。
The research development of medical ultrasound image recognition is still cumbered by the poor quality of ultrasound image, including speckle, low signal-to-noise ratio, lost of edge information, etc. In this dissertation, focusing on the instinctive characteristics of ultrasound image recognition problem, the class imbalance problem and the data noise problem are studied at first, and then an ultrasound uterus image recognition framework is proposed, which is based on the proposed feature data preprocessing mechanism and the multiple classifiers fusion. After that, a fast and automatic ultrasound uterus image recognition algorithm for the intra-uterine device is proposed and realized. At last, a fast and automatic ultrasound image recognition algorithm for fetal genital organ is proposed and realized.
The main researches of this dissertation are listed as following:
1, The related work of dealing with the class imbalance problem is firstly reviewed, and then a proper generation mechanism of synthetic minority class examples is discussed. According to the analysis, a novel oversampling algorithm with synthetic examples, ADOMS, is proposed. The experiments are arranged on the UCI datasets and the experimental results show that comparing with other relative methods, algorithm ADOMS is able to alleviate the deterioration of the classification performance of the classifiers effectively.
2, The related work of dealing with the data noise problem is firstly reviewed, and then based on the concept of mathematic morphology, a series of morphological data cleansing algorithms are proposed. The experiments are arranged on the UCI datasets and the experimental results show that these morphological data cleansing algorithms can effectively improve the classification performance of the classifiers, comparing with other relative methods.
3, A concatenation mechanism is proposed to handle the class imbalance problem and the data noise problem together, and the effect of the proposed concatenation mechanism to the ultrasound uterus image recognition problem is confirmed by the experiments. And then, combing a proposed feature data preprocessing mechanism and the multiple classifiers fusion, an ultrasound uterus image recognition framework is proposed.
4, A fast and automatic ultrasound uterus image recognition algorithm for the intra-uterine device (IUD) is proposed and realized. The algorithm is composed of automatic ultrasound uterus image segmentation and the specific recognition framework, which are connected by object of interest (OOI). Based on 719 ultrasound uterus images, the experiments are carried out. The experimental results show that the proposed algorithm is fully automatic, and the average time-consuming is 527 milliseconds per frame, as well as the accuracy for the uterus image with IUD is 81.1% and the accuracy for the uterus image without IUD is 94.7%.
5, A fast and automatic ultrasound image recognition algorithm for fetal genital organ is proposed and realized. The algorithm is composed of rough classification stage and fine classification stage, which are connected by pixel of interest (POI). Based on 658 positive images (the ultrasound images which containing fetal genital organ) and 500 negative images (the ultrasound images without fetal genital organ), the experiments are carried out. The experimental results show that the proposed algorithm is fully automatic, and the average time-consuming is 453 milliseconds per frame, as well as the accuracy for the positive images is 80.9%, and the accuracy for the negative images is 83.8%.
引文
[1] 霍福涛，张秀珍，“超声学进展”国外医学临床放射学分册，2：111-116，2005．
[2] JA Noble, D Boukerroui, "Ultrasound image segmentation: A survey" IEEE Trans. on Medical Imaging, 25(8): 987-1010, 2006.
[3] 严加勇，庄天戈，“医学超声图像分割技术的研究及发展趋势”北京生物医学工程，22(1)：67-71，2003．
[4] M Aleman-Flores, P Aleman-Flores, L Alvarez-Leon, etc. "Computerized ultrasound characterization of breast tumors" International Congress Series, 1281: 1063-1068, 2005.
[5] R Sivaramakrishna, K Powell, M Lieber, etc. "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[6] D Chen, R Chang, C Chen, etc. "Classification of breast ultrasound images using fractal feature" Journal of Clinical Imaging, 29: 235-245, 2005.
[7] LM Bruce, RR Adhami, "Classifying mammographic mass shapes using the wavelet transform modulus-maxima method" IEEE Trans. on Medical Imaging, 18(12): 1170-1177, 1999.
[8] N Piliouras, I Kalatzis, N Dimitropoulos, etc. "Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound" Computerized Medical Imaging and Graphics, 28: 247-255, 2004.
[9] W Shen, R Chang, W Moon, "Computer aided classification system for breast ultrasound based on breast imaging reporting and data system (BI-RADS)" ultrasound of medicine & biology, 33(11): 1688-1698, 2007.
[10] 林其忠，余建国，陈亚青，等．乳腺肿瘤超声图像识别模式分类方法的比较研究．上海医学影像，2006，15：102-104．
[11]林江莉，汪天富，彭玉兰，等．“乳腺肿瘤超声图像形态特征选择”四川师范大学学报，28：615-618．2005．
[12]张科宏，彭玉兰，李德玉，等．“基于边界特征的乳腺肿瘤超声图像识别”生物医学工程学杂志，23：1237-1240，2006．
[13]M Cvancarova, F Aibregtsen, K Brabrand, etc. "Segmentation of ultrasound images of liver tumors applying snake algorithms and GVF" International Congress Series, 1281: 218-223, 2005.
[14]T Vehmas, A Kaukiainen, K Luoma, etc. "Liver echogenicity: measurement or visual grading?" Computerized Medical Imaging and Graphics, 24: 289-293, 2004.
[15]徐涛，王明时，韩建新，等．“脂肪肝超声图像的定量分析”天津大学学报，2002，35：354-357．
[16]邹晓攀，陈菲，“基于机器视觉的肝癌超声图像特征信息提取”机器视觉，3：108-111，2006．
[17]林江莉，汪小毅，李德玉，等．“脂肪肝B超图像特征提取研究”四川大学学报，2005，37：130-134．
[18]黄亚丽，李芬华，张瑞波，“基于小波变换的脂肪肝B超图像识别”中国医学影像技术，2005．21：1761-1763．
[19]D Smutek, T Tjahjadi, R Sara, etc. "Image texture analysis of sonograms in chronic inflammations of thyroid gland" CMP, 2001. ftp://cmp.felk.cvut.cz/pub/cmp/articles/sara/Smutek-TR-2001-15.pdf
[20]A Mishra, PK Dutta, MK Ghosh, "A GA based approach for boundary detection of left ventricle with echocardiographic image sequences" Image and Vision Computing, 21: 967-976, 2003.
[21]ME Oiszewski, A Wahle, SC Mitchell, etc. "Segmentation of intravascular ultrasound images: a machine learning approach mimicking human vision" International Congress Series, 1268: 1045-1049, 2004.
[22]M Strzelecki, A Materka, J Drozdz, etc. "Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms" Computerized Medical Imaging and Graphics, 30: 95-107, 2006.
[23]DG Vince, KJ Dixon, RM Cothren, etc. "Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images" Computerized Medical Imaging and Graphics, 24: 221-229, 2000.
[24]AC Hodge, A Fenster, DB Downey, etc. "Prostate boundary segmentation from ultrasound images using 2D active shape models: Optimisation and extension to 3D" Computer Methods and Programs in Biomedicine, 84:99-113, 2006.
[25]Y Zhu, S Williams, R Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Imaging Analysis, 10:179-199, 2006.
[26]N Betrouni, M Vermandel, D Pasquier, etc. "Segmentation of abdominal ultrasound images of the prostate using a prior information and an adapted noise filter" Computerized Medical Imaging and Graphics, 29: 43-51,2005.
[27]Y Zhang, R Sankar, W Qian, "Boundary delineation in transrectal ultrasound image for prostate cancer" Computers in Biology and Medicine, 37:1591-1599, 2007.
[28]董硕，罗述谦，“活动形状模型在医学图像分割中的应用”国际生物医学工程杂志，30(3)：150-154．2007．
[29]FA Cosio, "Automatic initialization of an active shape model of the prostate" Medical Image Analysis, 12: 469-483, 2008.
[30]M Martin-Fernandez, C Alberola-Lopez, "An approach for contour detection of human kidneys from ultrasound images using Markov random fields and active contours" Medical Image Analysis, 9: 1-23, 2005.
[31]C Wu, Y Sun, "Segmentation of kidney from ultrasound B-mode images with texture-based classification" Computer Methods and Programs in Biomedicine, 84: 114-123, 2006.
[32]L Valentin, "Transvaginal sonography in gynaecology" Reviews in Gynaecological Practice, 4(1): 50-57, 2004.
[33]赵梅，“子宫肌瘤与子宫腺肌病的B超图像分析”中国超声医学杂志，12(10)：34-37，1996．
[34]图像来源于：http://health.big5.enorth.com.cn/system/2008/02/26/002872347.shtml
[35]N Mukhopadhaya, "Conventional myomectomy" Best Practice & Research Clinical Obstetrics and Gynaecology, 22(4): 677-705, 2008.
[36]花雪琴，张诚，“子宫肌瘤与子宫腺肌症的超声鉴别诊断”中国误诊学杂志，5(13)：2484-2485，2005．
[37]图像来源于：http://www.zhihuiyixue.com/bbs/post/view-109-49569-1-1-0.html
[38]图像来源于：http://www.zhihuiyixue.com/bbs/post/view-109-58732-1-1-0.html
[39]王蓉，“子宫肌瘤与子宫腺肌瘤的超声诊断及鉴别诊断”中华临床医药，5(17)：79-79，2004．
[40]图像来源于：http://www.zgiljr.com/article/40/458.html
[41]图像来源于：http://www.zgjljr.com/article/40/403.html
[42]张艳华，“B超对子宫肌瘤与子宫腺肌病声像图分析”中华临床医学实践杂志，4(4)：296-296，2005．
[43]黄丽卿，“经阴道超声诊断子宫内膜增生过长的价值研究”中国妇幼保健，22：5216-5217，2007．
[44]黄雪兰，“超声诊断子宫内膜病变的价值”实用医技杂志，12(7)：1705-1706，2005．
[45]吴丽芹，王秘林，赵淑文，“诊断子宫内膜病变三种方法比较”中华医学研究杂志，6(8)：892-894，2006．
[46]图像来源于：http://www.adoop.cn/medical-insurance/show-28932-1.html
[47]梁凤伟，朱志俏，巫晓华，等．“妊娠子宫破裂的超声诊断价值”中国超声诊断杂志，6(10)：769-770，2005．
[48]图像来源于：http://www.adoop.cn/medical-insurance/show-30103-1.html
[49]张媛香，“子宫内胚胎组织残留超声诊断价值”浙江预防医学，18(2)：47-47，2006．
[50]图像来源于：http://www.zhihuiyixue.com/bbs/post/view?bid=109&id=34629
[51]侯甫晓，岳学文，“子宫颈癌超声检查的价值”中国超声诊断杂志，4(7)：544-545，2003．
[52]图像来源于：http://www.usroom.net/article.asp?id=705
[53]辛德荣，“B超在宫内节育器诊断中的应用”天津医科大学学报，10(3)：471-473，2004．
[54]辛德荣，“超声在带器妊娠诊断中的应用”天津医科大学学报，10(1)：90-91，2004．
[55]宋戈萍，“宫内节育器的超声诊断”中国计划生育学杂志，49(5)：231-234，1999．
[56]魏溶，李涛，“实时超声监测宫内节育器的临床价值”河北医科大学学报，18(2)：85-86，1997．
[57]图像来源于：http://www.k120.com/cstech/image/05-753.html
[58]图像来源于：http://www.usroom.net/HTDOCS/XXLR1.ASP?ID=5430
[59]张儒秀，石俊，“超声在产前诊断中的应用”中国实用医药，3(17)：127-128，2008．
[60]曹海根，王金瑞，“实用腹部超声诊断学”北京：人民卫生出版社，774-788，1994．
[61]图像来源于：http://www.adoop.cn/medical-insurance/show-35972-1.html
[62]莫畏，“胎儿脐带缠绕的超声诊断价值”医学综述，14(13)：2075-2076，2008．
[63]李胜利，“胎儿畸形的产前超声检查”中华医学超声杂志(电子版)，2(1)：5-7，2005．
[64]银云燕，银云琳，兰桂珍，等．“先天性胎儿畸形的超声诊断分析”中国超声诊断杂志，4(10)：788-791，2003．
[65]B Potocnik, D Zazula, "Automated analysis of a sequence of ovarian ultrasound images. Part Ⅰ: segmentation of single 2D images" Image and Vision Computing, 20: 217-225, 2002.
[66]B Potocnik, D Zazula, "Automated analysis of a sequence of ovarian ultrasound images. Part Ⅱ: prediction-based object recognition from a sequence of images" Image and Vision Computing, 20: 227-235, 2002.
[67]B Potocnik, D Zazula, "Improved prediction-based ovarian follicle detection from a sequence of ultrasound images" Computer Methods and Programs in Biomedicine, 70:199-213, 2003.
[68]C Lu, T Van Gestel, JAK Suykens, etc. "Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines" Artificial Intelligence in Medicine, 28: 281-306, 2003.
[69]吴凯凯，汪源源，钱斌，“基于超声图像特征区分子宫肌瘤和腺肌病”中国生物医学工程学报，26(4)：537-581，2007．
[70]J Zhang, Y Wang, Y Dong, etc. "Ultrasonographic feature selection and pattern classification for cervical lymph nodes using support vector machines" Computer Methods and Programs in Biomedicine, 88: 75-84, 2007.
[71]SVB Jardim, MAT Figueiredo, "Automatic contour estimation in fetal ultrasound images" ICIP2003, 2: 1065-1068, 2003.
[72]W Lu, J Tan, R Floyd, "Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform" Ultrasound in Medicine & Biology, 31(7): 929-936, 2005.
[73]W Lu, J Tan, "Detection of incomplete ellipse in images with strong noise by iterative randomized Hough transform (IRHT)" Pattern Recognition, 41:1268-1279, 2008.
[74]余锦华，汪源源，陈萍，etc．“胎儿超声图像分割及自动径线测量”中国生物医学工程学报，26(6)：867-874：2007．
[75]J Yu, Y Wang, P Chen, etc. "Fetal abdominal contour extraction and measurement in ultrasound images" Ultrasound in Medicine & Biology, 34(2): 169-182, 2008.
[76]KN Bhanu Prakash, AG Ramakrishman, S Suresh, etc. "Fetal lung maturity analysis using ultrasound image features" IEEE Trans. on Information Technology in Biomedicine, 6(1): 38-45: 2002.
[77]吴君，杨太珠，林江莉，等．“基于人工神经网络的足月胎儿体重预测方法”生物医学工程学杂志，22(5)：922-925，2005．
[78]马翔，汪源源，王威琪，等．“图像特征参量分析方法及其在胎儿分级中的应用”航天医学与医学工程，14(5)：336-340：2001．
[79]NV Chawla, N Japkowicz, A Kolcz, "Editorial: Special Issue on Learning from Imbalanced Data Sets," SIGKDD Explorations, 6(1), 1-6, 2004.
[80]I Guyon, A Elisseeff, "An Introduction to Variable and Feature Selection" Journal of Machine Learning Research, 3:1157-1182, 2003.
[81]C Blake, C Merz, "UCI Repository of Machine Learning Databases," 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[1] R Barandela, JS Sanchez, V Garcia, E Rangel, "Strategies for Learning in Class Imbalance Problems," Pattern Recognition, 36, 849-851, 2003.
[2] A Kolcz, A Chowdhury, J Alspector, "Data duplication: an imbalance problem?" in Proc. of the ICMU03 Workshop on Learning from Imbalanced Datasets, 2003.
[3] C Phua, D Alahakoon, V Lee, "Minority Report in Fraud Detection: Classification of Skewed Data" SIGKDD Explorations, 6(1), 50-59, 2004.
[4] NV Chawla, "C4.5 and Imbalanced Data sets: Investigating the effect of sampling method, probabilistic estimate, and decision tree structure" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[5] B Raskutti, A Kowalczyk, "Extreme Re-balancing for SVMs: a case study" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[6] NV Chawla, N Japkowicz, A Kolcz, "Editorial: Special Issue on Learning from Imbalanced Data Sets," SIGKDD Explorations, 6(1), 1-6, 2004.
[7] N Japkowicz, "Class Imbalance: Are We Focusing on the Right Issue?" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[8] T Jo, N Japkowicz, "Class Imbalance versus Small Disjuncts," SIGKDD Explorations, 6(1), 40-49, 2004.
[9] GM Weiss, "Mining with Rarity: A Unifying Framework," SIGKDD Explorations, 6(1), 7-19, 2004.
[10] MA Maloof, "Learning When Data Sets are Imbalanced and When Costs are Unequal and Unknown," in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[11] G Wu, EY Chang, "Class-Boundary Alignment for Imbalanced Dataset Learning," in Proc. of the ICML'03 Workshop on Learning from lmbalanced Datasets, 2003.
[12] C Drummond, RC Holte, "C4.5, Class Imbalance, and Cost Sensitivity: Why Under-sampling Beats Over-sampling," in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[13] GEAPA Batista, RC Prati, MC Monard, "A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data," SIGKDD Explorations, 6(1), 20-29, 2004.
[14] NV Chawla, KW Bowyer, LO Hall, W.P. Kegelmeyer, "SMOTE: Synthetic Minority Oversampling Technique," Journal of Artificial Intelligence Research, 16, 321-257, 2002.
[15] JCB Melo, GDC Cavalcanti, KS Guimaraes, "PCA feature extraction for protein structure prediction" Neural Networks, 4, 2952-2957, 2003.
[16] J Cowe, DH Evans, "Automatic detection of emboli in the TCD RF signal using principle component analysis" Ultrasound of Medical & Biology, 32, 1853-1867,2006.
[17] HH Goldstine, FJ Murray, J von Neumann, "The Jacobi Method for Real Symmetric Matrices" Journal of the ACM, 6(1), 59-96, 1959.
[18] M Kubat, S Matwin, "Addressing the Curse of Imbalanced Training Sets: One-sided Selection," in Proc. of the 1CML, 179-186, 1997.
[19] YL Murphey, H Guo, "Neural Learning from Unbalanced Data." Applied Intelligence, 21, 117-128,2004.
[20] C Blake, C Merz, "UCI Repository of Machine Learning Databases," 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[21] AR Webb, Statistical Pattern Recognition, John Wiley & Sons, 2002.
[1] M Pechenizkiy, A Tsymbal, S Puuronen, O Pechenizkiy, "Class Noise and Supervised Learning in Medical Domains: The Effect of Feature Extraction", 19~(th) IEEE International Symposium on Computer-Based Medical Systems, 2006.
[2] XQ Zhu, XD Wu, QJ Chen, "Bridging Local and Global Data Cleansing: Identifying Class Noise in Large, Distributed Data Datasets" Data Mining and Knowledge Discovery, 12: 275-308, 2006.
[3] H Xiong, G Pandey, M Steinbach, V Kumar, "Enhancing Data Analysis with Noise Removal" IEEE Transactions on Knowledge and Data Engineering, Vol. 18, No. 3, 2006.
[4] JR Quinlan, "Induction of Decisions Trees" Machine Learning, 1: 81-106, 1986.
[5] YL Li, L Wessels, M Reinders, "Class-noise Tolerant Classification Based on a Probabilistic Noise Model" Twelfth Annual Conf. of the Advanced School for Computing and Imaging, 2006.
[6] XQ Zhu, XD Wu, "Class Noise vs. Attribute Noise: A Quantitative Study of Their Impacts" Artificial Intelligence Review, 22: 177-210, 2004.
[7] XQ Zhu, XD Wu, Y Yang, "Error Detection and Impact-sensitive Instance Ranking in Noisy Datasets" AAAI-2004, San Joise, CA.
[8] Y Sakakibara, "Noise-tolerant Occam Algorithms and Their Applications to Learning Decision Trees", Machine Learning, 11: 37-62, 1993.
[9] J Mingers, "An Empirical Comparison of Pruning Methods for Decision Tree Induction" Machine Learning, 4-2: 227-243, 1989.
[10] D Gamberger, N Lavrac, S Dzeroski, "Noise Detection and Elimination in Data Preprocessing: Experiments in Medical Domains" Applied Artificial Intelligence, 14: 205-223, 2000.
[11] CE Brodley, MA Friedl, "Identifying Mislabeled Training Data" Journal of Artificial Intelligence Research, 11,131-167, 1999.
[12] J Sander, M Ester, HP Kriegel, X Xu, "Density-based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications" Data Mining and Knowledge Discovery, Vol. 2, No. 2, 1998.
[13] D Wilson, T Martinez, "Reduction Techniques for Exemplar-Based Learning Algorithms" Machine Learning, 1998.
[14] I Tomek, "Two Modifications of CNN" IEEE Transactions on Systems, Man, and Communications SMC-6, 769-772, 1976.
[15]D Wilson, "Asymptotic Properties of Nearest Neighbor Rules Using Edited Data" IEEE Transactions on Systems, Man, and Communications 2: 3, 408-421, 1972.
[16]Occam's Razor: http://en.wikipedia.org/wiki/Occam's_Razor
[17]J Serra, "Image Analysis and Mathematic Morphology" Academic Press, New York, 1982.
[18]RC Gonzalez, RE Woods, "Digital Image Processing, 2E" Prentice Hall, 2002.
[19]YL Murphey, H Guo, "Neural Learning from Unbalanced Data" Applied Intelligence, 21,117-128,2004.
[20]C Blake, C Merz, UCI Repository of Machine Learning Databases, 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[1] M Pechenizkiy, A Tsymbai, S Puuronen, etc, "Class noise and supervised learning in medical domains: the effect of feature extraction" 19th IEEE International Symposium on Computer-Based Medical Systems, 2006.
[2] XQ Zhu, XD Wu, QJ Chen, "Bridging local and global data cleansing: identifying class noise in large, distributed data datasets" Data Mining and Knowledge Discovery, 12: 275-308, 2006.
[3] R Sivaramakrishna, K Powell, M Lieber, etc, "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[4] I Guler, E Ubeyli, "Feature saliency using signal-to-noise ratios in automated diagnositic systems developed for Doppler ultrasound signals" Engineering Applications of Artificial Intelligence, 19: 53-63, 2006.
[5] K Bhanu Prakash, A Ramakrishnan, S Suresh, etc, "Fetal lung maturity analysis using ultrasound image features" IEEE Trans On Information Technology in Biomedicine, 6: 38-45, 2002.
[6] WQ Zhang, "The report about the sampling investigation of the effects of the pregnancy prevention using IUD in China, by the organizations of Chinese population and family planning" 2005.
[7] 崔满华，安启哲，“宫内节育器的避孕原理”中国实用妇科与产科杂志，11(4)：209-210，1995．
[8] 毛勇，周晓波，夏铮，等．“特征选择算法研究综述”模式识别与人工智能，20(2)：211-218，2007．
[9] I Guyon, "An introduction to variable and feature selection" Journal of Machine Learning Research, 3: 1157-1182, 2003.
[10] R Kohavi, GH John, "Wrappers for feature subset selection" Artificial Intelligence, 97: 273-324, 1997.
[11] J Kittler, F Roli, "Multiple Classifier Systems, First International Workshop, MCS 2000, Cagliari, Italy, June 21-23, 2000, Proceedings" LNCS 1857, Springer, 2000, ISBN 3-540-67704-6.
[12] 王正群，孙兴华，杨静宇，“多分类器组合研究”计算机工程与应用，20：84-86，2002．
[1] Intrauterine Device, http://en.wikipedia.org/wiki/Intrauterine_device
[2] What is an IUD? http://www.fwhc.org/birth-control/iudinfo.htm
[3] 张俊英，“关于宫内节育器的探讨”实用医技杂志，15(16)：2135-2137，2008．
[4] 崔满华，安启哲，“宫内节育器的避孕原理”中国实用妇科与产科杂志，11(4)：209-210，1995．
[5] 顾红媛，“浅析宫内节育器避孕的原理及放置”中国临床医药研究杂志，144：15654-15654，2005．
[6] 谢淑雯，“4种活性宫内节育器放置7年的临床评价”现代医学卫生，21(6)：645-647，2005．
[7] 张维，“宫内节育器的进展与临床应用”常熟高专学报，16(4)：106-106，2002．
[8] 吴周光，倪雪漫，孙家庆，“宫腔内IUD的正常异常超声表现”实用妇产科杂志，8(3)：154，1992．
[9] 辛德荣，“B超在宫内节育器诊断中的应用”天津医科大学学报，10(3)：471-473，2004．
[10] 中华人民共和国国务院令(第309号)“计划生育技术服务管理条例”发布日期：2001-07-09．
[11]盘点宫内节育器的12个问题，中国国家人口和计划生育委员会网站 http://www.chinapop.gov.cn/kpyd/byjy/200408/t20040823_148960.htm
[12]节育提示：宫内节育器不是终身环，中国国家人口和计划生育委员会网站 http://www.chinapop.gov.cn/kpyd/byjy/200709/t20070927_48757.htm
[13]K Bhanu Prakash, A Ramakrishnan, S Suresh, et al. "Fetal lung maturity analysis using ultrasound image features" IEEE Trans Information Technology in Biomedicine, 6(1): 38-45,2002.
[14]M Strzelecki, A Materka, J Drozdz, et al. "Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms" Computerized Medical Imaging and Graphics, 30:95-107, 2006.
[15]Y Zhu, S Williams, R Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Image Analysis, 10:178-199, 2006.
[16] 吴君，杨太珠，林江莉，等．“基于人工神经网络的足月胎儿体重预测方法”生物医学工程学杂志，22(5)：922-925，2005．
[17]林江莉，汪小毅，李德玉，等．“脂肪肝B超图像特征提取研究”四川大学学报，37(1)：130-134．2005．
[18]M Karaman, M Kutay, G Bozdagi, "An adaptive speckle suppression filter for medial ultrasonic imaging" IEEE Trans Med Imaging, 14(2): 283-292, 1995.
[19]CHEN Yan, YIN Ru-ming, P Flynn, et al. "Aggressive region growing for speckle reduction in ultrasound images" Pattern Recognition Letters, 24: 677-691, 2003.
[20]T Loupas, WN McDicken, PL Allan, "Adaptive weighted median filter for speckle suppression in medical ultrasonic images" IEEE Trans Circuit System, 36:129-135:1989.
[21]R Duda, P Hart, D Stork, "Pattern Recognition" New York: John Wiley & Sons, 2001.
[22]I Guyon, A Elisseeff, "An introduction to variable and feature selection" Journal of Machine Learning Research, 3:1157-1182, 2003.
[1] 潘嘉，“韩国、印度和中国台湾治理出生性别比失衡的经验与启示”中国党政干部论坛，9：17-18．2007．
[2] Population Census Office under Chinese State Council, "Zhongguo 2000 Nian Renkou Pucha Ziliao (Tabulation on the 2000 Population Census of the People's Republic of China) (In Chinese)" Beijing: China Statistics Press, 2002.
[3] 王君平，徐静，“中国出生性别比失衡最严重”中外健康文摘，8：58-58：2007．
[4] Y Qi, WM Mason, "Prenatal sex-selective abortion and high sex ratio at birth in rural china: A case study in Henan province. On-Line Working Paper Series 2005" http://repositories.cdlib.org/ccpr/olwp/CCPR-057-05.
[5] S Li, "Imbalanced sex ratio at birth and comprehensive intervention in China" The 4~(th) Asia Pacific Conference on Reproductive and Sexual Health and Rights, Oct 29-31 2007, Hyderabad, India, http://www.unfpa.org/gender/docs/studies/china.pdf.
[6] 中华人民共和国国家计划生育委员会第8号部长令“关于禁止非医学需要的胎儿性别鉴定和选择性别的人工终止妊娠的规定”实施时间：2003-01-01．
[7] 郑幼卿，洪建章，丁鸿儒，“福建省打击非法胎儿性别鉴定、非法终止妊娠行动中存在的问题及对策”中国卫生监督杂志，14(4)：304-306，2007．
[8] 周强，“一种对B超胎儿性别鉴别进行记录的方法”专利申请号：200510090509．0
[9] TA Scholly, JH Sutphen, SC Mackey, etc. "Sonographic determination of fetal gender"American Journal of Roentgenology, 135:1161-1165, 1980.
[10]C Lu, T van Gestel, JAK Suykens, etc. "Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines" Artificial Intelligence in Medicine, 28:281-306, 2003.
[11]D Smutek, T Tjahjadi, R Sara, etc. "Image texture analysis of sonograms in chronic inflammations of thyroid gland" Research Report CTU-CMP-2001-15, April 2001, Czech Technical University, Prague, Czech Republic, ISSN 1213-2365.ftp://cmp.felk.evut.cz/pub/cmp/articles/sara/Smutek-TR-2001-15.pdf
[12]DG Vince, KJ Dixon, RM Cothren, etc. "Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images" Computerized Medical Imaging and Graphics, 24: 221-229, 2000.
[13]Y Zhu, S Williams, Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Image Analysis, 10:178-199, 2006.
[14] D Buller, A Buller, PR Innocent, etc. "Determining and classifying the region of interest in ultrasonic images of the breast using neural networks" Artificial Intelligence in Medicine, 8:53-66, 1996.
[15]DR Chen, RF Chang, CJ Chen, etc. "Classification of breast ultrasound images using fractal feature" Journal of Clinical Imaging, 29: 235-245, 2005.
[16]N Piliouras, I Kalatzis, N Dimitropoulos, etc. "Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound" Computerized Medical Imaging and Graphics, 28: 247-255, 2004.
[17]R Sivaramakrishna, KA Powell, ML Leiber, etc. "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[18]S Jardim, M Figueiredo, "Segmentation of fetal ultrasound images" Ultrasound of Medicine & Biology, 31(2): 243-250,2005.
[19]W Lu, J Tan, R Floyd, "Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform" Ultrasound of Medicine & Biology, 31(7): 929-936, 2005.
[20]T Kadonaga, K Abe, "Comparison of methods for detecting corner points from digital curves" Proceedings of the First International Workshop on Graphic Recognition. Aug 10-11 1995, University Park, PA, USA: 23-34.
[2] JA Noble, D Boukerroui, "Ultrasound image segmentation: A survey" IEEE Trans. on Medical Imaging, 25(8): 987-1010, 2006.
[3] 严加勇，庄天戈，“医学超声图像分割技术的研究及发展趋势”北京生物医学工程，22(1)：67-71，2003．
[4] M Aleman-Flores, P Aleman-Flores, L Alvarez-Leon, etc. "Computerized ultrasound characterization of breast tumors" International Congress Series, 1281: 1063-1068, 2005.
[5] R Sivaramakrishna, K Powell, M Lieber, etc. "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[6] D Chen, R Chang, C Chen, etc. "Classification of breast ultrasound images using fractal feature" Journal of Clinical Imaging, 29: 235-245, 2005.
[7] LM Bruce, RR Adhami, "Classifying mammographic mass shapes using the wavelet transform modulus-maxima method" IEEE Trans. on Medical Imaging, 18(12): 1170-1177, 1999.
[8] N Piliouras, I Kalatzis, N Dimitropoulos, etc. "Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound" Computerized Medical Imaging and Graphics, 28: 247-255, 2004.
[9] W Shen, R Chang, W Moon, "Computer aided classification system for breast ultrasound based on breast imaging reporting and data system (BI-RADS)" ultrasound of medicine & biology, 33(11): 1688-1698, 2007.
[10] 林其忠，余建国，陈亚青，等．乳腺肿瘤超声图像识别模式分类方法的比较研究．上海医学影像，2006，15：102-104．
[11]林江莉，汪天富，彭玉兰，等．“乳腺肿瘤超声图像形态特征选择”四川师范大学学报，28：615-618．2005．
[12]张科宏，彭玉兰，李德玉，等．“基于边界特征的乳腺肿瘤超声图像识别”生物医学工程学杂志，23：1237-1240，2006．
[13]M Cvancarova, F Aibregtsen, K Brabrand, etc. "Segmentation of ultrasound images of liver tumors applying snake algorithms and GVF" International Congress Series, 1281: 218-223, 2005.
[14]T Vehmas, A Kaukiainen, K Luoma, etc. "Liver echogenicity: measurement or visual grading?" Computerized Medical Imaging and Graphics, 24: 289-293, 2004.
[15]徐涛，王明时，韩建新，等．“脂肪肝超声图像的定量分析”天津大学学报，2002，35：354-357．
[16]邹晓攀，陈菲，“基于机器视觉的肝癌超声图像特征信息提取”机器视觉，3：108-111，2006．
[17]林江莉，汪小毅，李德玉，等．“脂肪肝B超图像特征提取研究”四川大学学报，2005，37：130-134．
[18]黄亚丽，李芬华，张瑞波，“基于小波变换的脂肪肝B超图像识别”中国医学影像技术，2005．21：1761-1763．
[19]D Smutek, T Tjahjadi, R Sara, etc. "Image texture analysis of sonograms in chronic inflammations of thyroid gland" CMP, 2001. ftp://cmp.felk.cvut.cz/pub/cmp/articles/sara/Smutek-TR-2001-15.pdf
[20]A Mishra, PK Dutta, MK Ghosh, "A GA based approach for boundary detection of left ventricle with echocardiographic image sequences" Image and Vision Computing, 21: 967-976, 2003.
[21]ME Oiszewski, A Wahle, SC Mitchell, etc. "Segmentation of intravascular ultrasound images: a machine learning approach mimicking human vision" International Congress Series, 1268: 1045-1049, 2004.
[22]M Strzelecki, A Materka, J Drozdz, etc. "Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms" Computerized Medical Imaging and Graphics, 30: 95-107, 2006.
[23]DG Vince, KJ Dixon, RM Cothren, etc. "Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images" Computerized Medical Imaging and Graphics, 24: 221-229, 2000.
[24]AC Hodge, A Fenster, DB Downey, etc. "Prostate boundary segmentation from ultrasound images using 2D active shape models: Optimisation and extension to 3D" Computer Methods and Programs in Biomedicine, 84:99-113, 2006.
[25]Y Zhu, S Williams, R Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Imaging Analysis, 10:179-199, 2006.
[26]N Betrouni, M Vermandel, D Pasquier, etc. "Segmentation of abdominal ultrasound images of the prostate using a prior information and an adapted noise filter" Computerized Medical Imaging and Graphics, 29: 43-51,2005.
[27]Y Zhang, R Sankar, W Qian, "Boundary delineation in transrectal ultrasound image for prostate cancer" Computers in Biology and Medicine, 37:1591-1599, 2007.
[28]董硕，罗述谦，“活动形状模型在医学图像分割中的应用”国际生物医学工程杂志，30(3)：150-154．2007．
[29]FA Cosio, "Automatic initialization of an active shape model of the prostate" Medical Image Analysis, 12: 469-483, 2008.
[30]M Martin-Fernandez, C Alberola-Lopez, "An approach for contour detection of human kidneys from ultrasound images using Markov random fields and active contours" Medical Image Analysis, 9: 1-23, 2005.
[31]C Wu, Y Sun, "Segmentation of kidney from ultrasound B-mode images with texture-based classification" Computer Methods and Programs in Biomedicine, 84: 114-123, 2006.
[32]L Valentin, "Transvaginal sonography in gynaecology" Reviews in Gynaecological Practice, 4(1): 50-57, 2004.
[33]赵梅，“子宫肌瘤与子宫腺肌病的B超图像分析”中国超声医学杂志，12(10)：34-37，1996．
[34]图像来源于：http://health.big5.enorth.com.cn/system/2008/02/26/002872347.shtml
[35]N Mukhopadhaya, "Conventional myomectomy" Best Practice & Research Clinical Obstetrics and Gynaecology, 22(4): 677-705, 2008.
[36]花雪琴，张诚，“子宫肌瘤与子宫腺肌症的超声鉴别诊断”中国误诊学杂志，5(13)：2484-2485，2005．
[37]图像来源于：http://www.zhihuiyixue.com/bbs/post/view-109-49569-1-1-0.html
[38]图像来源于：http://www.zhihuiyixue.com/bbs/post/view-109-58732-1-1-0.html
[39]王蓉，“子宫肌瘤与子宫腺肌瘤的超声诊断及鉴别诊断”中华临床医药，5(17)：79-79，2004．
[40]图像来源于：http://www.zgiljr.com/article/40/458.html
[41]图像来源于：http://www.zgjljr.com/article/40/403.html
[42]张艳华，“B超对子宫肌瘤与子宫腺肌病声像图分析”中华临床医学实践杂志，4(4)：296-296，2005．
[43]黄丽卿，“经阴道超声诊断子宫内膜增生过长的价值研究”中国妇幼保健，22：5216-5217，2007．
[44]黄雪兰，“超声诊断子宫内膜病变的价值”实用医技杂志，12(7)：1705-1706，2005．
[45]吴丽芹，王秘林，赵淑文，“诊断子宫内膜病变三种方法比较”中华医学研究杂志，6(8)：892-894，2006．
[46]图像来源于：http://www.adoop.cn/medical-insurance/show-28932-1.html
[47]梁凤伟，朱志俏，巫晓华，等．“妊娠子宫破裂的超声诊断价值”中国超声诊断杂志，6(10)：769-770，2005．
[48]图像来源于：http://www.adoop.cn/medical-insurance/show-30103-1.html
[49]张媛香，“子宫内胚胎组织残留超声诊断价值”浙江预防医学，18(2)：47-47，2006．
[50]图像来源于：http://www.zhihuiyixue.com/bbs/post/view?bid=109&id=34629
[51]侯甫晓，岳学文，“子宫颈癌超声检查的价值”中国超声诊断杂志，4(7)：544-545，2003．
[52]图像来源于：http://www.usroom.net/article.asp?id=705
[53]辛德荣，“B超在宫内节育器诊断中的应用”天津医科大学学报，10(3)：471-473，2004．
[54]辛德荣，“超声在带器妊娠诊断中的应用”天津医科大学学报，10(1)：90-91，2004．
[55]宋戈萍，“宫内节育器的超声诊断”中国计划生育学杂志，49(5)：231-234，1999．
[56]魏溶，李涛，“实时超声监测宫内节育器的临床价值”河北医科大学学报，18(2)：85-86，1997．
[57]图像来源于：http://www.k120.com/cstech/image/05-753.html
[58]图像来源于：http://www.usroom.net/HTDOCS/XXLR1.ASP?ID=5430
[59]张儒秀，石俊，“超声在产前诊断中的应用”中国实用医药，3(17)：127-128，2008．
[60]曹海根，王金瑞，“实用腹部超声诊断学”北京：人民卫生出版社，774-788，1994．
[61]图像来源于：http://www.adoop.cn/medical-insurance/show-35972-1.html
[62]莫畏，“胎儿脐带缠绕的超声诊断价值”医学综述，14(13)：2075-2076，2008．
[63]李胜利，“胎儿畸形的产前超声检查”中华医学超声杂志(电子版)，2(1)：5-7，2005．
[64]银云燕，银云琳，兰桂珍，等．“先天性胎儿畸形的超声诊断分析”中国超声诊断杂志，4(10)：788-791，2003．
[65]B Potocnik, D Zazula, "Automated analysis of a sequence of ovarian ultrasound images. Part Ⅰ: segmentation of single 2D images" Image and Vision Computing, 20: 217-225, 2002.
[66]B Potocnik, D Zazula, "Automated analysis of a sequence of ovarian ultrasound images. Part Ⅱ: prediction-based object recognition from a sequence of images" Image and Vision Computing, 20: 227-235, 2002.
[67]B Potocnik, D Zazula, "Improved prediction-based ovarian follicle detection from a sequence of ultrasound images" Computer Methods and Programs in Biomedicine, 70:199-213, 2003.
[68]C Lu, T Van Gestel, JAK Suykens, etc. "Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines" Artificial Intelligence in Medicine, 28: 281-306, 2003.
[69]吴凯凯，汪源源，钱斌，“基于超声图像特征区分子宫肌瘤和腺肌病”中国生物医学工程学报，26(4)：537-581，2007．
[70]J Zhang, Y Wang, Y Dong, etc. "Ultrasonographic feature selection and pattern classification for cervical lymph nodes using support vector machines" Computer Methods and Programs in Biomedicine, 88: 75-84, 2007.
[71]SVB Jardim, MAT Figueiredo, "Automatic contour estimation in fetal ultrasound images" ICIP2003, 2: 1065-1068, 2003.
[72]W Lu, J Tan, R Floyd, "Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform" Ultrasound in Medicine & Biology, 31(7): 929-936, 2005.
[73]W Lu, J Tan, "Detection of incomplete ellipse in images with strong noise by iterative randomized Hough transform (IRHT)" Pattern Recognition, 41:1268-1279, 2008.
[74]余锦华，汪源源，陈萍，etc．“胎儿超声图像分割及自动径线测量”中国生物医学工程学报，26(6)：867-874：2007．
[75]J Yu, Y Wang, P Chen, etc. "Fetal abdominal contour extraction and measurement in ultrasound images" Ultrasound in Medicine & Biology, 34(2): 169-182, 2008.
[76]KN Bhanu Prakash, AG Ramakrishman, S Suresh, etc. "Fetal lung maturity analysis using ultrasound image features" IEEE Trans. on Information Technology in Biomedicine, 6(1): 38-45: 2002.
[77]吴君，杨太珠，林江莉，等．“基于人工神经网络的足月胎儿体重预测方法”生物医学工程学杂志，22(5)：922-925，2005．
[78]马翔，汪源源，王威琪，等．“图像特征参量分析方法及其在胎儿分级中的应用”航天医学与医学工程，14(5)：336-340：2001．
[79]NV Chawla, N Japkowicz, A Kolcz, "Editorial: Special Issue on Learning from Imbalanced Data Sets," SIGKDD Explorations, 6(1), 1-6, 2004.
[80]I Guyon, A Elisseeff, "An Introduction to Variable and Feature Selection" Journal of Machine Learning Research, 3:1157-1182, 2003.
[81]C Blake, C Merz, "UCI Repository of Machine Learning Databases," 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[1] R Barandela, JS Sanchez, V Garcia, E Rangel, "Strategies for Learning in Class Imbalance Problems," Pattern Recognition, 36, 849-851, 2003.
[2] A Kolcz, A Chowdhury, J Alspector, "Data duplication: an imbalance problem?" in Proc. of the ICMU03 Workshop on Learning from Imbalanced Datasets, 2003.
[3] C Phua, D Alahakoon, V Lee, "Minority Report in Fraud Detection: Classification of Skewed Data" SIGKDD Explorations, 6(1), 50-59, 2004.
[4] NV Chawla, "C4.5 and Imbalanced Data sets: Investigating the effect of sampling method, probabilistic estimate, and decision tree structure" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[5] B Raskutti, A Kowalczyk, "Extreme Re-balancing for SVMs: a case study" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[6] NV Chawla, N Japkowicz, A Kolcz, "Editorial: Special Issue on Learning from Imbalanced Data Sets," SIGKDD Explorations, 6(1), 1-6, 2004.
[7] N Japkowicz, "Class Imbalance: Are We Focusing on the Right Issue?" in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[8] T Jo, N Japkowicz, "Class Imbalance versus Small Disjuncts," SIGKDD Explorations, 6(1), 40-49, 2004.
[9] GM Weiss, "Mining with Rarity: A Unifying Framework," SIGKDD Explorations, 6(1), 7-19, 2004.
[10] MA Maloof, "Learning When Data Sets are Imbalanced and When Costs are Unequal and Unknown," in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[11] G Wu, EY Chang, "Class-Boundary Alignment for Imbalanced Dataset Learning," in Proc. of the ICML'03 Workshop on Learning from lmbalanced Datasets, 2003.
[12] C Drummond, RC Holte, "C4.5, Class Imbalance, and Cost Sensitivity: Why Under-sampling Beats Over-sampling," in Proc. of the ICML'03 Workshop on Learning from Imbalanced Datasets, 2003.
[13] GEAPA Batista, RC Prati, MC Monard, "A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data," SIGKDD Explorations, 6(1), 20-29, 2004.
[14] NV Chawla, KW Bowyer, LO Hall, W.P. Kegelmeyer, "SMOTE: Synthetic Minority Oversampling Technique," Journal of Artificial Intelligence Research, 16, 321-257, 2002.
[15] JCB Melo, GDC Cavalcanti, KS Guimaraes, "PCA feature extraction for protein structure prediction" Neural Networks, 4, 2952-2957, 2003.
[16] J Cowe, DH Evans, "Automatic detection of emboli in the TCD RF signal using principle component analysis" Ultrasound of Medical & Biology, 32, 1853-1867,2006.
[17] HH Goldstine, FJ Murray, J von Neumann, "The Jacobi Method for Real Symmetric Matrices" Journal of the ACM, 6(1), 59-96, 1959.
[18] M Kubat, S Matwin, "Addressing the Curse of Imbalanced Training Sets: One-sided Selection," in Proc. of the 1CML, 179-186, 1997.
[19] YL Murphey, H Guo, "Neural Learning from Unbalanced Data." Applied Intelligence, 21, 117-128,2004.
[20] C Blake, C Merz, "UCI Repository of Machine Learning Databases," 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[21] AR Webb, Statistical Pattern Recognition, John Wiley & Sons, 2002.
[1] M Pechenizkiy, A Tsymbal, S Puuronen, O Pechenizkiy, "Class Noise and Supervised Learning in Medical Domains: The Effect of Feature Extraction", 19~(th) IEEE International Symposium on Computer-Based Medical Systems, 2006.
[2] XQ Zhu, XD Wu, QJ Chen, "Bridging Local and Global Data Cleansing: Identifying Class Noise in Large, Distributed Data Datasets" Data Mining and Knowledge Discovery, 12: 275-308, 2006.
[3] H Xiong, G Pandey, M Steinbach, V Kumar, "Enhancing Data Analysis with Noise Removal" IEEE Transactions on Knowledge and Data Engineering, Vol. 18, No. 3, 2006.
[4] JR Quinlan, "Induction of Decisions Trees" Machine Learning, 1: 81-106, 1986.
[5] YL Li, L Wessels, M Reinders, "Class-noise Tolerant Classification Based on a Probabilistic Noise Model" Twelfth Annual Conf. of the Advanced School for Computing and Imaging, 2006.
[6] XQ Zhu, XD Wu, "Class Noise vs. Attribute Noise: A Quantitative Study of Their Impacts" Artificial Intelligence Review, 22: 177-210, 2004.
[7] XQ Zhu, XD Wu, Y Yang, "Error Detection and Impact-sensitive Instance Ranking in Noisy Datasets" AAAI-2004, San Joise, CA.
[8] Y Sakakibara, "Noise-tolerant Occam Algorithms and Their Applications to Learning Decision Trees", Machine Learning, 11: 37-62, 1993.
[9] J Mingers, "An Empirical Comparison of Pruning Methods for Decision Tree Induction" Machine Learning, 4-2: 227-243, 1989.
[10] D Gamberger, N Lavrac, S Dzeroski, "Noise Detection and Elimination in Data Preprocessing: Experiments in Medical Domains" Applied Artificial Intelligence, 14: 205-223, 2000.
[11] CE Brodley, MA Friedl, "Identifying Mislabeled Training Data" Journal of Artificial Intelligence Research, 11,131-167, 1999.
[12] J Sander, M Ester, HP Kriegel, X Xu, "Density-based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications" Data Mining and Knowledge Discovery, Vol. 2, No. 2, 1998.
[13] D Wilson, T Martinez, "Reduction Techniques for Exemplar-Based Learning Algorithms" Machine Learning, 1998.
[14] I Tomek, "Two Modifications of CNN" IEEE Transactions on Systems, Man, and Communications SMC-6, 769-772, 1976.
[15]D Wilson, "Asymptotic Properties of Nearest Neighbor Rules Using Edited Data" IEEE Transactions on Systems, Man, and Communications 2: 3, 408-421, 1972.
[16]Occam's Razor: http://en.wikipedia.org/wiki/Occam's_Razor
[17]J Serra, "Image Analysis and Mathematic Morphology" Academic Press, New York, 1982.
[18]RC Gonzalez, RE Woods, "Digital Image Processing, 2E" Prentice Hall, 2002.
[19]YL Murphey, H Guo, "Neural Learning from Unbalanced Data" Applied Intelligence, 21,117-128,2004.
[20]C Blake, C Merz, UCI Repository of Machine Learning Databases, 1998. http://www.ics.uci.edu/-mlearn/MLRepository.html
[1] M Pechenizkiy, A Tsymbai, S Puuronen, etc, "Class noise and supervised learning in medical domains: the effect of feature extraction" 19th IEEE International Symposium on Computer-Based Medical Systems, 2006.
[2] XQ Zhu, XD Wu, QJ Chen, "Bridging local and global data cleansing: identifying class noise in large, distributed data datasets" Data Mining and Knowledge Discovery, 12: 275-308, 2006.
[3] R Sivaramakrishna, K Powell, M Lieber, etc, "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[4] I Guler, E Ubeyli, "Feature saliency using signal-to-noise ratios in automated diagnositic systems developed for Doppler ultrasound signals" Engineering Applications of Artificial Intelligence, 19: 53-63, 2006.
[5] K Bhanu Prakash, A Ramakrishnan, S Suresh, etc, "Fetal lung maturity analysis using ultrasound image features" IEEE Trans On Information Technology in Biomedicine, 6: 38-45, 2002.
[6] WQ Zhang, "The report about the sampling investigation of the effects of the pregnancy prevention using IUD in China, by the organizations of Chinese population and family planning" 2005.
[7] 崔满华，安启哲，“宫内节育器的避孕原理”中国实用妇科与产科杂志，11(4)：209-210，1995．
[8] 毛勇，周晓波，夏铮，等．“特征选择算法研究综述”模式识别与人工智能，20(2)：211-218，2007．
[9] I Guyon, "An introduction to variable and feature selection" Journal of Machine Learning Research, 3: 1157-1182, 2003.
[10] R Kohavi, GH John, "Wrappers for feature subset selection" Artificial Intelligence, 97: 273-324, 1997.
[11] J Kittler, F Roli, "Multiple Classifier Systems, First International Workshop, MCS 2000, Cagliari, Italy, June 21-23, 2000, Proceedings" LNCS 1857, Springer, 2000, ISBN 3-540-67704-6.
[12] 王正群，孙兴华，杨静宇，“多分类器组合研究”计算机工程与应用，20：84-86，2002．
[1] Intrauterine Device, http://en.wikipedia.org/wiki/Intrauterine_device
[2] What is an IUD? http://www.fwhc.org/birth-control/iudinfo.htm
[3] 张俊英，“关于宫内节育器的探讨”实用医技杂志，15(16)：2135-2137，2008．
[4] 崔满华，安启哲，“宫内节育器的避孕原理”中国实用妇科与产科杂志，11(4)：209-210，1995．
[5] 顾红媛，“浅析宫内节育器避孕的原理及放置”中国临床医药研究杂志，144：15654-15654，2005．
[6] 谢淑雯，“4种活性宫内节育器放置7年的临床评价”现代医学卫生，21(6)：645-647，2005．
[7] 张维，“宫内节育器的进展与临床应用”常熟高专学报，16(4)：106-106，2002．
[8] 吴周光，倪雪漫，孙家庆，“宫腔内IUD的正常异常超声表现”实用妇产科杂志，8(3)：154，1992．
[9] 辛德荣，“B超在宫内节育器诊断中的应用”天津医科大学学报，10(3)：471-473，2004．
[10] 中华人民共和国国务院令(第309号)“计划生育技术服务管理条例”发布日期：2001-07-09．
[11]盘点宫内节育器的12个问题，中国国家人口和计划生育委员会网站 http://www.chinapop.gov.cn/kpyd/byjy/200408/t20040823_148960.htm
[12]节育提示：宫内节育器不是终身环，中国国家人口和计划生育委员会网站 http://www.chinapop.gov.cn/kpyd/byjy/200709/t20070927_48757.htm
[13]K Bhanu Prakash, A Ramakrishnan, S Suresh, et al. "Fetal lung maturity analysis using ultrasound image features" IEEE Trans Information Technology in Biomedicine, 6(1): 38-45,2002.
[14]M Strzelecki, A Materka, J Drozdz, et al. "Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms" Computerized Medical Imaging and Graphics, 30:95-107, 2006.
[15]Y Zhu, S Williams, R Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Image Analysis, 10:178-199, 2006.
[16] 吴君，杨太珠，林江莉，等．“基于人工神经网络的足月胎儿体重预测方法”生物医学工程学杂志，22(5)：922-925，2005．
[17]林江莉，汪小毅，李德玉，等．“脂肪肝B超图像特征提取研究”四川大学学报，37(1)：130-134．2005．
[18]M Karaman, M Kutay, G Bozdagi, "An adaptive speckle suppression filter for medial ultrasonic imaging" IEEE Trans Med Imaging, 14(2): 283-292, 1995.
[19]CHEN Yan, YIN Ru-ming, P Flynn, et al. "Aggressive region growing for speckle reduction in ultrasound images" Pattern Recognition Letters, 24: 677-691, 2003.
[20]T Loupas, WN McDicken, PL Allan, "Adaptive weighted median filter for speckle suppression in medical ultrasonic images" IEEE Trans Circuit System, 36:129-135:1989.
[21]R Duda, P Hart, D Stork, "Pattern Recognition" New York: John Wiley & Sons, 2001.
[22]I Guyon, A Elisseeff, "An introduction to variable and feature selection" Journal of Machine Learning Research, 3:1157-1182, 2003.
[1] 潘嘉，“韩国、印度和中国台湾治理出生性别比失衡的经验与启示”中国党政干部论坛，9：17-18．2007．
[2] Population Census Office under Chinese State Council, "Zhongguo 2000 Nian Renkou Pucha Ziliao (Tabulation on the 2000 Population Census of the People's Republic of China) (In Chinese)" Beijing: China Statistics Press, 2002.
[3] 王君平，徐静，“中国出生性别比失衡最严重”中外健康文摘，8：58-58：2007．
[4] Y Qi, WM Mason, "Prenatal sex-selective abortion and high sex ratio at birth in rural china: A case study in Henan province. On-Line Working Paper Series 2005" http://repositories.cdlib.org/ccpr/olwp/CCPR-057-05.
[5] S Li, "Imbalanced sex ratio at birth and comprehensive intervention in China" The 4~(th) Asia Pacific Conference on Reproductive and Sexual Health and Rights, Oct 29-31 2007, Hyderabad, India, http://www.unfpa.org/gender/docs/studies/china.pdf.
[6] 中华人民共和国国家计划生育委员会第8号部长令“关于禁止非医学需要的胎儿性别鉴定和选择性别的人工终止妊娠的规定”实施时间：2003-01-01．
[7] 郑幼卿，洪建章，丁鸿儒，“福建省打击非法胎儿性别鉴定、非法终止妊娠行动中存在的问题及对策”中国卫生监督杂志，14(4)：304-306，2007．
[8] 周强，“一种对B超胎儿性别鉴别进行记录的方法”专利申请号：200510090509．0
[9] TA Scholly, JH Sutphen, SC Mackey, etc. "Sonographic determination of fetal gender"American Journal of Roentgenology, 135:1161-1165, 1980.
[10]C Lu, T van Gestel, JAK Suykens, etc. "Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines" Artificial Intelligence in Medicine, 28:281-306, 2003.
[11]D Smutek, T Tjahjadi, R Sara, etc. "Image texture analysis of sonograms in chronic inflammations of thyroid gland" Research Report CTU-CMP-2001-15, April 2001, Czech Technical University, Prague, Czech Republic, ISSN 1213-2365.ftp://cmp.felk.evut.cz/pub/cmp/articles/sara/Smutek-TR-2001-15.pdf
[12]DG Vince, KJ Dixon, RM Cothren, etc. "Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images" Computerized Medical Imaging and Graphics, 24: 221-229, 2000.
[13]Y Zhu, S Williams, Zwiggelaar, "Computer technology in detection and staging of prostate carcinoma: A review" Medical Image Analysis, 10:178-199, 2006.
[14] D Buller, A Buller, PR Innocent, etc. "Determining and classifying the region of interest in ultrasonic images of the breast using neural networks" Artificial Intelligence in Medicine, 8:53-66, 1996.
[15]DR Chen, RF Chang, CJ Chen, etc. "Classification of breast ultrasound images using fractal feature" Journal of Clinical Imaging, 29: 235-245, 2005.
[16]N Piliouras, I Kalatzis, N Dimitropoulos, etc. "Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound" Computerized Medical Imaging and Graphics, 28: 247-255, 2004.
[17]R Sivaramakrishna, KA Powell, ML Leiber, etc. "Texture analysis of lesions in breast ultrasound images" Computerized Medical Imaging and Graphics, 26: 303-307, 2002.
[18]S Jardim, M Figueiredo, "Segmentation of fetal ultrasound images" Ultrasound of Medicine & Biology, 31(2): 243-250,2005.
[19]W Lu, J Tan, R Floyd, "Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform" Ultrasound of Medicine & Biology, 31(7): 929-936, 2005.
[20]T Kadonaga, K Abe, "Comparison of methods for detecting corner points from digital curves" Proceedings of the First International Workshop on Graphic Recognition. Aug 10-11 1995, University Park, PA, USA: 23-34.