基于超声图像的前列腺病变计算机辅助诊断
|
摘要
前列腺癌是一种中老年男性的常见疾病,并且只有在癌症初期诊断出来才能够有效提高患者的生存率,通常使用直肠超声穿刺技术来进行前列腺疾病的早期检查。大量的研究表明,使用计算机辅助诊断技术(CAD)可以进一步提高病理诊断的准确性。前列腺病变CAD系统通常使用病变区域的形态和灰度纹理统计特征来对病变区域进行分类判别。由于超声图像对比度较低,仅使用这些特征很难有效地区分病变区域。因此本文研究超声图像的病变区域在不同尺度下和不同频率域中所具有的不同特征,并将它们有效地用于前列腺病变的辅助诊断。
本文所完成的主要研究和创新点描述如下:
(1)对直肠超声(TRUS)图像进行预处理。针对超声图像中斑点噪声较为严重的特点,本文提出了一种基于改进的各向异性扩散方程的自适应斑点抑制算法,通过使用区域中值代替原像素点和加入对角梯度算子,有效的抑制了斑点噪声,同时也增强了细节信息;加入了保真项,使得算法在有效地抑制斑点噪声的同时4还具有良好的鲁棒性,同时能够有效保持边界几何信息,解决了传统算法受迭代次数影响较大的问题。
(2)对前列腺超声图像进行分割,以得到前列腺的边界轮廓。首先提出了一种基于改进测地线模型的全自动前列腺边界轮廓分割算法,将径向浅浮槽算法和满水法填充算法结合获得超声图像中前列腺的大致目标轮廓,来作为主动轮廓模型的初始水平集,并且构造基于区域信息的符号压力函数来代替边界停止函数,同时加入了基于边界梯度信息的能量项,能够有效地克服弱边界的问题。该算法用二值水平集实现,使得算法的稳定性大为提高,并且计算量大大降低。针对对比度较差的超声图像,又提出了一种基于改进测地线主动轮廓模型的半自动分割算法,该算法使用手工勾画的粗略边界作为初始水平集,使用变分法,消除了测地线模型中的重初始化过程,使得算法运算速度有了较大的提高,根据区域先验知识改进了测地线的边界停止函数,能够有效避免边界泄漏问题,并使用最小方差来提高分割算法的精度。
(3)对分割后的图像进行前列腺病变特征参数的提取。不同于以往的研究仅仅使用灰度共生矩阵(GLCM)特征或者灰度级差矢量(GLDV)特征来对病变进行识别,本文所提取的特征参数包括小波域统计特征参数、各种尺度频率域特征参数、梯度图像特征参数等。由于特征参数之间存在一定的冗余性,为了有效地分析和利用所提取出的特征,使用了特征维度约减算法来选择最优的特征参数子集。
(4)根据所提取的特征参数来对前列腺病变区域的良恶性进行分类判断。使用SVM算法和AdaBoost算法对所提取出来的病变区域特征参数进行分类,并分析对比了不同特征参数对分类器判别结果的影响和不同分类器之间的分类性能,以寻找最优的组合。
按照上述四个步骤,本文对255幅前列腺直肠超声图像(其中125幅为恶性病变图像,130幅为良性病变图像)进行实验。实验结果表明,联合使用本文所提取出来的特征参数集的辅助诊断系统,性能明显优于只使用灰度级差矢量特征参数的系统,这表明本文所提出的基于直肠超声图像的系统对前列腺病变区域的良恶性具有较好的区分能力,能够为医生的临床诊断提供辅助依据。
Prostate cancer is one of the common diagnosed malignancies in middle-aged and elder men,and the survival rate of the patients can only be enchanced by detection in the early stage of cancer.Nowadays,TransRectal Ultrasound(TRUS) puncture technique is one of the most frequently used methods for the early detection of prostate cancer.Many researches show that the accuracy of the pathology detection can be further enhanced by using computer aided diagnosis(CAD) technology.The prostate cancer CAD system usually performs the diagnosis based on the morphology and grayscale texture statistical features of the pathological areas.However,the CAD system only utilizes the aforementioned features can't differentiate the pathology areas effectively because of the poor contrast in the TRUS images.Therefore,this dissertation studies the different characteristics of the pathological areas in the different scales and frequency domains to assist the diagnosis of prostate cancers effectively.
The main research work and contributions of this dissertation can be summarized as follows:
(1) Preprocessing the TRUS images.Aiming at the characteristics that the ultrasound images have a lot of speckle noises,an improved anisotropic diffusion adaptive speckle reduction algorithm was proposed.The algorithm used the medians of regions to replace the original pixels and added the diagonal gradient term,which would suppress the speckle noises effectively and enhance the detail information.The algorithm combined a fidelity term,which made the algorithm suppress the speckle noise effectively and more robust,moreover,the algorithm could maintain the boundary geometry information effectively and solve the problem that the results of the conventional algorithms were affected by the iterative numbers greatly.
(2) Segmenting the TRUS images to get the prostate boundary.This dissertation proposed an automatic prostate boundary segmentation algorithm based on the improved geodesic active contour.Firstly,a coarse contour could be gotten by combining radial bas-relief and region fill algorithm to the TRUS images,the contour could be used as the initial contour for the active contour model.Then the problem of weak edges could also be efficiently solved by presenting a new region-based signed pressure forces function to replace the edge stopping function and incorporating an energy term based on boundary gradient information.The algorithm was implemented by binary level set function,which reduced the expensive computational cost of re-initialization of the conventional level set and enhanced the stability of the algorithm.A semi-automatic segmentation algorithm based on improved geodesic active contour model was also proposed to deal with the TRUS image with poor contrast.The algorithm used the manual-drawing boundary as the initial level set.The need of the costly re-initialization procedure is completely eliminated by using variational formation,thus increased the speed of the evolvement.The edge stopping function in the geodesic active contour model was revised by incorporating a priori area information to avoid the problem of edge leaking.The accuracy of the algorithm was improved by the minimal variance term.
(3) Extracting the characteristic parameters of the prostate pathology from the segmented images.Other than the past studies only extracted the gray level coocurrence matrix(GLCM) and gray level difference vector(GLDV) features,the dissertation extracted parameters including wavelet statistical characteristics, characteristics from all scale-frequency domains,and characteristics from gradient images.There existed the redundancy among the extracted feature set,so the study used feature dimension reduction method to select the optimal feature subset for the sake of utilizing the extracted feature sets efficiently.
(4) Utilizing the feature subset extracted in the previous step to aid the classification of prostate pathological areas.The dissertation used SVM and AdaBoost to classify the extracted characteristics parameters of pathological areas.The study compared the affect of different characteristic parameters to the results of the classifier and the classification performance between the different classifiers,through which to look for the optimal combination of characteristic parameters and classifier.
Based on the aforementioned four steps,255 prostate TRUS images including 125 benign pathological areas and 130 malignant ones were studied in the dissertation, the experiment results showed that the performance of CAD system which used the characteristic parameters including wavelet statistical characteristics,characteristics from all scale-frequency domains,and characteristics from gradient images was much better than the system which only used the GLCM or GLDV characteristics. Therefore,this indicated that the system proposed by the dissertation performed well in the classification of malignant and benign between the prostate pathological areas, and it could be used as a supplementary basis for the clinical diagnosis of the prostate cancers.
本文所完成的主要研究和创新点描述如下:
(1)对直肠超声(TRUS)图像进行预处理。针对超声图像中斑点噪声较为严重的特点,本文提出了一种基于改进的各向异性扩散方程的自适应斑点抑制算法,通过使用区域中值代替原像素点和加入对角梯度算子,有效的抑制了斑点噪声,同时也增强了细节信息;加入了保真项,使得算法在有效地抑制斑点噪声的同时4还具有良好的鲁棒性,同时能够有效保持边界几何信息,解决了传统算法受迭代次数影响较大的问题。
(2)对前列腺超声图像进行分割,以得到前列腺的边界轮廓。首先提出了一种基于改进测地线模型的全自动前列腺边界轮廓分割算法,将径向浅浮槽算法和满水法填充算法结合获得超声图像中前列腺的大致目标轮廓,来作为主动轮廓模型的初始水平集,并且构造基于区域信息的符号压力函数来代替边界停止函数,同时加入了基于边界梯度信息的能量项,能够有效地克服弱边界的问题。该算法用二值水平集实现,使得算法的稳定性大为提高,并且计算量大大降低。针对对比度较差的超声图像,又提出了一种基于改进测地线主动轮廓模型的半自动分割算法,该算法使用手工勾画的粗略边界作为初始水平集,使用变分法,消除了测地线模型中的重初始化过程,使得算法运算速度有了较大的提高,根据区域先验知识改进了测地线的边界停止函数,能够有效避免边界泄漏问题,并使用最小方差来提高分割算法的精度。
(3)对分割后的图像进行前列腺病变特征参数的提取。不同于以往的研究仅仅使用灰度共生矩阵(GLCM)特征或者灰度级差矢量(GLDV)特征来对病变进行识别,本文所提取的特征参数包括小波域统计特征参数、各种尺度频率域特征参数、梯度图像特征参数等。由于特征参数之间存在一定的冗余性,为了有效地分析和利用所提取出的特征,使用了特征维度约减算法来选择最优的特征参数子集。
(4)根据所提取的特征参数来对前列腺病变区域的良恶性进行分类判断。使用SVM算法和AdaBoost算法对所提取出来的病变区域特征参数进行分类,并分析对比了不同特征参数对分类器判别结果的影响和不同分类器之间的分类性能,以寻找最优的组合。
按照上述四个步骤,本文对255幅前列腺直肠超声图像(其中125幅为恶性病变图像,130幅为良性病变图像)进行实验。实验结果表明,联合使用本文所提取出来的特征参数集的辅助诊断系统,性能明显优于只使用灰度级差矢量特征参数的系统,这表明本文所提出的基于直肠超声图像的系统对前列腺病变区域的良恶性具有较好的区分能力,能够为医生的临床诊断提供辅助依据。
Prostate cancer is one of the common diagnosed malignancies in middle-aged and elder men,and the survival rate of the patients can only be enchanced by detection in the early stage of cancer.Nowadays,TransRectal Ultrasound(TRUS) puncture technique is one of the most frequently used methods for the early detection of prostate cancer.Many researches show that the accuracy of the pathology detection can be further enhanced by using computer aided diagnosis(CAD) technology.The prostate cancer CAD system usually performs the diagnosis based on the morphology and grayscale texture statistical features of the pathological areas.However,the CAD system only utilizes the aforementioned features can't differentiate the pathology areas effectively because of the poor contrast in the TRUS images.Therefore,this dissertation studies the different characteristics of the pathological areas in the different scales and frequency domains to assist the diagnosis of prostate cancers effectively.
The main research work and contributions of this dissertation can be summarized as follows:
(1) Preprocessing the TRUS images.Aiming at the characteristics that the ultrasound images have a lot of speckle noises,an improved anisotropic diffusion adaptive speckle reduction algorithm was proposed.The algorithm used the medians of regions to replace the original pixels and added the diagonal gradient term,which would suppress the speckle noises effectively and enhance the detail information.The algorithm combined a fidelity term,which made the algorithm suppress the speckle noise effectively and more robust,moreover,the algorithm could maintain the boundary geometry information effectively and solve the problem that the results of the conventional algorithms were affected by the iterative numbers greatly.
(2) Segmenting the TRUS images to get the prostate boundary.This dissertation proposed an automatic prostate boundary segmentation algorithm based on the improved geodesic active contour.Firstly,a coarse contour could be gotten by combining radial bas-relief and region fill algorithm to the TRUS images,the contour could be used as the initial contour for the active contour model.Then the problem of weak edges could also be efficiently solved by presenting a new region-based signed pressure forces function to replace the edge stopping function and incorporating an energy term based on boundary gradient information.The algorithm was implemented by binary level set function,which reduced the expensive computational cost of re-initialization of the conventional level set and enhanced the stability of the algorithm.A semi-automatic segmentation algorithm based on improved geodesic active contour model was also proposed to deal with the TRUS image with poor contrast.The algorithm used the manual-drawing boundary as the initial level set.The need of the costly re-initialization procedure is completely eliminated by using variational formation,thus increased the speed of the evolvement.The edge stopping function in the geodesic active contour model was revised by incorporating a priori area information to avoid the problem of edge leaking.The accuracy of the algorithm was improved by the minimal variance term.
(3) Extracting the characteristic parameters of the prostate pathology from the segmented images.Other than the past studies only extracted the gray level coocurrence matrix(GLCM) and gray level difference vector(GLDV) features,the dissertation extracted parameters including wavelet statistical characteristics, characteristics from all scale-frequency domains,and characteristics from gradient images.There existed the redundancy among the extracted feature set,so the study used feature dimension reduction method to select the optimal feature subset for the sake of utilizing the extracted feature sets efficiently.
(4) Utilizing the feature subset extracted in the previous step to aid the classification of prostate pathological areas.The dissertation used SVM and AdaBoost to classify the extracted characteristics parameters of pathological areas.The study compared the affect of different characteristic parameters to the results of the classifier and the classification performance between the different classifiers,through which to look for the optimal combination of characteristic parameters and classifier.
Based on the aforementioned four steps,255 prostate TRUS images including 125 benign pathological areas and 130 malignant ones were studied in the dissertation, the experiment results showed that the performance of CAD system which used the characteristic parameters including wavelet statistical characteristics,characteristics from all scale-frequency domains,and characteristics from gradient images was much better than the system which only used the GLCM or GLDV characteristics. Therefore,this indicated that the system proposed by the dissertation performed well in the classification of malignant and benign between the prostate pathological areas, and it could be used as a supplementary basis for the clinical diagnosis of the prostate cancers.
引文
陈亚虎,周永昌,黄慕民,等.2001.彩超直方图估测前列腺血流的价值[J].中国超声医学杂志,17(5):328-330.
陈燕龙,钟碧良.2008.基于HMM和微粒群优化算法的表情识别[J].计算机工程,34(13):190-192.
崔伟东,周志华,李星.2000。神经网络VC维计算研究[J].计算机科学,27(7):59-62.
顾方六.2000.我国良性前列腺增生和前列腺发病调查[J].北京医科大学学报,32(1):30-33.
郭圣文,李松毅,罗立民.2003.一种基于四阶各向异性微分的抑噪与边缘增强方法[J].中国图像图形学报A辑,8(z1):492-495.
哈章,李传富,王金萍,等.2008.一种新型的医学图像分割评价方法[J].北京生物医学工程,27(4):385-388.
候格贤,毕笃彦,吴成柯.2000.图像分割质量评价方法研究[J].中国图像图形学报,5(1):39-43.
江锦雄,林洁明,韩莉,等.2008。PSA测定结合经直肠彩色多普勒超声检查在早期前列腺癌诊断的临床意义[J].广州医药,39(5):52-53.
蓝博文,王颖,谭理连,等.2000.前列腺癌的CT诊断与鉴别诊断[J].中华放射学杂志,12:852-854.
李培华,张田文.2000.主动轮廓模型(蛇模型)综述[J].软件学报,11(6):751-757.
李淑清,孔祥田,山刚志,等.2001.前列腺癌的超声表现与组织结构[J].中国超声医学杂志,17(5):334-336。
李松年.2002.中国影像医学.泌尿生殖系统卷[M].北京:人民卫生出版社,325-326.
李亚军,白人驹,高硕.2006.PET在前列腺癌中的应用[J].国际放射医学核医学杂志,30(5):283-286.
刘春明,张相芬,陈武凡.2006.基于小波的医学超声图像斑点噪声抑制方法[J].中国医学物理学杂志,23(5):364-367.
罗惠韬,章毓晋.1997.一个图像分割评价实例及讨论[J].数据采集与处理,12(1):18-22.
那彦群,孙则禹,叶章群,等.2006.中国泌尿外科疾病诊断治疗指南[M].北京:人民卫生出版社,1:103-104.
彭进业,郝重阳,齐华,等.2007.基于多尺度梯度矢量场GAC模型的MR 医学图像分割[J].中国图象图形学报,12(7):1214-1217.
瞿连喜,王翔,方祖军.2001.经直肠B超诊断前列腺癌[J].中国癌症杂志,11(2):153.
孙军,陈锋,郑凯尔.2001.ROC曲线分析在放射学中的应用[J].中华放射学杂志,35(8):574-577.
孙蕾,周明全,耿国华.2005.基于医学图像的数学规划支持向量机[J].计算机工程,31(19):4-6.
孙颖浩.2004.我国前列腺癌的研究现状[J].中华泌尿外科杂志,25:77-80.
唐杰,李颂,李俊来,等.2002.经直肠超声引导下的穿刺活检诊断前列腺癌189例[J].中华超声影像学杂志,11:400-402.
陶榆.1999.外科病理学[M].湖北:湖北科学技术出版社,734-741.
王玲,董昌元,贺伟,等.2001.经直肠彩色多普勒超声对前列腺增生和前列腺癌的血流动力学研究[J].中国超声医学杂志,17(2):144-147.
汪天富,李德玉,郑昌琼,等.2001.超声医学图像分割的混合神经网络方法[J].航天医学与医学工程,14(2):84-87.
许建华,张学工译.2004.统计学习理论[M].北京:电子工业出版社,364-384.
严加勇,庄天戈.2003.医学超声图像分割技术的研究及发展趋势[J].北京生物医学工程,22(1):67-71.
延伟东.2007.图像特征提取方法的研究[D],西安:西北工业大学.
杨杰,陈晓云.2007.图像分类方法比较研究[J].微计算机应用,28(6):627-632.
叶定伟.2006.前列腺癌的流行病学和中国的发展趋势[J].中华外科杂志.44(6):362-364.
余锦华,汪源源,施心陵.2007.基于EM算法参数估计的各向异性扩散超声图像的去噪[J].航天医学与医学工程,20(3):198-204.
张开华,周文罡,张振等.2008.一种改进的C.V主动轮廓模型[J].光电工程,35(12):112-116.
张晓龙,任芳.2009.支持向量机与AdaBoost的结合算法研究[J].计算机应用研究,26(1):77-79.
章一士,韩振奎.2007.前列腺特异抗原在前列腺癌诊断中的价值[J].延安大学学报(医学科学版),5(4):26-27.
张勇,王瓛,郭秀花.2008.基于医学图像纹理特征的疾病诊断方法及其应 用现状[J].北京生物医学工程,27(4):444-447.
章毓晋.2001.图像分割[M].北京:科学出版社.
赵春晖,孙圣和.1998.一种全方位多尺度形态滤波方法[J].模式识别与人工智能,11(1):101-104.
周秦武,卞正中,张大龙.2003.基于小波的超声斑点噪声抑制与对比度增强[J].声学学报,4(28):381-384.
周永昌,郭万学.1998.超声医学[M].北京:北京科学技术文献出版社,1070-1080.
Aksel A,Gilliam AD,Hossack JA,et al.2006.Speckle reducing anisotropic diffusion for echocardiography[C].The Fortieth Asilomar Conference on Signals,Systems and Computers,1988-1992.
Altman AL,Resnick MI,2001,Ultrasonographically guided biopsy of the prostate gland[J].J Ultrasound Med,20(2):159-167.
Anthony KW Sum,Paul YS Cheung.2007.Stabilized anisotropic diffusions[C]IEEE Inter Conference on Acoustics,Speech,and Signal Processing,709-712.
Archie A,Alexander MD,1995.To color Doppler image the prostate or not:That is the question[J].Radiology,1:11-13.
Arian RE,Pattynama PMT.1998.Receiver operating characteristic(ROC)analysis:Basic principles and applications in radiology[J].European Journal of Radiology,27(2):88-94.
Asernaut H,April G;1976.Properties of speckle integrated with a finite aperture and logarithmically transform[J].J Opt Soc Am,66:1160-1163.
Baeg S,Kehtamavaz N.2000.Texture based classification of mass abnormalities in mammograms[C].Proceedings of the 13~(th) IEEE Symposium on Computer-Based Medical Systems,163-168.
Bamber D.1975.The area above the ordinal dominance graph and area below the receiver operating characteristic graph[J].J Math Psychol,12:387-415.
Black MJ,Sapiro G,Marimont DH,et al.1998.Robust anisotropic diffusion[J].IEEE Trans on Image Processing,7(3):421-432.
Bigler SA,Deering RE,Brawer M.K.1993,Comparison of microscopic vascularity in benign and malignant prostate tissue[J].Human Pathology,24(2):220-226.
Bram VG,Bart M.H,2001.Computer-aided diagnosis in chest radiography:a survey[J].IEEE Transaction Medical Imaging,20:1228-1241.
Canny J.1986.A computational approach to edge detection[J].IEEE Trans Pattern Anal Machine Intell,8(6):679-698.
Caselles V,Catte F,Coll T.1993.A geometric model for active contours in image processing[J].Numerische mathematic,66:1-31.
Caselles V,Kimmel R,Spairo G 1997.Geodesic active contours[J].International Journal of Computer Vision,22(1):61-79.
Catalona WJ,Smith DS,Ratliff TL,et al.1991.Measurement of prostate-specific antigen in serum as a screening test for prostate cancer[J].The New England Journal of Medicine,324(17):1156-1161.
Chan TF,Vese LA,2001.Active contours without edges[J].IEEE Trans on Image Processing,10(2):266-277.
Chen C,Daponte J,Fox M.1989.Fractal feature analysis and classification in medical imaging[J].IEEE Trans Med Imaging,8:133-142.
Chen CM,Lu HHS,Lin YC.2000.An early vision-based snake model for ultrasound image segmentation[J].Ultrasound in Med & Biol,26(2):273-285.
Chen Guan-nan,Yang Kun-tao,Chen Rong,et al.2008.A new study on image enhancement and denoising coupled with shock filters and anisotropic diffusion[C].Congress on Image and Signal Processing,231-235.
Chen PH,Fan Rong-en,Lin CJ.2006.A study on SMO-type decomposition methods for support vector machine[J].IEEE Trans on Neural Networks,17(4):893-908.
Cherkassky V,Mulier F.1998.Learning from data:concept,theory and method[M].NY:John Wiley & Sons.
Czerwinski RN,Jones DL,O'Brien WD.1999.Detection of lines and boundaries in speckle image application to medical ultrasound[J].IEEE Trans Med Imaging,18(2):126-136.
de la Rosette JJ,1995.Computerized analysis of transrectal ultrasonography images in the detection of prostate carcinoma[J].BJU Int,75:485-491.
De Jong IJ,Pruim J,Elsinga PH,et al.2003.Preoperative staging of pelvic lymph nodes in prostate cancer 11C-choline PET[J].The Journal of Nuclear Medicine,44(3):331-335.
Djavan B,Remzi M,Zlotta A,et al.2002.Novel artificial neural network for early detection of prostate cancer[J].J Clin Oncol,20(4):921-929.
Doi K.2007.Computer-aided diagnosis in medical imaging:Historical review, current status and future potential[J].Comput Med Imaging Graph,31(4-5):198-211.
Doi K,MacMahon H,Katsuragawa S,et al.1999.Computer-aided diagnosis in radiology:potential and pitfalls[J].European Journal of Radiology,31:97-109.
Donoho D.1995.De-noising by soft-thresholding[J].IEEE Trans Information Theory,41(3):613-627.
Fan Zhang,Yang MY,Liang MK,et al.2007.Nonlinear diffusion in laplacian pyramid domain for ultrasonic speckle reduction[J].IEEE Trans on Medical Imaging,26(2):200-211.
Finne P,Finne R,Auvinen A,et al.2000.Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network[J].Urology,56(3):418-422.
Frauscher F,Klauser A,Volgger H,et al.2002,Comparison of contrast enhanced color Doppler targeted biopsy with conventional systematic biopsy:impact on prostate cancer detection[J].The Journal of Urology,167(4):1648-1652.
Freund Y,1995.Boosting a weak learning algorithm by majority[J].Information and Computation,121(2):256-285.
Freund Y,Schapire RE.1996.Experiments with a new boosting algorithm[C].Machine Learning:Proceeding of Thirteenth International Conference,148-156.
Freund Y,Schapire RE.1997.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,55(1):119～139.
Giesen RJ,Huynen AL,Aarnink RG,et al.1996.Construction and application of hierarchical decision tree for classification of ultrasonographic prostate images[J].Med Biol Eng Comput,34(2):105-109.
Gong L,Pathak SD,Haynor DR,et al.2004.Parametric shape modeling using deformable superellipses for prostate segmentation[J].IEEE Trans Med Imaging,23(3):340-349.
Greenlee RT,Murray T,Bolden S,et al.2000.Cancer Statistics[J].Cancer J Clin,50(1):7-33.
Halpern EJ,Frauscher F,Strup SE,et al.2002,Prostate:high-frequency Doppler US imaging for cancer detection[J].Radiology,225(1):71-77.
Halpern EJ,Frauscher F,Forsberg F,et al.2002,High-frequency Doppler US of the prostate:effect of patient position[J].Radiology,222(3):634-639.
Hain SF,Maisey MN.2003.Positron emission tomography for urological tumors[J].The Journal of urology,92(2):159-164.
Hao X,Gao X,Gao S.A.1999.Novel multi-scale nonlinear threshold method for ultrasonic speckle suppressing[J].IEEE Trans on Medical Image,18(9):787-794.
Haralick RM,Shanmugam K,Dinstein I.1973.Textural features for image classification[J].IEEE Trans on systems,man,and cybernetics,SMC-3(6):610-621.
Honde KK,McNeal JE,Terris MK,et al.1989,Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate[J].The Journal of urology,142(1):71-75.
Houston AG,Premkumar SB,Pitts DE,et al.1995.Prostate ultrasound image analysis:Localization of cancer lesions to assist biopsy[C].Proc of the Eighth IEEE Symposium on Computer-Based Medical Systems,94-101.
Hsu CW,Chang CC,Lin CJ.2007.A practical guide to support vector classification[EB/OL].Taiwan:Department of Computer Science,National Taiwan University,[2007-12-20].http://ww.csie.ntu.edu.tw/～cjlin/libsvm/index.html.
Huttenlocher DJ,Klanderman GA,Rucklidge WJ.1993.Comparing images using the Hausdorff distance[J].IEEE Trans Pattern Anal Machine Intell,15(9):850-863.
Huynen AL,Giesen RJ,Rosette JJ,et al.1994.Analysis of ultrasonographic prostate images for the detection of prostatic carcinoma:The automated urologic diagnostic expert system[J].Ultrasound Med Biol,20(1):1-10.
Jain A.K.1989.Fundamentals of digital image processing[M].Englewood Cliffs NJ:Prentice-Hall,35-57.
Jain A,Zongker D.1997.Feature selection:evaluation,application,and small sample performance[J].IEEE Trans Pattern Anal Mach Intell,19:153-158.
Javier H,Ian MT.2004.Diagnosis and treatment of prostate cancer[J].Med Clin NAm,(88):267-279.
Jemal A.2005.Cancer statistics[J],Cancer J Clin,55(1):10-30.
Joan C,Vilanova,Josep C,et al.2001.The value of endorectal MR imaging to predict positive biopsies in clinically intermediate-risk prostate cancer patients[J].Eur Radiol,11:229-235.
Karamra M,Kutay MA,Bszdagi G.1995.An adaptive speckle suppression filter for medical ultrasound imaging[J].IEEE Trans on Medical Image,14(2):283-292.
Kass M,Witkin A,Terzopoulous D.1987.Snakes:active contour models[C].Proceedings of the 1st International Conference on Computer Vision,London:IEEE Computer Society Press,pp:259-268.
Kass M,Witkin A,Terzopoulos D.1988.Snakes:Active contour models[J].Int J Comput Vis,1:321-331.
Kher A,Mitra S.1993.Optimum morphological filtering to remove speckle noise from SAR images[C].Proc SPIE Image Algebra and Morphological Image Processing IV,2030:97-108.
Kim HS,Yoo JM,Park MS,et al.2007.An anisotropic diffusion based on diagonal edges[C].The 9~(th)International Conference on Advanced Communication Technology,384-388.
Kohonen T.1990.The self-organizing map[C].Proc IEEE,78:1464-1480.
Kuan DT,Sawchuk AA,Strand TC.et al.1985.Adaptive noise smoothing filter for images with signal-dependent noise[J].IEEE Trans Pattern Analysis and Machine Intelligence,7(2):165-177.
Kwoh CK,Teo MY,Ng WS,et al.1998.Outline of prostate boundary using the harmonics method[J].Med Biol Eng Comput,36:768-771.
Ladak HM,Mao F,Wang Y.2000.Prostate segmentation from 2D ultrasound images[J].Med Phys,27:1777-1788.
Lee F,Gray JM,Mcleary RD,et al.1985.Transrectal ultrasound in the diagnosis of prostate cancer:location,echogenicity,histopathology and staging[J].Prostate,7(2):117-120.
Lee F,Torp-Pedersen ST,Siders DB,et al.1989.Transrectal ultrasound in diagnosis and staging of prostatic carcinoma[J].Radiology,170:609-615.
Lee JS.1980.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Trans Pattern Analysis and Machine Intelligence,2(2):165-168.
Li CM,Xu CY,Gui CF,et al.2005.Level set evolution without re-initializaiton:a new variational formulation[C].IEEE Conf Computer Vision Pattern Recognition(CVPR),1:430-436.
Li J,Mohamed SS,Salama MMA.et al.2007.Prostate tissue texture feature extraction for cancer recognition in TRUS image using wavelet decomposition[J].Image Analysis and Recognition,4633:993-1004.
Lie J,Lysaker M,Tai XC.2006.A binary level set model and some applications to Mumford-Shah image segmentation[J].IEEE Trans on Image Processing,15(5):1171-1181.
Lindsey Smith.2002.A tutorial on principal component analysis,http://www.cs.otago.ac.nz/cosc453/student_tutorial/principal_components.pdf.
Liu YJ,Ng WS,Teo MY,et al.1997.Computerised prostate boundary estimation in ultrasound image using the radial bas-relief method[J].Med Biol Eng Comput,35:4450-4454.
Llobet R,Perez-cortes JC,Toselli AH.2007.Computer-aided detection of prostate cancer[J],Int J Med Informatics,76(7):547-556.
Loch T,Leuschner I,Genberg C,et al.1999.Artificial neural network analysis(ANNA)of prostatic transrectal ultrasound[J].Prostate,39:198-204.
Lorenz A,Blum M,Ermert H,et al.1997.Comparison of different neuro-fuzzy classification systems for the detetion of prostate cancer in ultrasonic images[C].Proc IEEE Ultrasonics Symposium,1201-1204.
Loupas T,Mcdicken WN,Allan PL.1989.An adaptive weighted median filter for speckle suppression in medical ultrasound image[J].IEEE Trans Circuits Syst,36(1):129-135.
Malladi R,Sethian JA,Vemuri BC.1995.Shape modeling with front propagation-A level set approach[J].IEEE Trans Pattern Anal Machine Intell,17(2):158-175.
Mallat S.1989.A theory for multiresolution signal decomposition:the wavelet decomposition[J].IEEE Trans.Pattern Analysis and Machine Intelligence,11(7):674-693.
Mallat S,Zhong S.1992.Characterization of signals from multiscale edges[J].IEEE Trans.Pattern Anal Machine Intell,14(7):710-732.
Metz CE.1986.ROC methodology in radiologic imaging[J].Invest Radiol,21(9):720-733.
Michailovich OV,Tannenbaum A.2006.Despeckling of medical ultrasound images[J].IEEE Trans UFFC,53(1):64-78.
Mohamed SS.2006.Integrated feature analysis for prostate tissue characterization using TRUS images[D].Ontario:University of Waterloo.
Mohamed SS,Salama MMA.2005.Computer-aided diagnosis for prostate cancer using support vector machine[C]Proc of the SPIE,Medical Imaging 2005Visualization,Image-Guided Procedures,and Display.5744:898-906.
Moskalik A,Carson PL,Rubin JM,et al.2001,Analysis of three-dimensional ultrasound Doppler for the detection of prostate cancer[J].Urology,57(6):1128-1132.
Na Bian.2006.Evaluation of texture features for analysis of ovarian follicular development[D].Medical Image Computing and Computer-Assisted Intervention, 4191:93-100.
Osher S,Sethian JA,1988.Fronts propagating with curvature dependent speed:algorithms based on Hamilton-Jacobi formulations[J].J Comp Phys,79:12-49.
Ostu N.1979.A threshold selection method from gray-level histograms[J].IEEE Trans on Systems Man and Cybernetics,9(1):62-66.
Perez-Cortes JC,Juan A,Vallada E,2002.Textural analysis of prostate cancer in transrectal ultrasound images[C].Proceedings of Biosignal,283-285.
Perona P,Malik J.1990.Scale-space and edge detection using anisotropic diffusion[J].IEEE Trans Pattern Anal Machine Intell,12(7):629-639.
Peterson JJ,Kransdorf MJ,O'Connor MI,2003.Diagnosis of occult bone metastases:positron emission tomography[J].Clinical orthopaedics and related research,415:120-128.
Pham DL,Prince JL.1999.An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities[J].Pattern Recognition Letters,20(1):57-68.
Pohle R,Toennies KD.2001.Segmentation of medical images using adaptive region growing[C].Proc of SPIE America,SPIE Press:1337-1346.
Pun CM,Lee MC.2003.Log-polar wavelet energy signatures for rotation and scale invariant texture classification[J].IEEE Trans on Pattern Analysis and Machine Intelligence,25:590-603.
Rahnamaya S,Tizhoosh HR,Salama MMA.2005.Automated snake initialization for the segmentation of the prostate in ultrasound images[C].International Conference on Image Analysis and Recognition,3656:930-937.
Richard WD,Keen CG,1996.Automated texture-based segmentation of ultrasound images of the prostate[J].Comput Med Imaging Graph,20:131-140.
Rifkin,MD,1997.Ultrasound of the prostate[M],2nd.New york:Lippincott Raven,191-217.
Rifkin MD,Sudakoff G,Alexander AA,1998,Prostate:technique,results,and potential applications of color Doppler US scanning[J].AJK,171:205.
Robert A,Andrew C,Richard W,et al.2001.American cancer society guidelines for the early detection of cancer:Update of early detection guidelines for prostate,colorectal,and endometrial cancers[J].CA Cancer J Clin,(51):38-75.
Robert AW,Karl WC,David AC.et al.1998,MRF-based algorithms for segmentation of SAR Images[C].IEEE Inter Conference on Image Processing, 3:770-774.
Roula M,Diamond J,Bouridane A.et al.2002.A multispectral computer vision system for automatic grading of prostatic neoplasia[C].Proc IEEE International Symposium on Biomedical Imaging,193-196.
Sahiner B,Petrick N,Chan HP,et al.2001.Computer-aided characterization of mammographic masses:accuracy of mass segmentation and its effect on characterization[J].IEEE Trans Med Imaging,20(12):1275-1284.
Sakai H,Igawa T,Saha PK,et al.1992.A case of prostatic carcinoma presenting as a metastatic orbital tumor[J].Actas Urological Japonica(Kyoto),38:77-80.
Sasikala M,Kumaravel N,Subhashini L.2006.Automatic tumor segmentation using optimal texture features[C].The 3r International Conference on Advances in Medical,Signal and Information Processing,1-4.
Schapire RE,1990.The strength of weak learnability[J].Machine Learning,5(2):197-227.
Scheipers U,Lorenz A,Pesavento A,et al.2001.Ultraschall-Gewebecharakterisierung fur die prostatadiagnostick[J].Biomedizinische Technik,46(1):72-73.
Scherr DS,Eastham J,Ohori M,et al.2002,Prostate biopsy techniques and indications:when,where,and how?[J]Semin Urol Oncol,20(1):18-31.
Schmitz G,Ermert H,Senge T,1994.Tissue characterization of the prostate using Kohonen-mans[C].Proc IEEE Ultrasonics Symposium,1487-1490.
Shao F,Ling KV,Ng WS.2002.3D prostate surface detection from ultrasound image based on level set method[C].In Proc Of Med Image Computing and Computer-Assisted Intervention,2489:389-396.
Shen D,Zhang Y,Davatzikos,C,2003.Segmentation prostate boundaries from ultrasound images using statistical shape model[J].IEEE Trans Med Imaging,22(4):539-551.
Shen Dinggang,Lao Zhiqiang,Zeng Jianchao,et al.2004.Optimized prostate biopsy via a statistical atlas of cancer spatial distribution[J],Medical Image Analysis,8(2):139-150.
Song YW,Upda SS.1996.A new morphological approach for reducing speckle noise in ultrasonic images[C].IEEE 39th Midwest symposium on Circuits and Systems,3:1397-1400.
Stephan G,J CH,Jurgen M,et al.2000.Prostate-specific antigen:effect of pelvic irradiation[J].Radiology,(215):757-760.
Tauber C,Batatia H,Ayache A,et al.2004.A robust speckle reducing anisotropic diffusion[C].International Conference on Image Processing,247-250.
Taylor Lawrence S,Rubens DJ,Porter BC,2005,Prostate cancer:three-dimensional sonoelastography for in vitro detection[J].Radiology,237(3):981-985.
Tillmann L,Ivo L,Carl G et al.1999.Artificial neural network analysis(ANNA)of prostatic transrectal ultrasound[J].The Prostate,39:198-204.
Turk,Pentland A.1991.Face recognition using eigenfaces[C].Proceedings CVPR'91 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,586-591.
Valiant LG.1984.A theory of the Learnable[J].Communications of the ACM,27(11):1134-1142.
Vapnik VN.1995.The nature of statistical learning theory[M].NY:Springer-Verlag.
Vese LA,Chan TF.2002.A multiphase level set framework for image segmentation using the Munford and Shah model[J].International Journal of Computer Vision,50(3):271-293.
Wolf JS,Cher M,DALL'ERA M,et al.1995.The use and accuracy of cross-sectional imaging and fine needle aspiration cytology for detection of pelvic lymph node metastases before radical prostatectomy[J].The Journal of urology,153(2):993-999.
Xavier M,Jordi F.2002.Region-boundary cooperative image segmentation based on active regions[J].Lecture Notes in Computer Science,364-374.
Xu Chenyang,Anthony Yezzi Jr,Prince JL.2000.On the relationship between parametric and geometric active contours[C].In Proc Of 34th Asilomar Conference on Signals,Systems and Computers,483-489.
Xu C,Prince JL,1998.Snake shape and gradient vector flow[J].IEEE Trans Pattern Anal Machine Intell,7(3):359-3369.
Yang MS.1993.A survey of fuzzy clustering[J].Math Comput Modeling,18(11):1-16.
Yezzi A,Kichenassamy S,Kumar A,et al.1997.A geometric snake model for segmentation of medical imagery[J].IEEE Trans on Medical Imaging,16(2):199-209.
Yujin Zhang.1996.A survey on evaluation methods for image segmentation[J]. Pattern Recognition,29(8):1335-1346.
Yu KK,Hricak H.2000.Imaging prostate cancer[J].The Radiologic clinics of North America,38(1):59-85.
Yu YJ,Scott TA.2002.Speckle reducing anisotropic diffusion[J].IEEE Trans Image Process,11(11):1260-1270.
Zhang Huaizhong,Morrow P.,McClean S.2007.Incorporating feature based priors into the geodesic active contour model and its application in biomedical imagery[C].International Machine Vision and Image Processing Conference,67-74.
Zhou XH J,Leeds NE,Mckinnoii GC,et al.2002.Characterization of benign and metastatic vertebral compression fractures with quantitative diffusion MR imaging[J].AJNR,23:165-170.
Zong XL,Laine AF,Geiser EA.1998.Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing[J].IEEE Trans Med Imaging,17(4):532-540.
陈燕龙,钟碧良.2008.基于HMM和微粒群优化算法的表情识别[J].计算机工程,34(13):190-192.
崔伟东,周志华,李星.2000。神经网络VC维计算研究[J].计算机科学,27(7):59-62.
顾方六.2000.我国良性前列腺增生和前列腺发病调查[J].北京医科大学学报,32(1):30-33.
郭圣文,李松毅,罗立民.2003.一种基于四阶各向异性微分的抑噪与边缘增强方法[J].中国图像图形学报A辑,8(z1):492-495.
哈章,李传富,王金萍,等.2008.一种新型的医学图像分割评价方法[J].北京生物医学工程,27(4):385-388.
候格贤,毕笃彦,吴成柯.2000.图像分割质量评价方法研究[J].中国图像图形学报,5(1):39-43.
江锦雄,林洁明,韩莉,等.2008。PSA测定结合经直肠彩色多普勒超声检查在早期前列腺癌诊断的临床意义[J].广州医药,39(5):52-53.
蓝博文,王颖,谭理连,等.2000.前列腺癌的CT诊断与鉴别诊断[J].中华放射学杂志,12:852-854.
李培华,张田文.2000.主动轮廓模型(蛇模型)综述[J].软件学报,11(6):751-757.
李淑清,孔祥田,山刚志,等.2001.前列腺癌的超声表现与组织结构[J].中国超声医学杂志,17(5):334-336。
李松年.2002.中国影像医学.泌尿生殖系统卷[M].北京:人民卫生出版社,325-326.
李亚军,白人驹,高硕.2006.PET在前列腺癌中的应用[J].国际放射医学核医学杂志,30(5):283-286.
刘春明,张相芬,陈武凡.2006.基于小波的医学超声图像斑点噪声抑制方法[J].中国医学物理学杂志,23(5):364-367.
罗惠韬,章毓晋.1997.一个图像分割评价实例及讨论[J].数据采集与处理,12(1):18-22.
那彦群,孙则禹,叶章群,等.2006.中国泌尿外科疾病诊断治疗指南[M].北京:人民卫生出版社,1:103-104.
彭进业,郝重阳,齐华,等.2007.基于多尺度梯度矢量场GAC模型的MR 医学图像分割[J].中国图象图形学报,12(7):1214-1217.
瞿连喜,王翔,方祖军.2001.经直肠B超诊断前列腺癌[J].中国癌症杂志,11(2):153.
孙军,陈锋,郑凯尔.2001.ROC曲线分析在放射学中的应用[J].中华放射学杂志,35(8):574-577.
孙蕾,周明全,耿国华.2005.基于医学图像的数学规划支持向量机[J].计算机工程,31(19):4-6.
孙颖浩.2004.我国前列腺癌的研究现状[J].中华泌尿外科杂志,25:77-80.
唐杰,李颂,李俊来,等.2002.经直肠超声引导下的穿刺活检诊断前列腺癌189例[J].中华超声影像学杂志,11:400-402.
陶榆.1999.外科病理学[M].湖北:湖北科学技术出版社,734-741.
王玲,董昌元,贺伟,等.2001.经直肠彩色多普勒超声对前列腺增生和前列腺癌的血流动力学研究[J].中国超声医学杂志,17(2):144-147.
汪天富,李德玉,郑昌琼,等.2001.超声医学图像分割的混合神经网络方法[J].航天医学与医学工程,14(2):84-87.
许建华,张学工译.2004.统计学习理论[M].北京:电子工业出版社,364-384.
严加勇,庄天戈.2003.医学超声图像分割技术的研究及发展趋势[J].北京生物医学工程,22(1):67-71.
延伟东.2007.图像特征提取方法的研究[D],西安:西北工业大学.
杨杰,陈晓云.2007.图像分类方法比较研究[J].微计算机应用,28(6):627-632.
叶定伟.2006.前列腺癌的流行病学和中国的发展趋势[J].中华外科杂志.44(6):362-364.
余锦华,汪源源,施心陵.2007.基于EM算法参数估计的各向异性扩散超声图像的去噪[J].航天医学与医学工程,20(3):198-204.
张开华,周文罡,张振等.2008.一种改进的C.V主动轮廓模型[J].光电工程,35(12):112-116.
张晓龙,任芳.2009.支持向量机与AdaBoost的结合算法研究[J].计算机应用研究,26(1):77-79.
章一士,韩振奎.2007.前列腺特异抗原在前列腺癌诊断中的价值[J].延安大学学报(医学科学版),5(4):26-27.
张勇,王瓛,郭秀花.2008.基于医学图像纹理特征的疾病诊断方法及其应 用现状[J].北京生物医学工程,27(4):444-447.
章毓晋.2001.图像分割[M].北京:科学出版社.
赵春晖,孙圣和.1998.一种全方位多尺度形态滤波方法[J].模式识别与人工智能,11(1):101-104.
周秦武,卞正中,张大龙.2003.基于小波的超声斑点噪声抑制与对比度增强[J].声学学报,4(28):381-384.
周永昌,郭万学.1998.超声医学[M].北京:北京科学技术文献出版社,1070-1080.
Aksel A,Gilliam AD,Hossack JA,et al.2006.Speckle reducing anisotropic diffusion for echocardiography[C].The Fortieth Asilomar Conference on Signals,Systems and Computers,1988-1992.
Altman AL,Resnick MI,2001,Ultrasonographically guided biopsy of the prostate gland[J].J Ultrasound Med,20(2):159-167.
Anthony KW Sum,Paul YS Cheung.2007.Stabilized anisotropic diffusions[C]IEEE Inter Conference on Acoustics,Speech,and Signal Processing,709-712.
Archie A,Alexander MD,1995.To color Doppler image the prostate or not:That is the question[J].Radiology,1:11-13.
Arian RE,Pattynama PMT.1998.Receiver operating characteristic(ROC)analysis:Basic principles and applications in radiology[J].European Journal of Radiology,27(2):88-94.
Asernaut H,April G;1976.Properties of speckle integrated with a finite aperture and logarithmically transform[J].J Opt Soc Am,66:1160-1163.
Baeg S,Kehtamavaz N.2000.Texture based classification of mass abnormalities in mammograms[C].Proceedings of the 13~(th) IEEE Symposium on Computer-Based Medical Systems,163-168.
Bamber D.1975.The area above the ordinal dominance graph and area below the receiver operating characteristic graph[J].J Math Psychol,12:387-415.
Black MJ,Sapiro G,Marimont DH,et al.1998.Robust anisotropic diffusion[J].IEEE Trans on Image Processing,7(3):421-432.
Bigler SA,Deering RE,Brawer M.K.1993,Comparison of microscopic vascularity in benign and malignant prostate tissue[J].Human Pathology,24(2):220-226.
Bram VG,Bart M.H,2001.Computer-aided diagnosis in chest radiography:a survey[J].IEEE Transaction Medical Imaging,20:1228-1241.
Canny J.1986.A computational approach to edge detection[J].IEEE Trans Pattern Anal Machine Intell,8(6):679-698.
Caselles V,Catte F,Coll T.1993.A geometric model for active contours in image processing[J].Numerische mathematic,66:1-31.
Caselles V,Kimmel R,Spairo G 1997.Geodesic active contours[J].International Journal of Computer Vision,22(1):61-79.
Catalona WJ,Smith DS,Ratliff TL,et al.1991.Measurement of prostate-specific antigen in serum as a screening test for prostate cancer[J].The New England Journal of Medicine,324(17):1156-1161.
Chan TF,Vese LA,2001.Active contours without edges[J].IEEE Trans on Image Processing,10(2):266-277.
Chen C,Daponte J,Fox M.1989.Fractal feature analysis and classification in medical imaging[J].IEEE Trans Med Imaging,8:133-142.
Chen CM,Lu HHS,Lin YC.2000.An early vision-based snake model for ultrasound image segmentation[J].Ultrasound in Med & Biol,26(2):273-285.
Chen Guan-nan,Yang Kun-tao,Chen Rong,et al.2008.A new study on image enhancement and denoising coupled with shock filters and anisotropic diffusion[C].Congress on Image and Signal Processing,231-235.
Chen PH,Fan Rong-en,Lin CJ.2006.A study on SMO-type decomposition methods for support vector machine[J].IEEE Trans on Neural Networks,17(4):893-908.
Cherkassky V,Mulier F.1998.Learning from data:concept,theory and method[M].NY:John Wiley & Sons.
Czerwinski RN,Jones DL,O'Brien WD.1999.Detection of lines and boundaries in speckle image application to medical ultrasound[J].IEEE Trans Med Imaging,18(2):126-136.
de la Rosette JJ,1995.Computerized analysis of transrectal ultrasonography images in the detection of prostate carcinoma[J].BJU Int,75:485-491.
De Jong IJ,Pruim J,Elsinga PH,et al.2003.Preoperative staging of pelvic lymph nodes in prostate cancer 11C-choline PET[J].The Journal of Nuclear Medicine,44(3):331-335.
Djavan B,Remzi M,Zlotta A,et al.2002.Novel artificial neural network for early detection of prostate cancer[J].J Clin Oncol,20(4):921-929.
Doi K.2007.Computer-aided diagnosis in medical imaging:Historical review, current status and future potential[J].Comput Med Imaging Graph,31(4-5):198-211.
Doi K,MacMahon H,Katsuragawa S,et al.1999.Computer-aided diagnosis in radiology:potential and pitfalls[J].European Journal of Radiology,31:97-109.
Donoho D.1995.De-noising by soft-thresholding[J].IEEE Trans Information Theory,41(3):613-627.
Fan Zhang,Yang MY,Liang MK,et al.2007.Nonlinear diffusion in laplacian pyramid domain for ultrasonic speckle reduction[J].IEEE Trans on Medical Imaging,26(2):200-211.
Finne P,Finne R,Auvinen A,et al.2000.Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network[J].Urology,56(3):418-422.
Frauscher F,Klauser A,Volgger H,et al.2002,Comparison of contrast enhanced color Doppler targeted biopsy with conventional systematic biopsy:impact on prostate cancer detection[J].The Journal of Urology,167(4):1648-1652.
Freund Y,1995.Boosting a weak learning algorithm by majority[J].Information and Computation,121(2):256-285.
Freund Y,Schapire RE.1996.Experiments with a new boosting algorithm[C].Machine Learning:Proceeding of Thirteenth International Conference,148-156.
Freund Y,Schapire RE.1997.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,55(1):119～139.
Giesen RJ,Huynen AL,Aarnink RG,et al.1996.Construction and application of hierarchical decision tree for classification of ultrasonographic prostate images[J].Med Biol Eng Comput,34(2):105-109.
Gong L,Pathak SD,Haynor DR,et al.2004.Parametric shape modeling using deformable superellipses for prostate segmentation[J].IEEE Trans Med Imaging,23(3):340-349.
Greenlee RT,Murray T,Bolden S,et al.2000.Cancer Statistics[J].Cancer J Clin,50(1):7-33.
Halpern EJ,Frauscher F,Strup SE,et al.2002,Prostate:high-frequency Doppler US imaging for cancer detection[J].Radiology,225(1):71-77.
Halpern EJ,Frauscher F,Forsberg F,et al.2002,High-frequency Doppler US of the prostate:effect of patient position[J].Radiology,222(3):634-639.
Hain SF,Maisey MN.2003.Positron emission tomography for urological tumors[J].The Journal of urology,92(2):159-164.
Hao X,Gao X,Gao S.A.1999.Novel multi-scale nonlinear threshold method for ultrasonic speckle suppressing[J].IEEE Trans on Medical Image,18(9):787-794.
Haralick RM,Shanmugam K,Dinstein I.1973.Textural features for image classification[J].IEEE Trans on systems,man,and cybernetics,SMC-3(6):610-621.
Honde KK,McNeal JE,Terris MK,et al.1989,Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate[J].The Journal of urology,142(1):71-75.
Houston AG,Premkumar SB,Pitts DE,et al.1995.Prostate ultrasound image analysis:Localization of cancer lesions to assist biopsy[C].Proc of the Eighth IEEE Symposium on Computer-Based Medical Systems,94-101.
Hsu CW,Chang CC,Lin CJ.2007.A practical guide to support vector classification[EB/OL].Taiwan:Department of Computer Science,National Taiwan University,[2007-12-20].http://ww.csie.ntu.edu.tw/～cjlin/libsvm/index.html.
Huttenlocher DJ,Klanderman GA,Rucklidge WJ.1993.Comparing images using the Hausdorff distance[J].IEEE Trans Pattern Anal Machine Intell,15(9):850-863.
Huynen AL,Giesen RJ,Rosette JJ,et al.1994.Analysis of ultrasonographic prostate images for the detection of prostatic carcinoma:The automated urologic diagnostic expert system[J].Ultrasound Med Biol,20(1):1-10.
Jain A.K.1989.Fundamentals of digital image processing[M].Englewood Cliffs NJ:Prentice-Hall,35-57.
Jain A,Zongker D.1997.Feature selection:evaluation,application,and small sample performance[J].IEEE Trans Pattern Anal Mach Intell,19:153-158.
Javier H,Ian MT.2004.Diagnosis and treatment of prostate cancer[J].Med Clin NAm,(88):267-279.
Jemal A.2005.Cancer statistics[J],Cancer J Clin,55(1):10-30.
Joan C,Vilanova,Josep C,et al.2001.The value of endorectal MR imaging to predict positive biopsies in clinically intermediate-risk prostate cancer patients[J].Eur Radiol,11:229-235.
Karamra M,Kutay MA,Bszdagi G.1995.An adaptive speckle suppression filter for medical ultrasound imaging[J].IEEE Trans on Medical Image,14(2):283-292.
Kass M,Witkin A,Terzopoulous D.1987.Snakes:active contour models[C].Proceedings of the 1st International Conference on Computer Vision,London:IEEE Computer Society Press,pp:259-268.
Kass M,Witkin A,Terzopoulos D.1988.Snakes:Active contour models[J].Int J Comput Vis,1:321-331.
Kher A,Mitra S.1993.Optimum morphological filtering to remove speckle noise from SAR images[C].Proc SPIE Image Algebra and Morphological Image Processing IV,2030:97-108.
Kim HS,Yoo JM,Park MS,et al.2007.An anisotropic diffusion based on diagonal edges[C].The 9~(th)International Conference on Advanced Communication Technology,384-388.
Kohonen T.1990.The self-organizing map[C].Proc IEEE,78:1464-1480.
Kuan DT,Sawchuk AA,Strand TC.et al.1985.Adaptive noise smoothing filter for images with signal-dependent noise[J].IEEE Trans Pattern Analysis and Machine Intelligence,7(2):165-177.
Kwoh CK,Teo MY,Ng WS,et al.1998.Outline of prostate boundary using the harmonics method[J].Med Biol Eng Comput,36:768-771.
Ladak HM,Mao F,Wang Y.2000.Prostate segmentation from 2D ultrasound images[J].Med Phys,27:1777-1788.
Lee F,Gray JM,Mcleary RD,et al.1985.Transrectal ultrasound in the diagnosis of prostate cancer:location,echogenicity,histopathology and staging[J].Prostate,7(2):117-120.
Lee F,Torp-Pedersen ST,Siders DB,et al.1989.Transrectal ultrasound in diagnosis and staging of prostatic carcinoma[J].Radiology,170:609-615.
Lee JS.1980.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Trans Pattern Analysis and Machine Intelligence,2(2):165-168.
Li CM,Xu CY,Gui CF,et al.2005.Level set evolution without re-initializaiton:a new variational formulation[C].IEEE Conf Computer Vision Pattern Recognition(CVPR),1:430-436.
Li J,Mohamed SS,Salama MMA.et al.2007.Prostate tissue texture feature extraction for cancer recognition in TRUS image using wavelet decomposition[J].Image Analysis and Recognition,4633:993-1004.
Lie J,Lysaker M,Tai XC.2006.A binary level set model and some applications to Mumford-Shah image segmentation[J].IEEE Trans on Image Processing,15(5):1171-1181.
Lindsey Smith.2002.A tutorial on principal component analysis,http://www.cs.otago.ac.nz/cosc453/student_tutorial/principal_components.pdf.
Liu YJ,Ng WS,Teo MY,et al.1997.Computerised prostate boundary estimation in ultrasound image using the radial bas-relief method[J].Med Biol Eng Comput,35:4450-4454.
Llobet R,Perez-cortes JC,Toselli AH.2007.Computer-aided detection of prostate cancer[J],Int J Med Informatics,76(7):547-556.
Loch T,Leuschner I,Genberg C,et al.1999.Artificial neural network analysis(ANNA)of prostatic transrectal ultrasound[J].Prostate,39:198-204.
Lorenz A,Blum M,Ermert H,et al.1997.Comparison of different neuro-fuzzy classification systems for the detetion of prostate cancer in ultrasonic images[C].Proc IEEE Ultrasonics Symposium,1201-1204.
Loupas T,Mcdicken WN,Allan PL.1989.An adaptive weighted median filter for speckle suppression in medical ultrasound image[J].IEEE Trans Circuits Syst,36(1):129-135.
Malladi R,Sethian JA,Vemuri BC.1995.Shape modeling with front propagation-A level set approach[J].IEEE Trans Pattern Anal Machine Intell,17(2):158-175.
Mallat S.1989.A theory for multiresolution signal decomposition:the wavelet decomposition[J].IEEE Trans.Pattern Analysis and Machine Intelligence,11(7):674-693.
Mallat S,Zhong S.1992.Characterization of signals from multiscale edges[J].IEEE Trans.Pattern Anal Machine Intell,14(7):710-732.
Metz CE.1986.ROC methodology in radiologic imaging[J].Invest Radiol,21(9):720-733.
Michailovich OV,Tannenbaum A.2006.Despeckling of medical ultrasound images[J].IEEE Trans UFFC,53(1):64-78.
Mohamed SS.2006.Integrated feature analysis for prostate tissue characterization using TRUS images[D].Ontario:University of Waterloo.
Mohamed SS,Salama MMA.2005.Computer-aided diagnosis for prostate cancer using support vector machine[C]Proc of the SPIE,Medical Imaging 2005Visualization,Image-Guided Procedures,and Display.5744:898-906.
Moskalik A,Carson PL,Rubin JM,et al.2001,Analysis of three-dimensional ultrasound Doppler for the detection of prostate cancer[J].Urology,57(6):1128-1132.
Na Bian.2006.Evaluation of texture features for analysis of ovarian follicular development[D].Medical Image Computing and Computer-Assisted Intervention, 4191:93-100.
Osher S,Sethian JA,1988.Fronts propagating with curvature dependent speed:algorithms based on Hamilton-Jacobi formulations[J].J Comp Phys,79:12-49.
Ostu N.1979.A threshold selection method from gray-level histograms[J].IEEE Trans on Systems Man and Cybernetics,9(1):62-66.
Perez-Cortes JC,Juan A,Vallada E,2002.Textural analysis of prostate cancer in transrectal ultrasound images[C].Proceedings of Biosignal,283-285.
Perona P,Malik J.1990.Scale-space and edge detection using anisotropic diffusion[J].IEEE Trans Pattern Anal Machine Intell,12(7):629-639.
Peterson JJ,Kransdorf MJ,O'Connor MI,2003.Diagnosis of occult bone metastases:positron emission tomography[J].Clinical orthopaedics and related research,415:120-128.
Pham DL,Prince JL.1999.An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities[J].Pattern Recognition Letters,20(1):57-68.
Pohle R,Toennies KD.2001.Segmentation of medical images using adaptive region growing[C].Proc of SPIE America,SPIE Press:1337-1346.
Pun CM,Lee MC.2003.Log-polar wavelet energy signatures for rotation and scale invariant texture classification[J].IEEE Trans on Pattern Analysis and Machine Intelligence,25:590-603.
Rahnamaya S,Tizhoosh HR,Salama MMA.2005.Automated snake initialization for the segmentation of the prostate in ultrasound images[C].International Conference on Image Analysis and Recognition,3656:930-937.
Richard WD,Keen CG,1996.Automated texture-based segmentation of ultrasound images of the prostate[J].Comput Med Imaging Graph,20:131-140.
Rifkin,MD,1997.Ultrasound of the prostate[M],2nd.New york:Lippincott Raven,191-217.
Rifkin MD,Sudakoff G,Alexander AA,1998,Prostate:technique,results,and potential applications of color Doppler US scanning[J].AJK,171:205.
Robert A,Andrew C,Richard W,et al.2001.American cancer society guidelines for the early detection of cancer:Update of early detection guidelines for prostate,colorectal,and endometrial cancers[J].CA Cancer J Clin,(51):38-75.
Robert AW,Karl WC,David AC.et al.1998,MRF-based algorithms for segmentation of SAR Images[C].IEEE Inter Conference on Image Processing, 3:770-774.
Roula M,Diamond J,Bouridane A.et al.2002.A multispectral computer vision system for automatic grading of prostatic neoplasia[C].Proc IEEE International Symposium on Biomedical Imaging,193-196.
Sahiner B,Petrick N,Chan HP,et al.2001.Computer-aided characterization of mammographic masses:accuracy of mass segmentation and its effect on characterization[J].IEEE Trans Med Imaging,20(12):1275-1284.
Sakai H,Igawa T,Saha PK,et al.1992.A case of prostatic carcinoma presenting as a metastatic orbital tumor[J].Actas Urological Japonica(Kyoto),38:77-80.
Sasikala M,Kumaravel N,Subhashini L.2006.Automatic tumor segmentation using optimal texture features[C].The 3r International Conference on Advances in Medical,Signal and Information Processing,1-4.
Schapire RE,1990.The strength of weak learnability[J].Machine Learning,5(2):197-227.
Scheipers U,Lorenz A,Pesavento A,et al.2001.Ultraschall-Gewebecharakterisierung fur die prostatadiagnostick[J].Biomedizinische Technik,46(1):72-73.
Scherr DS,Eastham J,Ohori M,et al.2002,Prostate biopsy techniques and indications:when,where,and how?[J]Semin Urol Oncol,20(1):18-31.
Schmitz G,Ermert H,Senge T,1994.Tissue characterization of the prostate using Kohonen-mans[C].Proc IEEE Ultrasonics Symposium,1487-1490.
Shao F,Ling KV,Ng WS.2002.3D prostate surface detection from ultrasound image based on level set method[C].In Proc Of Med Image Computing and Computer-Assisted Intervention,2489:389-396.
Shen D,Zhang Y,Davatzikos,C,2003.Segmentation prostate boundaries from ultrasound images using statistical shape model[J].IEEE Trans Med Imaging,22(4):539-551.
Shen Dinggang,Lao Zhiqiang,Zeng Jianchao,et al.2004.Optimized prostate biopsy via a statistical atlas of cancer spatial distribution[J],Medical Image Analysis,8(2):139-150.
Song YW,Upda SS.1996.A new morphological approach for reducing speckle noise in ultrasonic images[C].IEEE 39th Midwest symposium on Circuits and Systems,3:1397-1400.
Stephan G,J CH,Jurgen M,et al.2000.Prostate-specific antigen:effect of pelvic irradiation[J].Radiology,(215):757-760.
Tauber C,Batatia H,Ayache A,et al.2004.A robust speckle reducing anisotropic diffusion[C].International Conference on Image Processing,247-250.
Taylor Lawrence S,Rubens DJ,Porter BC,2005,Prostate cancer:three-dimensional sonoelastography for in vitro detection[J].Radiology,237(3):981-985.
Tillmann L,Ivo L,Carl G et al.1999.Artificial neural network analysis(ANNA)of prostatic transrectal ultrasound[J].The Prostate,39:198-204.
Turk,Pentland A.1991.Face recognition using eigenfaces[C].Proceedings CVPR'91 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,586-591.
Valiant LG.1984.A theory of the Learnable[J].Communications of the ACM,27(11):1134-1142.
Vapnik VN.1995.The nature of statistical learning theory[M].NY:Springer-Verlag.
Vese LA,Chan TF.2002.A multiphase level set framework for image segmentation using the Munford and Shah model[J].International Journal of Computer Vision,50(3):271-293.
Wolf JS,Cher M,DALL'ERA M,et al.1995.The use and accuracy of cross-sectional imaging and fine needle aspiration cytology for detection of pelvic lymph node metastases before radical prostatectomy[J].The Journal of urology,153(2):993-999.
Xavier M,Jordi F.2002.Region-boundary cooperative image segmentation based on active regions[J].Lecture Notes in Computer Science,364-374.
Xu Chenyang,Anthony Yezzi Jr,Prince JL.2000.On the relationship between parametric and geometric active contours[C].In Proc Of 34th Asilomar Conference on Signals,Systems and Computers,483-489.
Xu C,Prince JL,1998.Snake shape and gradient vector flow[J].IEEE Trans Pattern Anal Machine Intell,7(3):359-3369.
Yang MS.1993.A survey of fuzzy clustering[J].Math Comput Modeling,18(11):1-16.
Yezzi A,Kichenassamy S,Kumar A,et al.1997.A geometric snake model for segmentation of medical imagery[J].IEEE Trans on Medical Imaging,16(2):199-209.
Yujin Zhang.1996.A survey on evaluation methods for image segmentation[J]. Pattern Recognition,29(8):1335-1346.
Yu KK,Hricak H.2000.Imaging prostate cancer[J].The Radiologic clinics of North America,38(1):59-85.
Yu YJ,Scott TA.2002.Speckle reducing anisotropic diffusion[J].IEEE Trans Image Process,11(11):1260-1270.
Zhang Huaizhong,Morrow P.,McClean S.2007.Incorporating feature based priors into the geodesic active contour model and its application in biomedical imagery[C].International Machine Vision and Image Processing Conference,67-74.
Zhou XH J,Leeds NE,Mckinnoii GC,et al.2002.Characterization of benign and metastatic vertebral compression fractures with quantitative diffusion MR imaging[J].AJNR,23:165-170.
Zong XL,Laine AF,Geiser EA.1998.Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing[J].IEEE Trans Med Imaging,17(4):532-540.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |