超声图像乳腺肿瘤分割新方法研究
|
摘要
乳腺癌是目前女性疾病中最常见的恶性肿瘤，已成为导致女性死亡的主要杀手之一。早发现、早诊断和早治疗是目前医学上对防治乳腺癌采取的“三早”原则。超声成像凭借其无创伤、无辐射和费用低廉等优点，已成为乳腺肿瘤临床诊断的主要手段之一。乳腺超声图像的肿瘤分割可以给医生提供辅助诊断和参考意见，提高了诊断的客观性和正确性，降低了误诊和漏诊现象的发生。
然而，乳腺超声图像的准确分割非常困难。首先，在超声成像过程中，由于受成像设备的影响，超声图像产生了固有的斑点噪声，使得图像的信噪比和对比度较低、边缘模糊甚至边缘信息缺失。其次，超声图像中存在多种伪影，比如衰减以及在射频场中，非均匀光束在人体内衰减导致的伪影。最后，不同乳腺肿瘤的大小、形状和位置差异较大。除此之外，乳腺超声图像中存在肿瘤的浸润效应，也就是，肿瘤经常侵入周围的正常组织，这使得肿瘤与周围正常组织，比如皮下脂肪组织，腺体组织非常相似，往往难以分辨，这给肿瘤分割造成了更大的困难。乳腺超声图像的上述特点使得肿瘤的分割仍然非常具有挑战性，是一个值得深入研究的课题。
为此，本文在图论、曲线演化理论和水平集方法的基础上，深入、细致地研究了基于图的Normalized Cut方法、水平集活动轮廓方法以及它们在二维或三维乳腺超声图像分割中的应用。本文的主要工作和研究成果如下：
1.基于相位和梯度矢量流的水平集乳腺超声肿瘤分割
在距离正则化水平集模型的基础上，本文提出一种基于相位和梯度矢量流的水平集活动轮廓模型。首先，引入单演信号的概念，利用柯西核而非Log Gabor构造正交滤波器，以提取多尺度的基于单演信号的特征；然后，将相位非对称方法应用于多尺度的图像特征上，以达到检测边缘和去除噪声的目的；接着，利用得到的边缘图，定义了一个边缘停止项，并在此基础上改进了梯度矢量流；最后，在活动轮廓模型中融入自定义的边缘停止项和梯度矢量流。一方面，由于本文方法仅利用了局部相位信息，因此它对乳腺超声图像中存在的灰度不均匀性和噪声具有较好的鲁棒性。另一方面，梯度矢量流的引入使得本文方法能够有效地捕获凹陷边界和弱边界。乳腺超声图像的分割实验证明，本文方法可以成功地分割出乳腺肿瘤。
2.基于同质片的乳腺超声图像肿瘤分割
在Normalized Cut（NCut）方法的基础上，本文提出了基于同质片的乳腺超声图像肿瘤分割方法。首先，定义了基于灰度和纹理信息的边界检测函数；然后，利用边界图定义了一种可以随图像像素位置变化而变化的自适应邻域系统，称之为同质片。由于同质片可以保证邻域不会跨越不同的组织，因此基于同质片的统计特征更有利于区分不同的组织，进而能够提高分割的准确度。最后，将每个同质片视为一个模糊集合，用同质片内纹理基元的模糊分布作为分割特征，再用NCut方法得到乳腺肿瘤。本文提出的算法既可以避免超声图像衰减伪影的影响，同时也避免了将肿瘤周围的正常组织，比如皮下脂肪组织、腺体组织等误划分为肿瘤。100例乳腺超声图像上的分割实验证明，本文算法取得了比现有方法更高的分割精度和鲁棒性。
3.基于同质体和局部能量的三维乳腺超声肿瘤分割
在经典的水平集活动轮廓模型Chan-Vese模型的基础上，借鉴Lankton方法局部处理的思想，本文提出了一种基于同质体和局部能量的水平集活动轮廓模型，并用于分割三维超声图像的乳腺肿瘤。首先，用三维相位非对称方法提取边缘曲面，进而利用每个体素邻域的边缘信息拟合了一个二次曲面，将拟合后曲面的极值作为各体素的边缘能量。这样，既使得提取的边缘曲面更为连续和光滑，而且也去除了曲面表面的噪声。然后，将二维同质片的概念推广至三维空间上，利用拟合后的边缘曲面构造了可以保持局部同质性的三维自适应邻域，将其称之为同质体。接着，通过分析同质体的纹理分布和计算局部灰度均值，定义了演化曲线周围基于同质体的局部能量。和同质片类似，利用基于同质体的特征有利于区分局部表现和外观相似却属于不同组织的体素。同时，还定义了演化曲线周围基于全局灰度均值的全局能量，这有利于驱动离真实肿瘤边界较远的演化曲线逐渐向真实边界处靠拢。最后，在活动轮廓模型中，综合全局和局部能量，通过曲线的快速演化实现乳腺超声图像的肿瘤分割。所提出的方法既可以克服乳腺超声图像灰度不均的问题，也可以避免陷入局部极值的问题。25例三维乳腺超声图像上的分割实验证明，与现有的方法相比较，所提出的方法可以有效地分割出乳腺超声肿瘤。
Breast cancer is the most common malignant lesions and is the leading cause ofdeath in women. Prevention and treatment of breast cancer adopts three principlesclinically: early detection, early diagnosis and early treatment. Ultrasound (US) imaginghas been one of the main measures of clinical diagnosis on breast tumor due to itsnon-invasive nature, minimal ionizing radiation and low cost. Tumor segmentation ofbreast US image can provide aided diagnosis and second opinion. This improves theobjectivity and accuracy of diagnosis and reduces the likelihood of misdiagnosis andmissed diagnosis.
However, accurately segmenting breast tumors in US images is a very difficult taskdue to the following reasons. First, US image has inherent speckle, fuzzy or evenmissing edges, low signal-to-noise ratio, and low contrast due to the effect of USimaging device. Second, there are characteristic artifacts, such as attenuation and thosecaused by nonuniform beam attenuation within the body in radio-frequency field. Third,tumor variance in shape, size and location differs greatly. The effect of tumorinfiltrating is also a reason, that is, the tumor often infiltrates into its surroundingnormal tissue. This leads to the presence of tumor-like structures in malignant tumorimage such as, subcutaneous fat and glandular tissue. It is difficult to distinguish themalignant tumor from these tumor-like structures visually and hence, tumorsegmentation task is much more difficult. All characteristics of breast US images givenabove make US image segmentation very challenging. Segmentation of ultrasonictumor is worthy of further study.
Based on the graph theory, curve evolution theory and level set method, this papermakes in-depth study on Normalized Cut (NCut) graph-based method, active contourlevel set method and their applications in two-dimensional(2-D) orthree-dimensional(3-D) US image segmentation. The main contents and innovationinclude the following three aspects:
1. Phase-and GVF-based level set segmentation of ultrasonic breast tumors
Based on the distance regularized level set evolution model, this paper presents a phase-and GVF-based level set method for segmentation of ultrasonic breast tumors.First, by introducing the concept of monogenic signal, we use Cauchy kernels ratherthan Log Gabor as pair of quadrature filters for the multi-scale feature extraction.Second, phase asymmetry approach is then applied to multi-scale features to enhanceedges and remove noise effect. Third, based on precalculated edge map, an edgestopping term is defined and gradient vector flow (GVF) is then improved. At last, theedge stopping term and the resulting GVF are incorporated into the active contourmodel. The proposed method is insensitive to intensity inhomogeneities and noise dueto the use of local phase information. On the other hand, the proposed method cancapture concave boundaries and weak boundaries due to the use of GVF field.Experiments on clinical breast US images showed that the proposed method can extracttumor boundaries from breast US image, as compared to the state-of-the-art methods.
2. Segmentation of ultrasonic breast tumors based on homogeneous patch
This paper presents a novel algorithm based on homogeneous patches (HP) andNCut for segmentation of breast tumor in US images. A novel edge-detection functionis defined by combining intensity and texture information to look for boundaries in USimages. Subsequently, a kind of adaptive neighborhood according to image locationreferred to as homogeneous patch (HP), is proposed by using edge map from anedge-detection function. The HPs are guaranteed to spread within the same tissue region.Hence, the statistic features within HPs can better distinguish different tissues and,furthermore, improve accuracy in image segmentation. Each HP is considered as afuzzy set. The fuzzy distribution of textons in HPs is used as final image features andtumor segmentation is obtained by using the NCut method. The proposed method canavoid attenuation artifacts and decrease the likelihood that the surrounding structuresare misclassified as tumor. Experimental results from100breast sonogramsdemonstrated the improvement in accuracy and robustness in segmenting the breastultrasound images by the presented algorithm, as compared to the state-of-the-artmethods.
3.3-D segmentation of ultrasonic breast tumors based on homogeneous volumeand local energy
By taking the advantages of the classical Chan-Vese (CV) level set model andLankton method, this paper presents a novel level set active contour model based on homogeneous volume and local energy for3-D segmentation of ultrasonic breast tumors.First,3-D phase asymmetry approach is used to extract edge surface. And then at eachvoxel in3-D image, a quadric surface is fitted to estimate the edge energies based on theprecalculated edge surface. The fitted surface is continuous and smooth and isinsensitivity to noise. Second, based on the precalculated fitted surface, the concept of2-D homogeneous patch (HP) is extended to3-D homogeneous volume (HV), i.e., akind of adaptive neighborhood which can guarantee locally homogeneous neighborhoodin3-D. Third, local energies are defined at each voxel along the curve by usingdistribution of textons and mean intensity within HVs. Similar to HPs, using HVs helpsto discriminate those pixels with similar appearance but belonging to different tissues.At the same time, global energies are defined at each voxel along the curve by usingglobal statistics. When the contour is far from object boundaries, the force from theglobal energies is used to guide the contour toward and finally stops the contour atobject boundaries. At last, the local and global energies are incorporated into thegeometric active contour model and tumor segmentation is obtained by using the fastcurve evolution method. The proposed method can overcome the problem of intensityinhomogeneities and avoid falling into local extrema. Experiments on25clinical3-Dbreast US images showed that the proposed method can segment3-D ultrasonic breasttumors accurately, as compared to the state-of-the-art methods.
然而，乳腺超声图像的准确分割非常困难。首先，在超声成像过程中，由于受成像设备的影响，超声图像产生了固有的斑点噪声，使得图像的信噪比和对比度较低、边缘模糊甚至边缘信息缺失。其次，超声图像中存在多种伪影，比如衰减以及在射频场中，非均匀光束在人体内衰减导致的伪影。最后，不同乳腺肿瘤的大小、形状和位置差异较大。除此之外，乳腺超声图像中存在肿瘤的浸润效应，也就是，肿瘤经常侵入周围的正常组织，这使得肿瘤与周围正常组织，比如皮下脂肪组织，腺体组织非常相似，往往难以分辨，这给肿瘤分割造成了更大的困难。乳腺超声图像的上述特点使得肿瘤的分割仍然非常具有挑战性，是一个值得深入研究的课题。
为此，本文在图论、曲线演化理论和水平集方法的基础上，深入、细致地研究了基于图的Normalized Cut方法、水平集活动轮廓方法以及它们在二维或三维乳腺超声图像分割中的应用。本文的主要工作和研究成果如下：
1.基于相位和梯度矢量流的水平集乳腺超声肿瘤分割
在距离正则化水平集模型的基础上，本文提出一种基于相位和梯度矢量流的水平集活动轮廓模型。首先，引入单演信号的概念，利用柯西核而非Log Gabor构造正交滤波器，以提取多尺度的基于单演信号的特征；然后，将相位非对称方法应用于多尺度的图像特征上，以达到检测边缘和去除噪声的目的；接着，利用得到的边缘图，定义了一个边缘停止项，并在此基础上改进了梯度矢量流；最后，在活动轮廓模型中融入自定义的边缘停止项和梯度矢量流。一方面，由于本文方法仅利用了局部相位信息，因此它对乳腺超声图像中存在的灰度不均匀性和噪声具有较好的鲁棒性。另一方面，梯度矢量流的引入使得本文方法能够有效地捕获凹陷边界和弱边界。乳腺超声图像的分割实验证明，本文方法可以成功地分割出乳腺肿瘤。
2.基于同质片的乳腺超声图像肿瘤分割
在Normalized Cut（NCut）方法的基础上，本文提出了基于同质片的乳腺超声图像肿瘤分割方法。首先，定义了基于灰度和纹理信息的边界检测函数；然后，利用边界图定义了一种可以随图像像素位置变化而变化的自适应邻域系统，称之为同质片。由于同质片可以保证邻域不会跨越不同的组织，因此基于同质片的统计特征更有利于区分不同的组织，进而能够提高分割的准确度。最后，将每个同质片视为一个模糊集合，用同质片内纹理基元的模糊分布作为分割特征，再用NCut方法得到乳腺肿瘤。本文提出的算法既可以避免超声图像衰减伪影的影响，同时也避免了将肿瘤周围的正常组织，比如皮下脂肪组织、腺体组织等误划分为肿瘤。100例乳腺超声图像上的分割实验证明，本文算法取得了比现有方法更高的分割精度和鲁棒性。
3.基于同质体和局部能量的三维乳腺超声肿瘤分割
在经典的水平集活动轮廓模型Chan-Vese模型的基础上，借鉴Lankton方法局部处理的思想，本文提出了一种基于同质体和局部能量的水平集活动轮廓模型，并用于分割三维超声图像的乳腺肿瘤。首先，用三维相位非对称方法提取边缘曲面，进而利用每个体素邻域的边缘信息拟合了一个二次曲面，将拟合后曲面的极值作为各体素的边缘能量。这样，既使得提取的边缘曲面更为连续和光滑，而且也去除了曲面表面的噪声。然后，将二维同质片的概念推广至三维空间上，利用拟合后的边缘曲面构造了可以保持局部同质性的三维自适应邻域，将其称之为同质体。接着，通过分析同质体的纹理分布和计算局部灰度均值，定义了演化曲线周围基于同质体的局部能量。和同质片类似，利用基于同质体的特征有利于区分局部表现和外观相似却属于不同组织的体素。同时，还定义了演化曲线周围基于全局灰度均值的全局能量，这有利于驱动离真实肿瘤边界较远的演化曲线逐渐向真实边界处靠拢。最后，在活动轮廓模型中，综合全局和局部能量，通过曲线的快速演化实现乳腺超声图像的肿瘤分割。所提出的方法既可以克服乳腺超声图像灰度不均的问题，也可以避免陷入局部极值的问题。25例三维乳腺超声图像上的分割实验证明，与现有的方法相比较，所提出的方法可以有效地分割出乳腺超声肿瘤。
Breast cancer is the most common malignant lesions and is the leading cause ofdeath in women. Prevention and treatment of breast cancer adopts three principlesclinically: early detection, early diagnosis and early treatment. Ultrasound (US) imaginghas been one of the main measures of clinical diagnosis on breast tumor due to itsnon-invasive nature, minimal ionizing radiation and low cost. Tumor segmentation ofbreast US image can provide aided diagnosis and second opinion. This improves theobjectivity and accuracy of diagnosis and reduces the likelihood of misdiagnosis andmissed diagnosis.
However, accurately segmenting breast tumors in US images is a very difficult taskdue to the following reasons. First, US image has inherent speckle, fuzzy or evenmissing edges, low signal-to-noise ratio, and low contrast due to the effect of USimaging device. Second, there are characteristic artifacts, such as attenuation and thosecaused by nonuniform beam attenuation within the body in radio-frequency field. Third,tumor variance in shape, size and location differs greatly. The effect of tumorinfiltrating is also a reason, that is, the tumor often infiltrates into its surroundingnormal tissue. This leads to the presence of tumor-like structures in malignant tumorimage such as, subcutaneous fat and glandular tissue. It is difficult to distinguish themalignant tumor from these tumor-like structures visually and hence, tumorsegmentation task is much more difficult. All characteristics of breast US images givenabove make US image segmentation very challenging. Segmentation of ultrasonictumor is worthy of further study.
Based on the graph theory, curve evolution theory and level set method, this papermakes in-depth study on Normalized Cut (NCut) graph-based method, active contourlevel set method and their applications in two-dimensional(2-D) orthree-dimensional(3-D) US image segmentation. The main contents and innovationinclude the following three aspects:
1. Phase-and GVF-based level set segmentation of ultrasonic breast tumors
Based on the distance regularized level set evolution model, this paper presents a phase-and GVF-based level set method for segmentation of ultrasonic breast tumors.First, by introducing the concept of monogenic signal, we use Cauchy kernels ratherthan Log Gabor as pair of quadrature filters for the multi-scale feature extraction.Second, phase asymmetry approach is then applied to multi-scale features to enhanceedges and remove noise effect. Third, based on precalculated edge map, an edgestopping term is defined and gradient vector flow (GVF) is then improved. At last, theedge stopping term and the resulting GVF are incorporated into the active contourmodel. The proposed method is insensitive to intensity inhomogeneities and noise dueto the use of local phase information. On the other hand, the proposed method cancapture concave boundaries and weak boundaries due to the use of GVF field.Experiments on clinical breast US images showed that the proposed method can extracttumor boundaries from breast US image, as compared to the state-of-the-art methods.
2. Segmentation of ultrasonic breast tumors based on homogeneous patch
This paper presents a novel algorithm based on homogeneous patches (HP) andNCut for segmentation of breast tumor in US images. A novel edge-detection functionis defined by combining intensity and texture information to look for boundaries in USimages. Subsequently, a kind of adaptive neighborhood according to image locationreferred to as homogeneous patch (HP), is proposed by using edge map from anedge-detection function. The HPs are guaranteed to spread within the same tissue region.Hence, the statistic features within HPs can better distinguish different tissues and,furthermore, improve accuracy in image segmentation. Each HP is considered as afuzzy set. The fuzzy distribution of textons in HPs is used as final image features andtumor segmentation is obtained by using the NCut method. The proposed method canavoid attenuation artifacts and decrease the likelihood that the surrounding structuresare misclassified as tumor. Experimental results from100breast sonogramsdemonstrated the improvement in accuracy and robustness in segmenting the breastultrasound images by the presented algorithm, as compared to the state-of-the-artmethods.
3.3-D segmentation of ultrasonic breast tumors based on homogeneous volumeand local energy
By taking the advantages of the classical Chan-Vese (CV) level set model andLankton method, this paper presents a novel level set active contour model based on homogeneous volume and local energy for3-D segmentation of ultrasonic breast tumors.First,3-D phase asymmetry approach is used to extract edge surface. And then at eachvoxel in3-D image, a quadric surface is fitted to estimate the edge energies based on theprecalculated edge surface. The fitted surface is continuous and smooth and isinsensitivity to noise. Second, based on the precalculated fitted surface, the concept of2-D homogeneous patch (HP) is extended to3-D homogeneous volume (HV), i.e., akind of adaptive neighborhood which can guarantee locally homogeneous neighborhoodin3-D. Third, local energies are defined at each voxel along the curve by usingdistribution of textons and mean intensity within HVs. Similar to HPs, using HVs helpsto discriminate those pixels with similar appearance but belonging to different tissues.At the same time, global energies are defined at each voxel along the curve by usingglobal statistics. When the contour is far from object boundaries, the force from theglobal energies is used to guide the contour toward and finally stops the contour atobject boundaries. At last, the local and global energies are incorporated into thegeometric active contour model and tumor segmentation is obtained by using the fastcurve evolution method. The proposed method can overcome the problem of intensityinhomogeneities and avoid falling into local extrema. Experiments on25clinical3-Dbreast US images showed that the proposed method can segment3-D ultrasonic breasttumors accurately, as compared to the state-of-the-art methods.
引文
[1] P. A. Wingo, P. M. Jamison, R. A. Hiatt, et al. Building the infrastructure for nationwide cancersurveillance and control-a comparison between the National Program of Cancer Registries(NPCR) and the Surveillance, Epidemiology, and End Results (SEER) Program (United States)[J]. Cancer Causes Control,2003,14(2):175-193
[2] Y. Zheng, J. F. Greenleaf, J. J. Gisvold. Reduction of breast biopsies with a modifiedself-organizing map[J]. IEEE Trans. Neural Netw.,1997,8(6):1386-1396
[3] A. C. Society. Breast Cancer Facts&Figures-2002[R]. Atlanta GA: American Cancer Society.2002
[4]李俊来，宋丹绯，张艳，等.B-CAD辅助乳腺超声检查诊断乳腺癌的价值[J].中国超声医学杂志，2009,25(2):124-127
[5]杨秉辉.癌的早期发现[M].上海：复旦大学出版社，2007,50-58
[6] B. J. Erickson, B. Bartholmai. Computer-aided detection and diagnosis at the start of the thirdmillennium[J]. Journal of Digital Imaging,2002,15(2):59-68
[7] S. G. Orel, M. D. Schnall. MR imaging of the breast for the detection, diagnosis, and staging ofbreast cancer[J]. Radiology,2001,220(1):13-30
[8] A. M. Schell, K. Rosenkranz, P. J. Lewis. Role of breast MRI in the preoperative evaluation ofpatients with newly diagnosed breast cancer[J]. Am. J. Roentgenol.,2009,192(5):1438-1444
[9]李雪娜，李亚明.乳腺癌FDG-PET显像的临床应用价值[J].中国临床医学影像杂志，2005,16(12):713-715
[10] F. Pons, J. Duch, D. Fuster. Breast cancer therapy: the role of PET-CT in decision making[J].Quarterly Journal of Nuclear Medicine and Molecular Imaging,2009,53(2):210-218
[11] P. C. Gotzsche, O. Olsen. Is screening for breast cancer with mammography justifiable[J]. TheLancet,2000,355(9198):129-134
[12] O. Olsen, P. C. G tzsche. Cochrane review on screening for breast cancer withmammography[J]. The Lancet,2000,358(9290):1340-1342
[13] G. Rahbar, A. C. Sie, G. C. Hansen, et al. Benign versus malignant solid breast masses: USdifferentiation[J]. Radiology,1999,213(3):889-894
[14] M. Kriege, C. T. M. Brekelmans, C. Boetes, et al. Efficacy of MRI and mammography forbreast-cancer screening in women with a familial or genetic predisposition[J]. New EnglandJournal of Medicine,2004,351(5):427-437
[15] M. Costantini, P. Belli, C. Ierardi, et al. Solid breast mass characterisation: use of thesonographic BI-RADS classification[J]. Radiol. Med.,2007,112:887-894
[16] N. N.Scally, W. Campbell, S. Hall, et al. Invasive ductal carcinoma arising within a breasthamartoma[J]. Ir J Med Sci.,2011,180(3):767-768
[17]郭章留.乳腺癌影像学检查的有关进展[J].临床放射学杂志，2002,21(9):738-740
[18]田家玮，陈宇，刘宇杰.高频超声与X线钼靶联合应用对早期乳腺癌的诊断价值[J].中国医学影像技术，2006,22(4):557-559
[19] A. T. Stavros, D. Thickman, C. L. Rapp, et al. Solid breast nodules: use of sonography todistinguish between benign and malignant lesions[J]. Radiology,1995,196(1):123-134
[20] H. Laine, J. Rainio, H. Arko, et al. Comparison of breast structure and findings by X-raymammography, ultrasound, cytology and histology: a retrospective study[J]. European Journalof Ultrasound,1995,2(2):107-115
[21] C. S. Park, J. H. Lee, H. W. Yim, et al. Observer agreement using the ACR breast imagingreporting and data system (BI-RADS)[J]. Korean Journal of Radiology,2007,8(5):397-402
[22] E. Lazarus, M. B. Mainiero, B. Schepps, et al. BI-RADS lexicon for US and mammography:interobserver variability and positive predictive value[J]. Radiology,2006,239(2):385-391
[23] J. A. Noble, D. Boukerroui. Ultrasound image segmentation: a survey[J]. IEEE Trans. Med.Imag.,2006,25(8):987-1010
[24]王新房.超声医学发展前景评述[J].中国超声医学杂志，2001,10(1):5-7
[25] Y. J. Yu, S. T. Acton. Speckle reducing anisotropic diffusion[J]. IEEE Trans. Image Process.,2002,11(11):1260-1270
[26] T. C. Asyal, K. E. Barner. Rayleigh-maximum-likelihood filtering for speckle reduction ofultrasound images[J]. IEEE Trans. Med. Imag.,2007,26(5):712-727
[27] H.D. Cheng, J. Shan, W. Jua, et al. Automated breast cancer detection and classification usingultrasound images: a survey[J]. Pattern Recognition,2010,43(1):299-317
[28] H.D. Cheng, X.H. Jiang, Y. Sun, et al. Color image segmentation: advances and prospects[J].Pattern Recognition,2001,34(12):2259-2281
[29] E. Littmann, H. Ritter. Adaptive color segmentation-a comparison of neural and statisticalmethods[J]. IEEE Trans. Neural Netw.,1997,8(1):175-185
[30]倪维平，严卫东，吴俊政，等.MSTAR图像2D Gabor滤波增强与自适应阈值分割[J].光电工程，2013,40(3):87-93
[31]朱代辉，林时苗，杨育彬.医学三维影像体数据阈值分割方法[J].计算机科学，2013,40(1):269-272
[32]胡锦美，李佐勇，张祖昌.基于等周理论的自动多级阈值分割方法[J].系统仿真学报，2013,25(1):150-157
[33] K. Horsch, M.L. Giger, L.A. Venta, et al. Computerized diagnosis of breast lesion onultrasound[J]. Med. Phys.,2002,29(2):157-164
[34] K. Horsch, M.L. Giger, L.A. Venta, et al. Automatic segmentation of breast lesion onultrasound[J]. Med. Phys.,2001,28(8):1652-1659
[35] S. Joo, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solid breast nodules onultrasound with digital image processing and artificial neural network[C]. Proceedings of the26th Annual International Conference of the IEEE EMBS, New York,2004,1397-1400
[36] S. Joo, Y. S. Yang, W. K. Moon, et al. Computer-aided diagnosis of solid breast nodules: use ofan artificial neural network based on multiple sonographic features[J]. IEEE Trans. Med. Imag.,2004,23(10):1292-1300
[37] C. K. Yeh, Y. S. Chen, W. C. Fan, et al. A disk expansion segmentation method for ultrasonicbreast lesions[J]. Pattern Recognition,2009,42(5):596-606
[38] J. Shan, H. D. Cheng, Y. Wang. A completely automatic segmentation method for breastultrasound images using region growing[C].11th Joint Conference on Information Science,Shenzhen,2008,72-77
[39]沈嘉琳，汪源源，王涌，等.基于灰度阈值分割和动态规划的超声图像乳腺肿瘤边缘提取[J].航天医学与医学工程，2005,18(4):281-286
[40]沈嘉琳，汪源源，王涌，等.一种超声乳腺图像中提取肿瘤边缘的方法[J].仪器仪表学报，2005,26(8):364-367
[41]于山山.乳腺肿瘤超声图像边缘提取的研究[D].青岛：中国海洋大学，2006,1-13
[42]朱云飞，汪天富，林江莉，等.基于模糊数的乳腺肿瘤超声图像边缘快速提取方法[J].生物医学工程学杂志，2006,23(3):488-491
[43]黄剑华，于瀛星，张英涛，等.基于一致性直方图的超声乳腺图片分割方法[J].哈尔滨工业大学学报，2008,40(7):1103-1106
[44] M. Kass, A. Witkin, D. Terzopoulos. Snakes-active contour models[J]. Int. J. Comput. Vis..1987,1(4):321-331
[45] A. Madabhushi, D. N. Metaxas. Combining low-, high-level and empirical domain knowledgefor automated segmentation of ultrasonic breast lesions[J]. IEEE Trans. Med. Imag.,2003,22(2):155-169
[46] M. Alemán, P. Alemán, L. Alvarez. Semiautomatic snake-based segmentation of solid breastnodules on ultrasonography[C]. Lectures Notes in Computer Science-EuroCast2005, LasPalmas de Gran Canaria, Spain,2005,467-472
[47] M. Alemán, P. Alemán, L. Alvarez, et al. Computer-aided measurement of solid breast tumorfeatures on ultrasound images[C]. Computer Vision Approaches to Medical Image Analysis,ECCV, Las Palmas, Spain,2004,353-364
[48] M. Alemán, L. Alvarez, Vicent Caselles. Texture-oriented anisotropic filtering and geodesicactive contours in breast tumor ultrasound segmentation[J]. J Math Imaging vis.,2007,28(1):81-97
[49]严加勇，庄天戈.基于边带限制的梯度矢量流主动轮廓线模型的超声图像分割[J].上海交通大学学报，2003,37(2):232-236
[50]林其忠，余建国，王怡.超声乳腺肿瘤图像的边缘提取[J].中国医学影像技术，2007,23(10):1572-1574
[51]林其忠.乳腺肿瘤超声图像的计算机辅助诊断方法研究[D].上海：上海复旦大学，2007,25-55
[52]赵暖，陈亚青，余建国，等.超声图像处理中Snake模型研究[J].上海生物医学工程，2004,25(4):3-9
[53]赵暖，陈亚青，余建国，等.Snake在乳腺肿瘤超声图像处理中的运用[J].上海医学影像，2005,14(1):10-12
[54]林其忠，余建国，赵暖，等.乳腺肿瘤超声图像的特征分析[J].仪器仪表学报，2006,27(6):744-747
[55] R. F. Chang, W. J. Wu, W. K. Moon, et al. Automatic ultrasound segmentation and morphologybased diagnosis of solid breast tumors[J]. Breast Cancer Res. Tr.,2005,89(2):179-185
[56] W. J. Wu, W. K. Moon. Ultrasound breast tumor image computer-aided diagnosis with textureand morphological features[J]. Acad. Radiol.,2008,15(7):873-880
[57] W. K. Moon, R. F. Chang, C. J. Chen, et al. Solid breast masses: classification withcomputer-aided analysis of continuous US images[J]. Radiology,2005,236(2):458-464
[58] A. Sarti, C. Corsi, E. Mazzini, et al. Maximum likelihood segmentation of ultrasound imageswith Rayleigh distribution[J]. IEEE Trans. Ultrason. Ferroelectrics Freq. Contr.,2005,52(6):947-960
[59] B. Liu, H. D. Cheng, J. Huang, et al. Probability density difference-based active contour forultrasound image segmentation[J]. Pattern Recognition.2010,43(6):2028-2042
[60]刘博，黄剑华，唐降龙，等.结合全局概率密度差异与局部灰度拟合的超声图像分割[J].自动化学报，2010,36(7):951-959
[61]刘博.乳腺超声图像中的肿瘤区域定位与肿瘤分类技术研究[D].哈尔滨：哈尔滨工业大学,2010,60-101
[62]黄韫栀，刘奇.基于LevelSet的超声乳腺肿瘤图像的轮廓提取[J].中国医学影像学杂志，2013,21(2):134-138
[63]杨晓霜，汪源源.基于局部调整动态轮廓模型提取超声图像乳腺肿瘤边缘[J].生物医学工程学进展，2008,29(2):63-66
[64]哈章，李传富，王金萍，等.基于改进C-V模型的乳腺肿瘤超声图像分割[J].中国医疗器械杂志，2007,31(6):395-399
[65] T. Chan, L.Vese. Active contours without edges[J]. IEEE Trans. Image Process.,2001,10(2):266-277
[66] A. Belaid, D. Boukerroui, Y. Maingourd, et al. Phase-based level set segmentation ofultrasound images[J]. IEEE Trans. Inf. Technol. Biomed.,2011,15(1):138-147
[67] S. G. Antunes,J. S Silva, J. B. Santos, et al. A new level set based segmentation method for thefour cardiac chambers[C]. The5th Iberian Conference on Information Systems andTechnologies (CISTI), Santiago de compostela,2010,1-6
[68] S. G. Antunes, J. S Silva, J. B. Santos, et al. Phase symmetry approach applied to children heartchambers segmentation: a comparative study[J]. IEEE Trans. Biomed. Eng.,2011,58(8):2264-2271
[69] J. S Silva, J. B. Santos, D. Roxo, et al. Algorithm versus physicians variability evaluation in thecardiac chambers extraction[J]. IEEE Trans. Inf. Technol. Biomed.,2012,16(5):835-841
[70] H.D. Cheng, L. Hu, J. Tian, et al. A novel markov random field segmentation algorithm and itsapplication to breast ultrasound image analysis[C]. The Sixth International Conference onComputer Vision, Pattern Recognition and Image Processing, Salt Lake City, USA,2005
[71] G. F. Xiao, M. Brady, J. A. Noble, et al. Segmentation of ultrasound B-mode images withintensity inhomogeneity correction[J]. IEEE Trans. Med. Imag.,2002,21(1):48-57
[72] E. A. Ashton, K. J. Parker. Multiple resolution bayesian segmentation of ultrasound images[J].Ultrason. Imag.,1995,17(4):291-304
[73] D. Boukerroui, O. Basset, N. Gu, et al. Multiresolution texture based adaptive clusteringalgorithm for breast lesion segmentation[J]. Eur. J. Ultrasound,1998,8(2):135-144
[74] D. Boukerroui, O. Basset, A. Baskurt, et al. A multiparametric and multiresolutionsegmentation algorithm of3D ultrasonic data[J]. IEEE Trans. Ultrason. Ferroelectrics Freq.Contr.,2001,48(1):64-77
[75]鲜敏.基于先验知识模型的乳腺超声图像自动分割技术研究[D].哈尔滨：哈尔滨工业大学,2011,18-30
[76] D.R. Chen, R.F. Chang, Y.L. Huang. Computer-aided diagnosis applied to us of solid breastnodules by using neural networks[J]. Radiology,1999,213(2):407-412
[77] D. R. Chen, R. F. Chang, W. J. Kuo, et al. Diagnosis of breast tumors with sonographic textureanalysis using wavelet transform and neural networks[J]. Ultrasound Med. Biol.,2002,28(10):1301-1310
[78] Y.L. Huang, D.R. Chen. Watershed segmentation for breast tumor in2-D sonography[J].Ultrasound Med. Biol.,2004,30(5):625-632
[79] K. Drukker, M. L. Giger, K. Horsch, et al. Computerized lesion detection on breastultrasound[J]. Med. Phys.,2002,29(7):1438-1446
[80]苏燕妮，汪源源.乳腺肿瘤超声图像中感兴趣区域的自动检测[J].中国生物医学工程学报，2010,29(2):178-186
[81]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[J].生物医学工程学杂志，2006,23(6):1237-1240
[82]汪源源，焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程，2011,19(6):1398-1405
[83] J. Shi, J. Malik. Normalized cuts and image segmentation[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2000,22(8):888-905
[84] Z Wu, R Leahy. An optimal graph theoretic approach to data clustering: theory and itsapplication to image segmentation[J].IEEE Trans. Pattern Anal. Mach.Intell.,1993,15(11):1101-1113
[85] S. Sarkar, P. Soundararajan. Supervised learning of large perceptual organization: Graphspectral partitioning and learning automata[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(5):504-525
[86] S Wang, J. M. Siskind. Image segmentation with ratio cut[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2003,25(6):675-690
[87] J. Malik, S. Belongie, T. Leung et al. Contour and texture analysis for image segmentation[J].Int. J. Comput. Vis.,2001,43(1):7-27
[88] J. Carballido-Gamio, S. J. Belongie, S. Majumdar. Normalized cuts in3-D for spinal MRIsegmentation[J]. IEEE Trans. Med. Imag.,2004,23(1):36-44
[89] C. Fowlkes, S. Belongie, F. Chung, et al. Spectral grouping using the Nystr m method[J].IEEETrans. Pattern Anal. Mach. Intell.,2004,26(2):214-225
[90] X. F. Ren. Local grouping for optical flow[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Anchorage, AK,2008,1-8
[91] T. Cour, F. Benezit, J. Shi. Spectral Segmentation with multiscale graph decomposition[C].Proc. IEEE Conf. Comput. Vis. Pattern Recognit., USA,2005,1124-1131
[92] T. K. Leung, J. Malik. Contour continuity in region based image segmentation[C]. Proc. Eur.Conf. Compu. Vis., Germany,1998,544-559
[93] S. X. Yu. Segmentation using multiscale cues[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Washington, DC,2004,1247-1254
[94] S. X. Yu. Segmentation induced by scale invariance[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Washington, DC,2005,444-451
[95]陈彦至.Ncut与医学图像分割[D].上海：东华大学，2009,31-48
[96]李纯,卢志茂，杨朋.基于快速谱聚类的图像分割算法[J].应用科技，2012,39(2):25-30
[97]王向荣.基于图论的医学X线图像分割方法硏究[D].北京：北京交通大学，2012,26-36
[98]周逊，郭敏，马苗.基于鱼群算法优化normalized cut的彩色图像分割方法.计算机应用研究[J].2013,30(2):616-618
[99] X. Liu, Z. M. Huo, J. W. Zhang. Automated segmentation of breast lesions in ultrasoundimages[C]. Proceedings of IEEE Annual International Conference on Engineering in MedicalBiology, Shanghai,2005,7433-7435
[100]阳维.乳腺肿瘤的超声图像特征定量分析与良恶性识别[D].上海：上海交通大学，2009,19-33
[101] C. M. Zhu, G. C. Gu, H. B. Liu, et al. Segmentation of ultrasound image based on texturefeature and graph cut[C]. Proceedings of IEEE International Conference on ComputerScience Software Engineering, Hubei, China,2008,795-798
[102] Q. H. Huang, S. Y. Lee, L. Z. Liu, et al. A robust graph-based segmentation method for breasttumors in ultrasound images[J]. Ultrasonics,2012,52(2):266-275
[103]冯林，孙焘，吴振宇，等.基于分水岭变换和图论的图像分割方法[J].仪器仪表学报，2008,29(3):649-653
[104] S. X. Yu, J. B. Shi. Segmentation given partial grouping constraints[J]. IEEE Trans. PatternAnal. Mach. Intell.,2004,26(2):173-183
[105] X. Wu, C. W. Ngo, A. G. Hauptmann. Multimodal news story clustering with pairwise visualnear-duplicate constraint[J]. IEEE Trans. Multimedia,2008,10(2):188-199
[106] W. B. Tao, H. Jin, Y. M. Zhang, et al. Image thresholding using graph cuts[J]. IEEE Trans.Syst., Man, Cybern. A, Syst, Hum.,2008,38(5):1181-1195
[107] K. Bria, B. Sugato, D. Inderjit, et al. Semi-supervised graph clustering: a kernel approach[J].Mach. Learn.,2009,74(1):1-22
[108] S. Y. Chen, H. H. Chang, S. H. Hung, et al. Breast tumor identification in ultrasound imagesusing the normalized cuts with partial grouping constraints[C]. Proceedings of IEEEInternational Conference on Biomedical Engineering and Informatics, Sanya,2008,28-32
[109] V. Caselles, R. Kimmel, G. Sapiro. Geodesic active contours[J]. Int. J. Comput. Visi.,1997,22(1):61-79
[110] C. M. Li, C. Y. Xu, C. F. Gui, et al. Level set evolution without re-initialization; a newvariational formulation[C]. IEEE, Computer Vision and Pattern Recognition. San Diego, CA,2005,430-436
[111] C. M. Li, C. Y. Xu, K. M. Konwar, et al. Fast distance preserving level set evolution formedical image segmentation[C]. Proc. of the9th Int’l Conf. on Control, Automation, Roboticsand Vision, Grand Hyatt Singapore,2006,1-7
[112] C. M. Li, C. Y. Xu, K. M. Konwar, et al. Distance regularized level set evolution and itsapplication to image segmentation[J]. IEEE Trans. Image Process.,2010,19(20):3243-3254
[113] S. Lankton, A.Tannenbaum. A localizing region-based active contours[J]. IEEE Trans. ImageProcess.,2008,17(11):2029-2039
[114] S. Taheri, S.H. Ong, V.F.H. Chong. Level-set segmentation of brain tumors using athreshold-based speed function[J]. Image and Vision Computing,2010,28(1):26-37
[115] D. R. Chen, R. F. Chang, W. J. Wu, et al.3-D Breast ultrasound segmentation using activecontour model[J]. Ultrasound Med. Biol.,2003,29(7):1017-1026
[116] R. F. Chang, W. J. Wu, W. K. Moon, et al. Segmentation of breast tumor in three-dimensionalultrasound images using three-dimensional discrete active contour model[J]. Ultrasound Med.Biol.,2003,29(11):1571-1581
[117] R. F. Chang, W. J. Wu, C. C. Tseng, et al.3-D snake for US in margin evaluation formalignant breast tumor excision using mammotome[J]. IEEE Trans. Inf. Tech. Biomed.2003,7(3):197-201
[118] B. Sahiner, H. P. Chan, M. A. Roubidoux, et al. Computerized characterization of breastmasses on three dimensional ultrasound volumes[J]. Med. Phys.,2004,31(4):744-754
[119] L.A. Christopher, E.J. Delp, C.R. Meyer, et al.3-D Bayesian ultrasound breast imagesegmentation using the EM/MPM algorithm[C]. Proceedings of the2002IEEE InternationalSymposium on Biomedical Imaging, USA,2002,86-89
[120] J.A. Sethian. Level set methods and fast marching methods: evolving interfaces incomputational geometry, fluid mechanics, computer vision, computer-aided design, optimalcontrol and material sciences[M]. London: Cambridge University Press,1999,7-12
[121] D. Adalsteinsson, J.Sethian. A fast level set method for propagating interfaces[J]. J. Comput.Phys.,1995,118(2):269-277
[122] J.A. Sethian. A fast marching level set method for monotonically advancing fronts[C].Proceedings of the National Academy of Sciences. USA,1993,93(4):1591-1595
[123]郑强，董恩清.窄带主动轮廓模型及在医学和纹理图像局部分割中的应用[J].中国医学影像学杂志,2013,39(1):21-30
[124] S.O sher, J.A Sethian. Fronts propagation with curvature-dependent speed: algorithms basedon Hamilton-Jacobi formulations[J]. J. Comput. Phys.,1988,79(1):12-49
[125] J.Sethian. Curvature and the evolution of fronts[J]. Commun. Math. Phys.,1985,101(4):487-499
[126] R.Malladi, J.Sethian. Level set methods for curvature flow, image enhancement, and shaperecovery in medical images[J]. Visualization and Mathematics: Experiments, Simulations andEnvironments,1997:329-345
[127] M. Grayson. Shortening embedded curves[J]. The Annals of Mathematics,1989,129(1):71-111
[128] M. Grayson. The heat equation shrinks embedded plane curves to round points[J]. J. Differ.Geom.,1987,26(2):285-314
[129] R.Malladi, J.Sethian, B.vemuri. Evolutionary fronts for topology-independent shape modelingand recovery[C]. Proceedings of the third European conference on Computer Vision,1994,3-13
[130]罗红根，朱利民，丁汉.基于主动轮廓模型和水平集方法的图像分割技术[J].中国图像图形学报，2006,11(3):301-309
[131] S.Osher, R.Fredkiw. Level set methods: an overview and some recent results[J]. J. Comput.Phys.,2001,169(2):463-502
[132]李俊.基于曲线圆滑的图像分割方法及应用研究[D].上海：上海交通大学，2001,1-27
[133] S.Osher, R.Tsai. Level set methods and their applications in image science[J]. Comm.Math.Sciences.2003,1(4):1-20
[134] T.Barth, J.Sethian. Numerical schemes for the hamilton-jacobi and level set equations ontriangulated domains[J]. J. Comput. Phys.,1998,145(1):1-40
[135]陈波，赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图像图形学报，2007,12(1):11-20
[136] D. Chopp. Computing minimal surfaces via level set curvature flow[J]. J. Comput. Phys.,1993,106(1):77-91
[137] J.Weickert, B.Romeny, M.Viergever. Efficient and reliable schemes for nonlinear diffusionfiltering[J]. IEEE Trans. Image Process.,1998,7(3):398-410
[138] J. Gomes, O. Faugeras. Reconciling distance functions and level sets[J]. Journal of VisualCommunication and Image Representation,2000,11(2):209-223
[139] M. Sussman, P. Smereka, S. Osher. A level set approach for computing solutions toincompressible two-phase flow[J]. Comput. Phys.1994,114(1),:146-159
[140] A. V. Oppenheim, J. S. Lim. The importance of phase in signals[C]. Proceedings of the IEEE,USA,1981,69(5):529-541
[141] G. H. Granlund, H. Knutsson. Signal processing for computer vision[M]. Norwell, MA:Kluwer Academic Publisher,1995,259-275
[142] M. Felsberg, G. Sommer. The monogenic scale-space: a unifying approach to phase-basedimage processing in scale-space[J]. J. Math. Imag. Vis.,2004,20(1):5-26
[143] D. Boukerroui, J. A. Noble, M. Brady. On the choice of band-pass quadrature filters[J]. J.Math. Imaging Vis.,2004,21(1):53-80
[144] P. Kovesi. Phase congruency: a low-level image invariant[J]. Psychological Research,2000,64(2):136-148
[145] C. Xu, J. L. Prince. Snakes, shapes, and gradient vector flow[J]. IEEE Trans. Image Process.,1998,7(3):359-369
[146] C. Xu, J. L. Prince. Generalized gradient vector flow external forces for active contours[J].Signal Processing,1998,71(2):131-139
[147] D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge. Comparing images using theHausdorff distance[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1993,15(9):850-863
[148] B. Sahiner, N. Petrick, H.-P. Chan, et al. Computer-aided characterization of mammographicmasses: Accuracy of mass segmentation and its effects on characterization[J]. IEEE Trans.Med. Imag.,2001,20(12):1275-1284
[149] J. K. Udupa, V. R. Lablanc, H. Schmidt, et al. A methodology for evaluating imagesegmentation algorithms[C]. Proc. SPIE, San Diego. CA,2002,266-277
[150] Y.Wang and P.Liatsis. Automatic segmentation of coronary arteries in CT imaging in thepresence of kissing vessel artifacts[J]. IEEE Trans. Inf. Technol. Biomed.,2012,16(4):782-788
[151] S.X. Yu, J. Shi. Multiclass spectral clustering[C]. Proceedings of the Ninth IEEE InternationalConference on Computer Vision, Nice, France,2003,313-319
[152] Y. Q. Zhan, D. G. Shen. Deformable segmentation of3-D ultrasound prostate images usingstatistical texture matching method[J]. IEEE Trans. Med. Imag.,2006,25(3):256-272
[153] D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detect natural image boundaries usinglocal brightness, color and texture cues[J]. IEEE Trans. Pattern Anal. Mach. Intell,2004,26(5):530-549
[154] D. G. Shen, Y. Q. Zhan, C. Davatzikos. Segmentation of prostate boundaries from ultrasoundimages using statistical shape model[J]. IEEE Trans. Med. Imag.,2003,22(4):539-551
[155] K. Somkantha, N. Theera-Umpon, S. Auephanwiriyakul. Boundary detection in medicalimages using edge following algorithm based on intensity gradient and texture gradientfeatures[J]. IEEE Trans. Inf. Technol. Biomed.2011,58(3):567-573
[156] X. Ren, J. Malik. Learning a classification model for segmentation[C]. Proceedings of IEEEInternational Conference on Computer Vision, Nice, France,2003,10-17
[157] A. Levinshtein, A. Stere, K. N. Kutulakos, et al. Turbopixels: fast superpixels using geometricflows[J]. IEEE Trans. Pattern Anal. Mach. Intell.2009,31(12):2290-2297
[158] S. M. Xiang, C. H. Pan, F. P. Nie, et al. Turbopixel segmentation using eigen-images[J]. IEEETrans. Image Process.,2010,19(1):3024-3034
[159] Q. Wang, G. R. Wu, P.-T. Yap, et al. Attribute vector guided groupwise registration[J].Neuroimage,2010,50(4):1485-1496
[160] I.B. Tutar, S.D. Pathak, L.X. Gong, et al. Semiautomatic3-D prostate segmentation fromTRUS images using spherical harmonics[J]. IEEE Trans. Med. Imag.,2006,25(12):1645-1654
[161] M. G. Linguraru, W. J. Richbourg, J. F. Liu, et al. Tumor burden analysis on computedtomography by automated liver and tumor segmentation[J]. IEEE Trans. Med. Imag.,2012,31(10):1965-1976
[162] M. Goryawala, M. R. Guillen, M. Cabrerizo, et al. A3-D liver segmentation method withparallel computing for selective internal radiation therapy[J]. IEEE Trans. Inf. Technol.Biomed.,2012,16(1):62-69
[163] P. H. Lim, U. Bagci, Li Bai. Introducing willmore flow into level set segmentation of spinalvertebrae[J]. IEEE Trans. Biomed. Eng.,2013,60(1):115-122
[164] X.S. Yang, Y.Y Wang. Extracting boundaries of ultrasonic breast tumor images based on acoarse-to-fine active contour model[C]. ICALIP, Shanghai, China,2008,157-162
[165] C.M. Li., C.-Y.Kao, J.C. Gore., et al. Minimization of region-scalable fitting energy for imageSegmentation[J]. IEEE Trans. Image Process.,2008,10(17):1940-1949
[166] C.M. Li Active contours with local binary fitting energy[C]. IMA workshop on newmathematics and algorithms for3-D image analysis,2006
[167] C.M. Li, C. Kao, J. Gore, Z. Ding. Implicit active contours driven by local binary fittingenergy[C]. Proceedings of IEEE conference on computer vision and pattern recognition(CVPR), Minneapolis, Minnesota, USA,2007,1-7
[168] C. Darolti, A. Mertins, C. Bodensteiner, et al. Local region descriptors for active contoursevolution[J]. IEEE Trans. Image Process.,2008,12(17):2275-2288
[169] D.Barbosa, T.Dietenbeck, D.Friboulet, et al. Real-time region-based segmentation of3dinhomogeneous objects in Medical images[C]. ISBI, Chicago, IL,2011,1986-1989
[170] D. Barbosa, O. Bernard, O. Savu, et al. Coupled B-spline active geometric functions formyocardial segmentation: a localized region-based approach[C].2010IEEE InternationalUltrasonics Symposium Proceedings, San Diego, CA,2010,1648-1651
[171] D. Barbosa,T. Dietenbeck, J.Schaerer, et al. B-spline explicit active surfaces: an efficientframework for real-time3-D region-based segmentation[J]. IEEE Trans. Image Process.,2012,21(1):241-251
[172] D. Mumford, J. Shah. Optimal approximations by piecewise smooth functions and associatedvariational problems[J]. Communications on Pure and Applied Mathematics,1989,42(5):577-685
[173] D. Mumford, J. Shah. Boundary detection by minimizing functions[C]. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition, San Francisco. CA, USA,1985,22-26
[174] R. Dosil, X.M. Pardo, X.R. Fdez-Vidal. Decomposition of three-dimensional medical imagesinto visual patterns[J]. IEEE Trans. Biomed. Eng.,2005,52(12):2115-2118
[175] R.J. Ferrari, S. Allaire, A. Hope, et al. Detection of point landmarks in3D medical images viaphase congruency model[J]. J Braz Comput Soc,2011,17(2):117-132
[176] J. Amanatides, A. Woo. A fast voxel traversal algorithm for ray tracing[C]. Proceedings ofEurographics’87, North-holland,1987,3-10
[177]李俊，杨新，施鹏飞.基于Mumford-shah模型的快速水平集图像分割方法[J].计算机学报，2002,25(11):1175-1183
[178]郝家胜.基于几何流的医学图像分割方法及其应用研究[D].哈尔滨：哈尔滨工业大学，2008,61-63
[2] Y. Zheng, J. F. Greenleaf, J. J. Gisvold. Reduction of breast biopsies with a modifiedself-organizing map[J]. IEEE Trans. Neural Netw.,1997,8(6):1386-1396
[3] A. C. Society. Breast Cancer Facts&Figures-2002[R]. Atlanta GA: American Cancer Society.2002
[4]李俊来，宋丹绯，张艳，等.B-CAD辅助乳腺超声检查诊断乳腺癌的价值[J].中国超声医学杂志，2009,25(2):124-127
[5]杨秉辉.癌的早期发现[M].上海：复旦大学出版社，2007,50-58
[6] B. J. Erickson, B. Bartholmai. Computer-aided detection and diagnosis at the start of the thirdmillennium[J]. Journal of Digital Imaging,2002,15(2):59-68
[7] S. G. Orel, M. D. Schnall. MR imaging of the breast for the detection, diagnosis, and staging ofbreast cancer[J]. Radiology,2001,220(1):13-30
[8] A. M. Schell, K. Rosenkranz, P. J. Lewis. Role of breast MRI in the preoperative evaluation ofpatients with newly diagnosed breast cancer[J]. Am. J. Roentgenol.,2009,192(5):1438-1444
[9]李雪娜，李亚明.乳腺癌FDG-PET显像的临床应用价值[J].中国临床医学影像杂志，2005,16(12):713-715
[10] F. Pons, J. Duch, D. Fuster. Breast cancer therapy: the role of PET-CT in decision making[J].Quarterly Journal of Nuclear Medicine and Molecular Imaging,2009,53(2):210-218
[11] P. C. Gotzsche, O. Olsen. Is screening for breast cancer with mammography justifiable[J]. TheLancet,2000,355(9198):129-134
[12] O. Olsen, P. C. G tzsche. Cochrane review on screening for breast cancer withmammography[J]. The Lancet,2000,358(9290):1340-1342
[13] G. Rahbar, A. C. Sie, G. C. Hansen, et al. Benign versus malignant solid breast masses: USdifferentiation[J]. Radiology,1999,213(3):889-894
[14] M. Kriege, C. T. M. Brekelmans, C. Boetes, et al. Efficacy of MRI and mammography forbreast-cancer screening in women with a familial or genetic predisposition[J]. New EnglandJournal of Medicine,2004,351(5):427-437
[15] M. Costantini, P. Belli, C. Ierardi, et al. Solid breast mass characterisation: use of thesonographic BI-RADS classification[J]. Radiol. Med.,2007,112:887-894
[16] N. N.Scally, W. Campbell, S. Hall, et al. Invasive ductal carcinoma arising within a breasthamartoma[J]. Ir J Med Sci.,2011,180(3):767-768
[17]郭章留.乳腺癌影像学检查的有关进展[J].临床放射学杂志，2002,21(9):738-740
[18]田家玮，陈宇，刘宇杰.高频超声与X线钼靶联合应用对早期乳腺癌的诊断价值[J].中国医学影像技术，2006,22(4):557-559
[19] A. T. Stavros, D. Thickman, C. L. Rapp, et al. Solid breast nodules: use of sonography todistinguish between benign and malignant lesions[J]. Radiology,1995,196(1):123-134
[20] H. Laine, J. Rainio, H. Arko, et al. Comparison of breast structure and findings by X-raymammography, ultrasound, cytology and histology: a retrospective study[J]. European Journalof Ultrasound,1995,2(2):107-115
[21] C. S. Park, J. H. Lee, H. W. Yim, et al. Observer agreement using the ACR breast imagingreporting and data system (BI-RADS)[J]. Korean Journal of Radiology,2007,8(5):397-402
[22] E. Lazarus, M. B. Mainiero, B. Schepps, et al. BI-RADS lexicon for US and mammography:interobserver variability and positive predictive value[J]. Radiology,2006,239(2):385-391
[23] J. A. Noble, D. Boukerroui. Ultrasound image segmentation: a survey[J]. IEEE Trans. Med.Imag.,2006,25(8):987-1010
[24]王新房.超声医学发展前景评述[J].中国超声医学杂志，2001,10(1):5-7
[25] Y. J. Yu, S. T. Acton. Speckle reducing anisotropic diffusion[J]. IEEE Trans. Image Process.,2002,11(11):1260-1270
[26] T. C. Asyal, K. E. Barner. Rayleigh-maximum-likelihood filtering for speckle reduction ofultrasound images[J]. IEEE Trans. Med. Imag.,2007,26(5):712-727
[27] H.D. Cheng, J. Shan, W. Jua, et al. Automated breast cancer detection and classification usingultrasound images: a survey[J]. Pattern Recognition,2010,43(1):299-317
[28] H.D. Cheng, X.H. Jiang, Y. Sun, et al. Color image segmentation: advances and prospects[J].Pattern Recognition,2001,34(12):2259-2281
[29] E. Littmann, H. Ritter. Adaptive color segmentation-a comparison of neural and statisticalmethods[J]. IEEE Trans. Neural Netw.,1997,8(1):175-185
[30]倪维平，严卫东，吴俊政，等.MSTAR图像2D Gabor滤波增强与自适应阈值分割[J].光电工程，2013,40(3):87-93
[31]朱代辉，林时苗，杨育彬.医学三维影像体数据阈值分割方法[J].计算机科学，2013,40(1):269-272
[32]胡锦美，李佐勇，张祖昌.基于等周理论的自动多级阈值分割方法[J].系统仿真学报，2013,25(1):150-157
[33] K. Horsch, M.L. Giger, L.A. Venta, et al. Computerized diagnosis of breast lesion onultrasound[J]. Med. Phys.,2002,29(2):157-164
[34] K. Horsch, M.L. Giger, L.A. Venta, et al. Automatic segmentation of breast lesion onultrasound[J]. Med. Phys.,2001,28(8):1652-1659
[35] S. Joo, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solid breast nodules onultrasound with digital image processing and artificial neural network[C]. Proceedings of the26th Annual International Conference of the IEEE EMBS, New York,2004,1397-1400
[36] S. Joo, Y. S. Yang, W. K. Moon, et al. Computer-aided diagnosis of solid breast nodules: use ofan artificial neural network based on multiple sonographic features[J]. IEEE Trans. Med. Imag.,2004,23(10):1292-1300
[37] C. K. Yeh, Y. S. Chen, W. C. Fan, et al. A disk expansion segmentation method for ultrasonicbreast lesions[J]. Pattern Recognition,2009,42(5):596-606
[38] J. Shan, H. D. Cheng, Y. Wang. A completely automatic segmentation method for breastultrasound images using region growing[C].11th Joint Conference on Information Science,Shenzhen,2008,72-77
[39]沈嘉琳，汪源源，王涌，等.基于灰度阈值分割和动态规划的超声图像乳腺肿瘤边缘提取[J].航天医学与医学工程，2005,18(4):281-286
[40]沈嘉琳，汪源源，王涌，等.一种超声乳腺图像中提取肿瘤边缘的方法[J].仪器仪表学报，2005,26(8):364-367
[41]于山山.乳腺肿瘤超声图像边缘提取的研究[D].青岛：中国海洋大学，2006,1-13
[42]朱云飞，汪天富，林江莉，等.基于模糊数的乳腺肿瘤超声图像边缘快速提取方法[J].生物医学工程学杂志，2006,23(3):488-491
[43]黄剑华，于瀛星，张英涛，等.基于一致性直方图的超声乳腺图片分割方法[J].哈尔滨工业大学学报，2008,40(7):1103-1106
[44] M. Kass, A. Witkin, D. Terzopoulos. Snakes-active contour models[J]. Int. J. Comput. Vis..1987,1(4):321-331
[45] A. Madabhushi, D. N. Metaxas. Combining low-, high-level and empirical domain knowledgefor automated segmentation of ultrasonic breast lesions[J]. IEEE Trans. Med. Imag.,2003,22(2):155-169
[46] M. Alemán, P. Alemán, L. Alvarez. Semiautomatic snake-based segmentation of solid breastnodules on ultrasonography[C]. Lectures Notes in Computer Science-EuroCast2005, LasPalmas de Gran Canaria, Spain,2005,467-472
[47] M. Alemán, P. Alemán, L. Alvarez, et al. Computer-aided measurement of solid breast tumorfeatures on ultrasound images[C]. Computer Vision Approaches to Medical Image Analysis,ECCV, Las Palmas, Spain,2004,353-364
[48] M. Alemán, L. Alvarez, Vicent Caselles. Texture-oriented anisotropic filtering and geodesicactive contours in breast tumor ultrasound segmentation[J]. J Math Imaging vis.,2007,28(1):81-97
[49]严加勇，庄天戈.基于边带限制的梯度矢量流主动轮廓线模型的超声图像分割[J].上海交通大学学报，2003,37(2):232-236
[50]林其忠，余建国，王怡.超声乳腺肿瘤图像的边缘提取[J].中国医学影像技术，2007,23(10):1572-1574
[51]林其忠.乳腺肿瘤超声图像的计算机辅助诊断方法研究[D].上海：上海复旦大学，2007,25-55
[52]赵暖，陈亚青，余建国，等.超声图像处理中Snake模型研究[J].上海生物医学工程，2004,25(4):3-9
[53]赵暖，陈亚青，余建国，等.Snake在乳腺肿瘤超声图像处理中的运用[J].上海医学影像，2005,14(1):10-12
[54]林其忠，余建国，赵暖，等.乳腺肿瘤超声图像的特征分析[J].仪器仪表学报，2006,27(6):744-747
[55] R. F. Chang, W. J. Wu, W. K. Moon, et al. Automatic ultrasound segmentation and morphologybased diagnosis of solid breast tumors[J]. Breast Cancer Res. Tr.,2005,89(2):179-185
[56] W. J. Wu, W. K. Moon. Ultrasound breast tumor image computer-aided diagnosis with textureand morphological features[J]. Acad. Radiol.,2008,15(7):873-880
[57] W. K. Moon, R. F. Chang, C. J. Chen, et al. Solid breast masses: classification withcomputer-aided analysis of continuous US images[J]. Radiology,2005,236(2):458-464
[58] A. Sarti, C. Corsi, E. Mazzini, et al. Maximum likelihood segmentation of ultrasound imageswith Rayleigh distribution[J]. IEEE Trans. Ultrason. Ferroelectrics Freq. Contr.,2005,52(6):947-960
[59] B. Liu, H. D. Cheng, J. Huang, et al. Probability density difference-based active contour forultrasound image segmentation[J]. Pattern Recognition.2010,43(6):2028-2042
[60]刘博，黄剑华，唐降龙，等.结合全局概率密度差异与局部灰度拟合的超声图像分割[J].自动化学报，2010,36(7):951-959
[61]刘博.乳腺超声图像中的肿瘤区域定位与肿瘤分类技术研究[D].哈尔滨：哈尔滨工业大学,2010,60-101
[62]黄韫栀，刘奇.基于LevelSet的超声乳腺肿瘤图像的轮廓提取[J].中国医学影像学杂志，2013,21(2):134-138
[63]杨晓霜，汪源源.基于局部调整动态轮廓模型提取超声图像乳腺肿瘤边缘[J].生物医学工程学进展，2008,29(2):63-66
[64]哈章，李传富，王金萍，等.基于改进C-V模型的乳腺肿瘤超声图像分割[J].中国医疗器械杂志，2007,31(6):395-399
[65] T. Chan, L.Vese. Active contours without edges[J]. IEEE Trans. Image Process.,2001,10(2):266-277
[66] A. Belaid, D. Boukerroui, Y. Maingourd, et al. Phase-based level set segmentation ofultrasound images[J]. IEEE Trans. Inf. Technol. Biomed.,2011,15(1):138-147
[67] S. G. Antunes,J. S Silva, J. B. Santos, et al. A new level set based segmentation method for thefour cardiac chambers[C]. The5th Iberian Conference on Information Systems andTechnologies (CISTI), Santiago de compostela,2010,1-6
[68] S. G. Antunes, J. S Silva, J. B. Santos, et al. Phase symmetry approach applied to children heartchambers segmentation: a comparative study[J]. IEEE Trans. Biomed. Eng.,2011,58(8):2264-2271
[69] J. S Silva, J. B. Santos, D. Roxo, et al. Algorithm versus physicians variability evaluation in thecardiac chambers extraction[J]. IEEE Trans. Inf. Technol. Biomed.,2012,16(5):835-841
[70] H.D. Cheng, L. Hu, J. Tian, et al. A novel markov random field segmentation algorithm and itsapplication to breast ultrasound image analysis[C]. The Sixth International Conference onComputer Vision, Pattern Recognition and Image Processing, Salt Lake City, USA,2005
[71] G. F. Xiao, M. Brady, J. A. Noble, et al. Segmentation of ultrasound B-mode images withintensity inhomogeneity correction[J]. IEEE Trans. Med. Imag.,2002,21(1):48-57
[72] E. A. Ashton, K. J. Parker. Multiple resolution bayesian segmentation of ultrasound images[J].Ultrason. Imag.,1995,17(4):291-304
[73] D. Boukerroui, O. Basset, N. Gu, et al. Multiresolution texture based adaptive clusteringalgorithm for breast lesion segmentation[J]. Eur. J. Ultrasound,1998,8(2):135-144
[74] D. Boukerroui, O. Basset, A. Baskurt, et al. A multiparametric and multiresolutionsegmentation algorithm of3D ultrasonic data[J]. IEEE Trans. Ultrason. Ferroelectrics Freq.Contr.,2001,48(1):64-77
[75]鲜敏.基于先验知识模型的乳腺超声图像自动分割技术研究[D].哈尔滨：哈尔滨工业大学,2011,18-30
[76] D.R. Chen, R.F. Chang, Y.L. Huang. Computer-aided diagnosis applied to us of solid breastnodules by using neural networks[J]. Radiology,1999,213(2):407-412
[77] D. R. Chen, R. F. Chang, W. J. Kuo, et al. Diagnosis of breast tumors with sonographic textureanalysis using wavelet transform and neural networks[J]. Ultrasound Med. Biol.,2002,28(10):1301-1310
[78] Y.L. Huang, D.R. Chen. Watershed segmentation for breast tumor in2-D sonography[J].Ultrasound Med. Biol.,2004,30(5):625-632
[79] K. Drukker, M. L. Giger, K. Horsch, et al. Computerized lesion detection on breastultrasound[J]. Med. Phys.,2002,29(7):1438-1446
[80]苏燕妮，汪源源.乳腺肿瘤超声图像中感兴趣区域的自动检测[J].中国生物医学工程学报，2010,29(2):178-186
[81]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[J].生物医学工程学杂志，2006,23(6):1237-1240
[82]汪源源，焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程，2011,19(6):1398-1405
[83] J. Shi, J. Malik. Normalized cuts and image segmentation[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2000,22(8):888-905
[84] Z Wu, R Leahy. An optimal graph theoretic approach to data clustering: theory and itsapplication to image segmentation[J].IEEE Trans. Pattern Anal. Mach.Intell.,1993,15(11):1101-1113
[85] S. Sarkar, P. Soundararajan. Supervised learning of large perceptual organization: Graphspectral partitioning and learning automata[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(5):504-525
[86] S Wang, J. M. Siskind. Image segmentation with ratio cut[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2003,25(6):675-690
[87] J. Malik, S. Belongie, T. Leung et al. Contour and texture analysis for image segmentation[J].Int. J. Comput. Vis.,2001,43(1):7-27
[88] J. Carballido-Gamio, S. J. Belongie, S. Majumdar. Normalized cuts in3-D for spinal MRIsegmentation[J]. IEEE Trans. Med. Imag.,2004,23(1):36-44
[89] C. Fowlkes, S. Belongie, F. Chung, et al. Spectral grouping using the Nystr m method[J].IEEETrans. Pattern Anal. Mach. Intell.,2004,26(2):214-225
[90] X. F. Ren. Local grouping for optical flow[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Anchorage, AK,2008,1-8
[91] T. Cour, F. Benezit, J. Shi. Spectral Segmentation with multiscale graph decomposition[C].Proc. IEEE Conf. Comput. Vis. Pattern Recognit., USA,2005,1124-1131
[92] T. K. Leung, J. Malik. Contour continuity in region based image segmentation[C]. Proc. Eur.Conf. Compu. Vis., Germany,1998,544-559
[93] S. X. Yu. Segmentation using multiscale cues[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Washington, DC,2004,1247-1254
[94] S. X. Yu. Segmentation induced by scale invariance[C]. Proc. IEEE Conf. Comput. Vis. PatternRecognit., Washington, DC,2005,444-451
[95]陈彦至.Ncut与医学图像分割[D].上海：东华大学，2009,31-48
[96]李纯,卢志茂，杨朋.基于快速谱聚类的图像分割算法[J].应用科技，2012,39(2):25-30
[97]王向荣.基于图论的医学X线图像分割方法硏究[D].北京：北京交通大学，2012,26-36
[98]周逊，郭敏，马苗.基于鱼群算法优化normalized cut的彩色图像分割方法.计算机应用研究[J].2013,30(2):616-618
[99] X. Liu, Z. M. Huo, J. W. Zhang. Automated segmentation of breast lesions in ultrasoundimages[C]. Proceedings of IEEE Annual International Conference on Engineering in MedicalBiology, Shanghai,2005,7433-7435
[100]阳维.乳腺肿瘤的超声图像特征定量分析与良恶性识别[D].上海：上海交通大学，2009,19-33
[101] C. M. Zhu, G. C. Gu, H. B. Liu, et al. Segmentation of ultrasound image based on texturefeature and graph cut[C]. Proceedings of IEEE International Conference on ComputerScience Software Engineering, Hubei, China,2008,795-798
[102] Q. H. Huang, S. Y. Lee, L. Z. Liu, et al. A robust graph-based segmentation method for breasttumors in ultrasound images[J]. Ultrasonics,2012,52(2):266-275
[103]冯林，孙焘，吴振宇，等.基于分水岭变换和图论的图像分割方法[J].仪器仪表学报，2008,29(3):649-653
[104] S. X. Yu, J. B. Shi. Segmentation given partial grouping constraints[J]. IEEE Trans. PatternAnal. Mach. Intell.,2004,26(2):173-183
[105] X. Wu, C. W. Ngo, A. G. Hauptmann. Multimodal news story clustering with pairwise visualnear-duplicate constraint[J]. IEEE Trans. Multimedia,2008,10(2):188-199
[106] W. B. Tao, H. Jin, Y. M. Zhang, et al. Image thresholding using graph cuts[J]. IEEE Trans.Syst., Man, Cybern. A, Syst, Hum.,2008,38(5):1181-1195
[107] K. Bria, B. Sugato, D. Inderjit, et al. Semi-supervised graph clustering: a kernel approach[J].Mach. Learn.,2009,74(1):1-22
[108] S. Y. Chen, H. H. Chang, S. H. Hung, et al. Breast tumor identification in ultrasound imagesusing the normalized cuts with partial grouping constraints[C]. Proceedings of IEEEInternational Conference on Biomedical Engineering and Informatics, Sanya,2008,28-32
[109] V. Caselles, R. Kimmel, G. Sapiro. Geodesic active contours[J]. Int. J. Comput. Visi.,1997,22(1):61-79
[110] C. M. Li, C. Y. Xu, C. F. Gui, et al. Level set evolution without re-initialization; a newvariational formulation[C]. IEEE, Computer Vision and Pattern Recognition. San Diego, CA,2005,430-436
[111] C. M. Li, C. Y. Xu, K. M. Konwar, et al. Fast distance preserving level set evolution formedical image segmentation[C]. Proc. of the9th Int’l Conf. on Control, Automation, Roboticsand Vision, Grand Hyatt Singapore,2006,1-7
[112] C. M. Li, C. Y. Xu, K. M. Konwar, et al. Distance regularized level set evolution and itsapplication to image segmentation[J]. IEEE Trans. Image Process.,2010,19(20):3243-3254
[113] S. Lankton, A.Tannenbaum. A localizing region-based active contours[J]. IEEE Trans. ImageProcess.,2008,17(11):2029-2039
[114] S. Taheri, S.H. Ong, V.F.H. Chong. Level-set segmentation of brain tumors using athreshold-based speed function[J]. Image and Vision Computing,2010,28(1):26-37
[115] D. R. Chen, R. F. Chang, W. J. Wu, et al.3-D Breast ultrasound segmentation using activecontour model[J]. Ultrasound Med. Biol.,2003,29(7):1017-1026
[116] R. F. Chang, W. J. Wu, W. K. Moon, et al. Segmentation of breast tumor in three-dimensionalultrasound images using three-dimensional discrete active contour model[J]. Ultrasound Med.Biol.,2003,29(11):1571-1581
[117] R. F. Chang, W. J. Wu, C. C. Tseng, et al.3-D snake for US in margin evaluation formalignant breast tumor excision using mammotome[J]. IEEE Trans. Inf. Tech. Biomed.2003,7(3):197-201
[118] B. Sahiner, H. P. Chan, M. A. Roubidoux, et al. Computerized characterization of breastmasses on three dimensional ultrasound volumes[J]. Med. Phys.,2004,31(4):744-754
[119] L.A. Christopher, E.J. Delp, C.R. Meyer, et al.3-D Bayesian ultrasound breast imagesegmentation using the EM/MPM algorithm[C]. Proceedings of the2002IEEE InternationalSymposium on Biomedical Imaging, USA,2002,86-89
[120] J.A. Sethian. Level set methods and fast marching methods: evolving interfaces incomputational geometry, fluid mechanics, computer vision, computer-aided design, optimalcontrol and material sciences[M]. London: Cambridge University Press,1999,7-12
[121] D. Adalsteinsson, J.Sethian. A fast level set method for propagating interfaces[J]. J. Comput.Phys.,1995,118(2):269-277
[122] J.A. Sethian. A fast marching level set method for monotonically advancing fronts[C].Proceedings of the National Academy of Sciences. USA,1993,93(4):1591-1595
[123]郑强，董恩清.窄带主动轮廓模型及在医学和纹理图像局部分割中的应用[J].中国医学影像学杂志,2013,39(1):21-30
[124] S.O sher, J.A Sethian. Fronts propagation with curvature-dependent speed: algorithms basedon Hamilton-Jacobi formulations[J]. J. Comput. Phys.,1988,79(1):12-49
[125] J.Sethian. Curvature and the evolution of fronts[J]. Commun. Math. Phys.,1985,101(4):487-499
[126] R.Malladi, J.Sethian. Level set methods for curvature flow, image enhancement, and shaperecovery in medical images[J]. Visualization and Mathematics: Experiments, Simulations andEnvironments,1997:329-345
[127] M. Grayson. Shortening embedded curves[J]. The Annals of Mathematics,1989,129(1):71-111
[128] M. Grayson. The heat equation shrinks embedded plane curves to round points[J]. J. Differ.Geom.,1987,26(2):285-314
[129] R.Malladi, J.Sethian, B.vemuri. Evolutionary fronts for topology-independent shape modelingand recovery[C]. Proceedings of the third European conference on Computer Vision,1994,3-13
[130]罗红根，朱利民，丁汉.基于主动轮廓模型和水平集方法的图像分割技术[J].中国图像图形学报，2006,11(3):301-309
[131] S.Osher, R.Fredkiw. Level set methods: an overview and some recent results[J]. J. Comput.Phys.,2001,169(2):463-502
[132]李俊.基于曲线圆滑的图像分割方法及应用研究[D].上海：上海交通大学，2001,1-27
[133] S.Osher, R.Tsai. Level set methods and their applications in image science[J]. Comm.Math.Sciences.2003,1(4):1-20
[134] T.Barth, J.Sethian. Numerical schemes for the hamilton-jacobi and level set equations ontriangulated domains[J]. J. Comput. Phys.,1998,145(1):1-40
[135]陈波，赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图像图形学报，2007,12(1):11-20
[136] D. Chopp. Computing minimal surfaces via level set curvature flow[J]. J. Comput. Phys.,1993,106(1):77-91
[137] J.Weickert, B.Romeny, M.Viergever. Efficient and reliable schemes for nonlinear diffusionfiltering[J]. IEEE Trans. Image Process.,1998,7(3):398-410
[138] J. Gomes, O. Faugeras. Reconciling distance functions and level sets[J]. Journal of VisualCommunication and Image Representation,2000,11(2):209-223
[139] M. Sussman, P. Smereka, S. Osher. A level set approach for computing solutions toincompressible two-phase flow[J]. Comput. Phys.1994,114(1),:146-159
[140] A. V. Oppenheim, J. S. Lim. The importance of phase in signals[C]. Proceedings of the IEEE,USA,1981,69(5):529-541
[141] G. H. Granlund, H. Knutsson. Signal processing for computer vision[M]. Norwell, MA:Kluwer Academic Publisher,1995,259-275
[142] M. Felsberg, G. Sommer. The monogenic scale-space: a unifying approach to phase-basedimage processing in scale-space[J]. J. Math. Imag. Vis.,2004,20(1):5-26
[143] D. Boukerroui, J. A. Noble, M. Brady. On the choice of band-pass quadrature filters[J]. J.Math. Imaging Vis.,2004,21(1):53-80
[144] P. Kovesi. Phase congruency: a low-level image invariant[J]. Psychological Research,2000,64(2):136-148
[145] C. Xu, J. L. Prince. Snakes, shapes, and gradient vector flow[J]. IEEE Trans. Image Process.,1998,7(3):359-369
[146] C. Xu, J. L. Prince. Generalized gradient vector flow external forces for active contours[J].Signal Processing,1998,71(2):131-139
[147] D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge. Comparing images using theHausdorff distance[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1993,15(9):850-863
[148] B. Sahiner, N. Petrick, H.-P. Chan, et al. Computer-aided characterization of mammographicmasses: Accuracy of mass segmentation and its effects on characterization[J]. IEEE Trans.Med. Imag.,2001,20(12):1275-1284
[149] J. K. Udupa, V. R. Lablanc, H. Schmidt, et al. A methodology for evaluating imagesegmentation algorithms[C]. Proc. SPIE, San Diego. CA,2002,266-277
[150] Y.Wang and P.Liatsis. Automatic segmentation of coronary arteries in CT imaging in thepresence of kissing vessel artifacts[J]. IEEE Trans. Inf. Technol. Biomed.,2012,16(4):782-788
[151] S.X. Yu, J. Shi. Multiclass spectral clustering[C]. Proceedings of the Ninth IEEE InternationalConference on Computer Vision, Nice, France,2003,313-319
[152] Y. Q. Zhan, D. G. Shen. Deformable segmentation of3-D ultrasound prostate images usingstatistical texture matching method[J]. IEEE Trans. Med. Imag.,2006,25(3):256-272
[153] D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detect natural image boundaries usinglocal brightness, color and texture cues[J]. IEEE Trans. Pattern Anal. Mach. Intell,2004,26(5):530-549
[154] D. G. Shen, Y. Q. Zhan, C. Davatzikos. Segmentation of prostate boundaries from ultrasoundimages using statistical shape model[J]. IEEE Trans. Med. Imag.,2003,22(4):539-551
[155] K. Somkantha, N. Theera-Umpon, S. Auephanwiriyakul. Boundary detection in medicalimages using edge following algorithm based on intensity gradient and texture gradientfeatures[J]. IEEE Trans. Inf. Technol. Biomed.2011,58(3):567-573
[156] X. Ren, J. Malik. Learning a classification model for segmentation[C]. Proceedings of IEEEInternational Conference on Computer Vision, Nice, France,2003,10-17
[157] A. Levinshtein, A. Stere, K. N. Kutulakos, et al. Turbopixels: fast superpixels using geometricflows[J]. IEEE Trans. Pattern Anal. Mach. Intell.2009,31(12):2290-2297
[158] S. M. Xiang, C. H. Pan, F. P. Nie, et al. Turbopixel segmentation using eigen-images[J]. IEEETrans. Image Process.,2010,19(1):3024-3034
[159] Q. Wang, G. R. Wu, P.-T. Yap, et al. Attribute vector guided groupwise registration[J].Neuroimage,2010,50(4):1485-1496
[160] I.B. Tutar, S.D. Pathak, L.X. Gong, et al. Semiautomatic3-D prostate segmentation fromTRUS images using spherical harmonics[J]. IEEE Trans. Med. Imag.,2006,25(12):1645-1654
[161] M. G. Linguraru, W. J. Richbourg, J. F. Liu, et al. Tumor burden analysis on computedtomography by automated liver and tumor segmentation[J]. IEEE Trans. Med. Imag.,2012,31(10):1965-1976
[162] M. Goryawala, M. R. Guillen, M. Cabrerizo, et al. A3-D liver segmentation method withparallel computing for selective internal radiation therapy[J]. IEEE Trans. Inf. Technol.Biomed.,2012,16(1):62-69
[163] P. H. Lim, U. Bagci, Li Bai. Introducing willmore flow into level set segmentation of spinalvertebrae[J]. IEEE Trans. Biomed. Eng.,2013,60(1):115-122
[164] X.S. Yang, Y.Y Wang. Extracting boundaries of ultrasonic breast tumor images based on acoarse-to-fine active contour model[C]. ICALIP, Shanghai, China,2008,157-162
[165] C.M. Li., C.-Y.Kao, J.C. Gore., et al. Minimization of region-scalable fitting energy for imageSegmentation[J]. IEEE Trans. Image Process.,2008,10(17):1940-1949
[166] C.M. Li Active contours with local binary fitting energy[C]. IMA workshop on newmathematics and algorithms for3-D image analysis,2006
[167] C.M. Li, C. Kao, J. Gore, Z. Ding. Implicit active contours driven by local binary fittingenergy[C]. Proceedings of IEEE conference on computer vision and pattern recognition(CVPR), Minneapolis, Minnesota, USA,2007,1-7
[168] C. Darolti, A. Mertins, C. Bodensteiner, et al. Local region descriptors for active contoursevolution[J]. IEEE Trans. Image Process.,2008,12(17):2275-2288
[169] D.Barbosa, T.Dietenbeck, D.Friboulet, et al. Real-time region-based segmentation of3dinhomogeneous objects in Medical images[C]. ISBI, Chicago, IL,2011,1986-1989
[170] D. Barbosa, O. Bernard, O. Savu, et al. Coupled B-spline active geometric functions formyocardial segmentation: a localized region-based approach[C].2010IEEE InternationalUltrasonics Symposium Proceedings, San Diego, CA,2010,1648-1651
[171] D. Barbosa,T. Dietenbeck, J.Schaerer, et al. B-spline explicit active surfaces: an efficientframework for real-time3-D region-based segmentation[J]. IEEE Trans. Image Process.,2012,21(1):241-251
[172] D. Mumford, J. Shah. Optimal approximations by piecewise smooth functions and associatedvariational problems[J]. Communications on Pure and Applied Mathematics,1989,42(5):577-685
[173] D. Mumford, J. Shah. Boundary detection by minimizing functions[C]. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition, San Francisco. CA, USA,1985,22-26
[174] R. Dosil, X.M. Pardo, X.R. Fdez-Vidal. Decomposition of three-dimensional medical imagesinto visual patterns[J]. IEEE Trans. Biomed. Eng.,2005,52(12):2115-2118
[175] R.J. Ferrari, S. Allaire, A. Hope, et al. Detection of point landmarks in3D medical images viaphase congruency model[J]. J Braz Comput Soc,2011,17(2):117-132
[176] J. Amanatides, A. Woo. A fast voxel traversal algorithm for ray tracing[C]. Proceedings ofEurographics’87, North-holland,1987,3-10
[177]李俊，杨新，施鹏飞.基于Mumford-shah模型的快速水平集图像分割方法[J].计算机学报，2002,25(11):1175-1183
[178]郝家胜.基于几何流的医学图像分割方法及其应用研究[D].哈尔滨：哈尔滨工业大学，2008,61-63
© 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 |