CN103098090B - 多参数三维磁共振图像脑肿瘤分割方法 - Google Patents
多参数三维磁共振图像脑肿瘤分割方法 Download PDFInfo
- Publication number
- CN103098090B CN103098090B CN201180030783.2A CN201180030783A CN103098090B CN 103098090 B CN103098090 B CN 103098090B CN 201180030783 A CN201180030783 A CN 201180030783A CN 103098090 B CN103098090 B CN 103098090B
- Authority
- CN
- China
- Prior art keywords
- image
- tumor
- probability
- information
- brain tumor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 208000003174 Brain Neoplasms Diseases 0.000 title claims abstract description 34
- 238000005192 partition Methods 0.000 title abstract 7
- 238000002595 magnetic resonance imaging Methods 0.000 title 1
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 89
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 230000011218 segmentation Effects 0.000 claims description 46
- 238000006116 polymerization reaction Methods 0.000 claims description 11
- 230000003902 lesion Effects 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 210000005013 brain tissue Anatomy 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims 1
- 238000012549 training Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000000638 solvent extraction Methods 0.000 abstract 1
- JXSJBGJIGXNWCI-UHFFFAOYSA-N diethyl 2-[(dimethoxyphosphorothioyl)thio]succinate Chemical compound CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC JXSJBGJIGXNWCI-UHFFFAOYSA-N 0.000 description 5
- 210000004556 brain Anatomy 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 208000006274 Brain Stem Neoplasms Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 208000035269 cancer or benign tumor Diseases 0.000 description 1
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 210000004884 grey matter Anatomy 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000003045 statistical classification method Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000004885 white matter Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S128/00—Surgery
- Y10S128/92—Computer assisted medical diagnostics
- Y10S128/922—Computer assisted medical diagnostics including image analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
对多参数三维磁共振图像进行脑肿瘤自动分割的方法,对图像中每个体素进行分类并获取其属于脑肿瘤区域的概率;提取图像的多尺度结构信息;基于初始脑肿瘤概率图像和图像的多尺度结构信息构建多尺度的脑肿瘤概率图像;基于多尺度的脑肿瘤概率图像确定显著的肿瘤区域;基于初始图像的肿瘤概率信息和显著肿瘤区域获取鲁棒的肿瘤分割初始标签;使用基于图论的标签传播方法分割脑肿瘤区域。本发明获取统计上可靠的、空间上紧凑的且具有足够体素数目的鲁棒肿瘤分割初始标签信息,有利于肿瘤分割结果的准确性和可靠性。基于标签传播的分割方法在一定程度上降低个体图像间灰度差异和训练统计信息不充分对分割结果造成的影响,提高了肿瘤分割的稳定性。
Description
技术领域
本发明涉及医学图像处理技术领域,特别涉及对多参数三维磁共振图像进行脑肿瘤自动分割的方法。
背景技术
在医学影像诊断中,对磁共振脑图像中的脑肿瘤区域进行分割具有重要的意义。准确的脑肿瘤区域分割能够为临床诊断、手术计划的制定和治疗效果的评估提供重要的信息。在当前的临床应用中往往由专家对肿瘤区域进行手工分割,不仅费时、费力,而且分割结果容易受到专家知识水平、临床经验以及其他一些主观因素的影响。因此,开发准确、可重复的脑肿瘤自动分割算法具有重要的实际意义。
近年来,研究人员提出多种肿瘤的自动分割方法,如基于统计分类的方法、基于聚类的方法、基于动态轮廓模型的方法。包含空间限制的统计分类方法取得了较好的分割结果,但待分割图像和训练图像的之间的不一致性会显著降低这类方法的效果;而基于聚类或动态轮廓模型的方法往往需要合理的初始化参数以得到可靠的分割结果。为了降低个体图像间的不一致性造成的影响并提高算法的辨别能力,基于图的交互式分割算法越来越多的被应用到医学图像分割中,如图割、随机行走等。这类方法首先从用户输入的目标区域和背景区域提取对应的统计模型,然后利用基于模型的数据项和基于空间限制的平滑项计算最终的分割结果。因此,目标区域和背景区域选取的位置、大小对分割的结果具有重要的影响。然而,在三维图像中初始区域的手工选择也是一个耗时的过程,其稳定性也会受到图像质量的影响,尤其是在目标区域边界比较模糊的情况下。
相关研究人员也提出了自动的目标区域和背景区域的初始化方法。这些方法一般使用统计分类方法对图像进行预分割,然后对预分割的结果使用阈值、形态学操作进行后处理,进而得到初始的目标区域和背景区域,如文献Li et al.,“Segmentation of Brain Tumorsin Multi-parametric MR Images via Robust Statistic InformationPropagation”,ACCV 2010,pgs.606-617;Wang et al.,“FullAutomatic Brain Tumor Segmentation Using A Normalized GaussianBayesian Classifier and 3D Fluid Vector Flow”,ICIP 2010,pgs.2553-2556。然而,对于不同的图像,后处理过程中的相关参数往往差异比较大,影响初始化的结果,从而降低最终分割结果的准确性。
发明内容
本发明提供一种对多参数三维磁共振图像进行脑肿瘤自动分割的方法。
为了实现上述目的,一种对多参数三维磁共振图像进行脑肿瘤自动分割的方法,包括步骤:
对图像中每个体素进行分类并获取其属于脑肿瘤区域的概率;
提取图像的多尺度结构信息;
基于初始脑肿瘤概率图像和图像的多尺度结构信息构建多尺度的脑肿瘤概率图像;
基于多尺度的脑肿瘤概率图像确定显著的肿瘤区域;
基于初始图像的肿瘤概率信息和显著肿瘤区域获取鲁棒的肿瘤分割初始标签;
使用基于图论的标签传播方法分割脑肿瘤区域。
本发明能够获取统计上可靠的、空间上紧凑的且具有足够体素数目的鲁棒肿瘤分割初始标签信息,有利于提高肿瘤分割结果的准确性和可靠性。基于标签传播的分割方法能够在一定程度上降低个体图像间灰度差异和训练统计信息不充分对分割结果造成的影响,提高肿瘤分割的稳定性。
附图说明
图1是包含肿瘤的多参数磁共振脑图像;
图2是本发明一种实施方式的流程图;
图3是多尺度磁共振图像和肿瘤概率图像的示意图;
图4是边界尺度检测过程的示意图;
图5是对图1中脑肿瘤图像进行分割的结果。
具体实施方式
下面结合附图详细说明本发明技术方案中所涉及的各个细节问题。应指出的是,所描述的实施例仅旨在便于对本发明的理解,而不起任何限定作用。
本发明的实施目的是对多参数三维磁共振图像进行脑肿瘤区域的自动分割。使用的多参数三维磁共振图像包括T1加权像,T2加权像以及FLAIR加权像。如图1所示,图像102、104、106分别展示了一层不同参数磁共振图像的轴状位视图,其中102为T1加权像,104为T2加权像,106为对FLAIR加权像;图像108展示了由专家手工分割的脑肿瘤区域。
本发明综合利用由训练图像得到的统计肿瘤信息和待分割图像自身的多尺度结构信息确定鲁棒的肿瘤分割初始标签,进而使用基于图的标签传播方法进行肿瘤区域的精确分割。基于支持向量机的分类器利用各体素的图像上下文信息进行分类以提供统计肿瘤信息;基于体素间图像特征相似性的聚合方法递归地对图像进行粗化以提取多尺度的图像结构信息;基于统计肿瘤信息和多尺度图像结构构建多尺度的统计肿瘤信息,并根据多尺度统计肿瘤信息的变化趋势使用感知显著点检测的方法确定显著的肿瘤区域;结合统计肿瘤信息和显著肿瘤区域确定鲁棒的肿瘤分割初始标签;最后基于图的标签传播方法依据图像体素之间的灰度相似性、空间结构邻近性,通过优化相应的目标函数获得最终的分割结果。
图2展示了使用本方法进行多参数磁共振图像脑肿瘤自动分割的流程。
在步骤202中,读取多参数三维磁共振图像,其中包括T1加权像,T2加权像,FLAIR加权像;因此,多参数图像中的每个体素包含三个灰度值,对应于三个脉冲序列的图像。
在步骤204中,对多参数三维磁共振图像进行预处理,其步骤主要包括:1)多参数图像间的图像配准以消除可能存在的头动影响;2)去除图像中的非脑组织;3)图像偏差场校正以减轻图像的灰度不均匀性;4)不同个体图像间的灰度标准化。具体实施方法可参阅文献:Smith et al.,“Advances in Functional and Structural MRimage Analysis and Implementation as FSL”,NeuroImage 23(2004),pgs.208-219;Smith,“Fast robust Automated BrainExtraction”,Human Brain Mapping 17(2002),pgs.143155;Sledet al.,“A Nonparametric Method for Automatic Correction ofIntensity Non-uniformity in MRI Data”,IEEE Trans.Med.Imaging 17(1998),pgs.87-97。
在步骤206中,使用在训练图像集上训练得到的基于支持向量机的分类器对待分割图像中每个体素进行分类并计算其属于肿瘤区域的概率,从而得到初始肿瘤概率图像。对于每个体素,本实施方法中使用其空间邻域内所有节点的多参数图像灰度信息构成特征向量,作为支持向量机的输入。训练支持向量机所使用的相关参数通过交叉验证的方法确定。支持向量机将每个体素分类为肿瘤或非肿瘤并输出相应的分类概率。由于利用传统的支持向量机进行分类没有考虑分割结果的空间限制,往往会产生一些错分的孤立的假阳性肿瘤区域,如图5的504所示。
在步骤208中,根据体素之间图像特征的相似性通过聚合的方式提取图像自身的多尺度结构信息。多尺度的图像信息能够为目标区域的检测提供更为鲁棒和丰富的信息,本实施方法中采用了高效的SWA方法提取多尺度的图像信息,具体实施方式可参阅文献:E.Sharon,et al,“Fast multiscale image segmentation”,CVPR 2000,pgs.70-77。SWA方法递归地粗化初始图像:根据体素之间图像特征的相似性将性质相似的体素聚合成为体元并计算其统计图像特征,进而递归地根据体元间统计图像特征的相似性进一步聚合,直至整个图像聚合成为唯一一个体元,从而生成多尺度的图像层级结构。这个图像层级结构包含了不同尺度上的图像表示:在层级结构的底部,不同的体素/体元表示不同的脑组织结构,如灰质、白质、脑脊液、水肿区域、肿瘤区域、肿瘤坏死区域等;随着层级的升高,不同的体元表示更为概略的信息,如非肿瘤区域、肿瘤区域等;在层级结构的顶部,非肿瘤区域和肿瘤区域聚合成混合区域。
在步骤212中,基于由步骤206得到的初始肿瘤概率图像和由步骤208得到的多尺度图像结构信息构建多尺度的肿瘤概率图像,即将初始脑肿瘤概率图像作为初始图像,使用基于多参数图像得到的层级结构对其进行聚合。这个过程等价于基于图像结构的自适应的图像平滑过程,能够自适应的去除由于传统统计分类过程中缺少空间限制而导致的离散的肿瘤概率值较高的区域。多尺度的磁共振图像和肿瘤概率图像如图3所示,其中图302至图310为不同尺度的FLAIR图像,图312至图320为不同尺度的肿瘤概率图像。
在步骤214中,基于多尺度的肿瘤概率图像确定显著的肿瘤区域。原始SWA算法中并没有包含目标区域检测的方法,本实施方法中利用感知显著点检测的方法从多尺度的肿瘤概率图像中确定显著的肿瘤区域,具体实施方式可参阅参考文献:F.L.Chung,et al,“Anevolutionary approach to pattern-based time seriessegmentation”,IEEE Transactions on Evolutionary Computation8(2004),pgs.471-489。由多尺度的图像层级结构生成过程可以预见,肿瘤概率图像的多尺度聚合过程可以分为两个阶段:在第一阶段,非肿瘤区域的体素、肿瘤区域的体素分别聚合成较大尺度上的体元;在第二阶段,当尺度超过一定的阈值时,非肿瘤区域和肿瘤区域聚合成混合区域。对于单个体素来讲,随着聚合的尺度不断增加,其对应的统计肿瘤概率值会发生相应的变化,本方法中将这个变化过程记作该体素的统计肿瘤概率变化轨迹。由于在聚合的第一阶段,一般都是具有相同性质的体素/体元间的聚合,可以预见其统计肿瘤概率不会发生剧烈的变化;在聚合进行到第二阶段时,不同性质的体元聚合成混合区域,其统计肿瘤概率将会发生剧烈的变化,本方法中将此时的尺度记作边界尺度。本方法使用每个体素统计肿瘤概率变化轨迹的第一个感知显著点来确定其边界尺度,其计算方法如下:
其中Tps为该体素在尺度s的肿瘤概率,Tp0和Tpe分别是在第一个和最后一个尺度上的肿瘤概率值。第一个感知显著点的检测过程如图4的402所示。在确定了所有体素的边界尺度之后,整个图像的边界尺度由投票策略确定,体素边界尺度发生次数最多的尺度即为图像的边界尺度,其过程如图4的404所示。显著肿瘤区域在图像边界尺度的肿瘤概率图像中通过以下方法确定:首先计算边界尺度的概率图像中所有体元的肿瘤概率的均值和标准差;然后肿瘤概率值大于均值超过一个标准差的体元被认为是显著的肿瘤区域。这种检测方法能够处理包含多个肿瘤区域的图像。
在步骤216中,根据原始图像的肿瘤概率信息和显著肿瘤区域确定肿瘤分割的初始标签:区域SVMt∩Candt中的体素标记为初始肿瘤区域,区域(SVMt∪Candt)\(SVMt∩Candt)中的体素记为未标记区域,其余的体素记为非肿瘤区域,其中SVMt为由初始肿瘤概率确定的肿瘤区域,Candt为步骤214中确定的显著肿瘤区域。由此过程确定的分割初始标签能够同时保持统计的可靠性和空间分布的紧凑性,仅对可靠分类的体素进行标签初始化,以减少由于个体图像差异对分割造成的不良影响。
在步骤210和218中,为待分割图像建立图的表示并基于步骤216中得到的鲁棒分割初始估计使用基于标签传播的方法获得最终分割结果。基于图的分割方法将待分割图像看作一个加权图G(V,E),其中V中的每个节点对应图像中的每个体素,E中的每条边对应一对节点之间的关系,并被赋予权重以度量两端节点特征的相似性。在图的表示下,肿瘤区域分割问题转化为对图中每个节点赋予前景或背景的标签值,分别表示肿瘤区域和非肿瘤区域。由聚类假设可知,邻近的节点或者处于相同特征结构上的节点可能具有相同的标签值。因此,给定部分标记节点的标签信息,未标记节点的标签值可以根据节点间的特征一致性由标记节点的标签信息推测获得。关于图的建立及目标函数优化过程、在肿瘤图像分割中的应用过程可参阅文献:Zhou etal.,“Learning with local and global consistency”,Advancesin Neural Information Processing Systems(2004),pgs.321-328;Li et al.,“Segmentation of Brain Tumors in Multi-parametricMR Images via Robust Statistic Information Propagation”,ACCV2010,pgs.606-617。
在步骤220中,输出分割的脑肿瘤区域:分割的肿瘤区域可以通过将二值掩膜图像覆盖到多参数磁共振图像上得到。
图5给出了使用本方法对图1中所示磁共振图像进行脑肿瘤分割得到的结果。其中,图502为FLAIR加权像(和图1中106相同);图504为单独使用基于支持向量机的分类器进行肿瘤分割得到的结果;图506为单独基于初始肿瘤概率图像通过阈值、形态学操作确定的标签初始化的结果(蓝色为肿瘤,红色为非肿瘤);图510为基于多尺度肿瘤概率图像和SWA方法得到的显著肿瘤区域;图像512为本方法得到的鲁棒的初始化标签;图像508为本方法得到的最终分割结果。通过图像506和512相比较可以看出,综合利用统计分类器的结果以及图像自身的多尺度结构能够提取到统计上可靠、空间分布紧凑的初始化标签,有助于提高最终分割结果的准确性;通过图508和图108相比较可以看出,本方法能够准确地对脑肿瘤区域进行分割。
以上所述,仅为本发明中的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉该技术的人在本发明所披露的技术范围内,可理解想到的变换或替换,都应涵盖在本发明的包含范围之内,因此,本发明的保护范围应该以权利要求书的保护范围为准。
Claims (9)
1.一种对多参数三维磁共振图像进行脑肿瘤自动分割的方法,包括步骤:
对图像中每个体素进行分类并获取其属于脑肿瘤区域的概率;
提取图像的多尺度结构信息;
基于初始脑肿瘤概率图像和图像的多尺度结构信息构建多尺度的脑肿瘤概率图像;
基于多尺度的脑肿瘤概率图像确定显著的肿瘤区域;
基于初始图像的肿瘤概率信息和显著肿瘤区域获取鲁棒的肿瘤分割初始标签;
使用基于图论的标签传播方法分割脑肿瘤区域;
所述提取图像的多尺度结构信息包括:基于体素间图像特征相似性的聚合方法提取图像的多尺度结构,其中根据体素间图像特征的相似性,将性质相似的体素聚合成体元并计算其对应的肿瘤概率,进而递归地根据体元间图像特征的相似性进行聚合,直至将整幅图像聚合成一个体元,从而得到多尺度的图像结构,在图像递归聚合的同时得到肿瘤概率的多尺度概率图。
2.按权利要求1所述的方法,其特征在于还包括图像预处理步骤:
多参数图像间的图像配准以实现多参数图像的空间一致性;
去除图像中的非脑组织;
图像偏差场校正以减轻图像的灰度不均匀性;
不同个体图像间的灰度标准化。
3.按权利要求1所述的方法,其特征在于所述对图像中每个体素进行分类并获取其属于肿瘤区域的概率包括:
使用基于支持向量机的分类器进行分类并获取所述概率。
4.按权利要求3所述的方法,其特征在于对于多参数磁共振图像中的每一个体素,根据其一空间邻域内所有体素的多参数灰度信息构建特征向量,进而使用支持向量机进行分类并获取其属于肿瘤区域的概率。
5.按权利要求1所述的方法,其特征在于所述确定显著的肿瘤区域包括
计算边界尺度的概率图像中所有体元的肿瘤概率的均值和标准差;
肿瘤概率值大于均值且肿瘤概率值与均值的差值超过一个标准差的体元被认为是显著的肿瘤区域。
6.按权利要求1所述的方法,其特征在于所述基于图论的标签传播方法包括:
基于图像信息构建相应的图结构;
初始化图结构的标签信息;
迭代地求解基于图的能量函数。
7.按权利要求6所述的方法,其特征在于所述基于图像信息构建相应的图结构包括:
构建无向加权图,其中每个节点对应于多参数磁共振图像中的一个体素,每条边的权重对应于所连接两节点的特征相似性度量。
8.按权利要求6所述的方法,其特征在于所述初始化图结构的标签信息包括:
图中各节点具有一个标签值,根据各节点对应的初始肿瘤概率以及检测得到的显著肿瘤区域确定节点初始标签。
9.按权利要求6所述的方法,其特征在于所述基于图的能量函数包括最终标记结果、初始标记一致性的度量、以及节点之间标记一致性的度量。
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2011/084340 WO2013091186A1 (zh) | 2011-12-21 | 2011-12-21 | 多参数三维磁共振图像脑肿瘤分割方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103098090A CN103098090A (zh) | 2013-05-08 |
CN103098090B true CN103098090B (zh) | 2015-01-21 |
Family
ID=48208636
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201180030783.2A Expired - Fee Related CN103098090B (zh) | 2011-12-21 | 2011-12-21 | 多参数三维磁共振图像脑肿瘤分割方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US8908948B2 (zh) |
CN (1) | CN103098090B (zh) |
WO (1) | WO2013091186A1 (zh) |
Families Citing this family (115)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9456054B2 (en) | 2008-05-16 | 2016-09-27 | Palo Alto Research Center Incorporated | Controlling the spread of interests and content in a content centric network |
WO2009146388A1 (en) * | 2008-05-28 | 2009-12-03 | The Trustees Of Columbia University In The City Of New York | Voxel-based methods for assessing subjects using positron emission tomography |
US8923293B2 (en) | 2009-10-21 | 2014-12-30 | Palo Alto Research Center Incorporated | Adaptive multi-interface use for content networking |
JP6136537B2 (ja) * | 2013-04-26 | 2017-05-31 | オムロン株式会社 | 画像処理装置、画像処理方法、画像処理制御プログラム、および記録媒体 |
US9400834B2 (en) * | 2013-12-06 | 2016-07-26 | Palo Alto Research Center Incorporated | Efficient detection of information of interest using mode-based graph clustering |
EP3077990A1 (en) * | 2013-12-06 | 2016-10-12 | Koninklijke Philips N.V. | Bone segmentation from image data |
AU2014362251B2 (en) | 2013-12-12 | 2019-10-10 | Conventus Orthopaedics, Inc. | Tissue displacement tools and methods |
US10098051B2 (en) | 2014-01-22 | 2018-10-09 | Cisco Technology, Inc. | Gateways and routing in software-defined manets |
US9954678B2 (en) | 2014-02-06 | 2018-04-24 | Cisco Technology, Inc. | Content-based transport security |
US9836540B2 (en) | 2014-03-04 | 2017-12-05 | Cisco Technology, Inc. | System and method for direct storage access in a content-centric network |
US9626413B2 (en) | 2014-03-10 | 2017-04-18 | Cisco Systems, Inc. | System and method for ranking content popularity in a content-centric network |
US9716622B2 (en) | 2014-04-01 | 2017-07-25 | Cisco Technology, Inc. | System and method for dynamic name configuration in content-centric networks |
US9473576B2 (en) | 2014-04-07 | 2016-10-18 | Palo Alto Research Center Incorporated | Service discovery using collection synchronization with exact names |
US9992281B2 (en) | 2014-05-01 | 2018-06-05 | Cisco Technology, Inc. | Accountable content stores for information centric networks |
US9609014B2 (en) | 2014-05-22 | 2017-03-28 | Cisco Systems, Inc. | Method and apparatus for preventing insertion of malicious content at a named data network router |
US9699198B2 (en) | 2014-07-07 | 2017-07-04 | Cisco Technology, Inc. | System and method for parallel secure content bootstrapping in content-centric networks |
US9621354B2 (en) | 2014-07-17 | 2017-04-11 | Cisco Systems, Inc. | Reconstructable content objects |
US9729616B2 (en) | 2014-07-18 | 2017-08-08 | Cisco Technology, Inc. | Reputation-based strategy for forwarding and responding to interests over a content centric network |
US9590887B2 (en) | 2014-07-18 | 2017-03-07 | Cisco Systems, Inc. | Method and system for keeping interest alive in a content centric network |
US9754371B2 (en) * | 2014-07-31 | 2017-09-05 | California Institute Of Technology | Multi modality brain mapping system (MBMS) using artificial intelligence and pattern recognition |
US9882964B2 (en) | 2014-08-08 | 2018-01-30 | Cisco Technology, Inc. | Explicit strategy feedback in name-based forwarding |
US9729662B2 (en) | 2014-08-11 | 2017-08-08 | Cisco Technology, Inc. | Probabilistic lazy-forwarding technique without validation in a content centric network |
US9800637B2 (en) | 2014-08-19 | 2017-10-24 | Cisco Technology, Inc. | System and method for all-in-one content stream in content-centric networks |
US10069933B2 (en) | 2014-10-23 | 2018-09-04 | Cisco Technology, Inc. | System and method for creating virtual interfaces based on network characteristics |
US9590948B2 (en) | 2014-12-15 | 2017-03-07 | Cisco Systems, Inc. | CCN routing using hardware-assisted hash tables |
US10237189B2 (en) | 2014-12-16 | 2019-03-19 | Cisco Technology, Inc. | System and method for distance-based interest forwarding |
US10003520B2 (en) | 2014-12-22 | 2018-06-19 | Cisco Technology, Inc. | System and method for efficient name-based content routing using link-state information in information-centric networks |
US9660825B2 (en) | 2014-12-24 | 2017-05-23 | Cisco Technology, Inc. | System and method for multi-source multicasting in content-centric networks |
US9832291B2 (en) | 2015-01-12 | 2017-11-28 | Cisco Technology, Inc. | Auto-configurable transport stack |
US9946743B2 (en) | 2015-01-12 | 2018-04-17 | Cisco Technology, Inc. | Order encoded manifests in a content centric network |
US9916457B2 (en) | 2015-01-12 | 2018-03-13 | Cisco Technology, Inc. | Decoupled name security binding for CCN objects |
US9954795B2 (en) | 2015-01-12 | 2018-04-24 | Cisco Technology, Inc. | Resource allocation using CCN manifests |
US10333840B2 (en) | 2015-02-06 | 2019-06-25 | Cisco Technology, Inc. | System and method for on-demand content exchange with adaptive naming in information-centric networks |
US10075401B2 (en) | 2015-03-18 | 2018-09-11 | Cisco Technology, Inc. | Pending interest table behavior |
US9589211B2 (en) * | 2015-05-08 | 2017-03-07 | Siemens Healthcare Gmbh | Learning-based aorta segmentation using an adaptive detach and merge algorithm |
US10075402B2 (en) | 2015-06-24 | 2018-09-11 | Cisco Technology, Inc. | Flexible command and control in content centric networks |
US10701038B2 (en) | 2015-07-27 | 2020-06-30 | Cisco Technology, Inc. | Content negotiation in a content centric network |
US9986034B2 (en) | 2015-08-03 | 2018-05-29 | Cisco Technology, Inc. | Transferring state in content centric network stacks |
US9832123B2 (en) | 2015-09-11 | 2017-11-28 | Cisco Technology, Inc. | Network named fragments in a content centric network |
US10355999B2 (en) | 2015-09-23 | 2019-07-16 | Cisco Technology, Inc. | Flow control with network named fragments |
US9977809B2 (en) | 2015-09-24 | 2018-05-22 | Cisco Technology, Inc. | Information and data framework in a content centric network |
US10313227B2 (en) | 2015-09-24 | 2019-06-04 | Cisco Technology, Inc. | System and method for eliminating undetected interest looping in information-centric networks |
US10454820B2 (en) | 2015-09-29 | 2019-10-22 | Cisco Technology, Inc. | System and method for stateless information-centric networking |
US10909675B2 (en) | 2015-10-09 | 2021-02-02 | Mayo Foundation For Medical Education And Research | System and method for tissue characterization based on texture information using multi-parametric MRI |
US10263965B2 (en) | 2015-10-16 | 2019-04-16 | Cisco Technology, Inc. | Encrypted CCNx |
US9794238B2 (en) | 2015-10-29 | 2017-10-17 | Cisco Technology, Inc. | System for key exchange in a content centric network |
US9807205B2 (en) | 2015-11-02 | 2017-10-31 | Cisco Technology, Inc. | Header compression for CCN messages using dictionary |
US9912776B2 (en) | 2015-12-02 | 2018-03-06 | Cisco Technology, Inc. | Explicit content deletion commands in a content centric network |
US10097346B2 (en) | 2015-12-09 | 2018-10-09 | Cisco Technology, Inc. | Key catalogs in a content centric network |
US10078062B2 (en) | 2015-12-15 | 2018-09-18 | Palo Alto Research Center Incorporated | Device health estimation by combining contextual information with sensor data |
US10257271B2 (en) | 2016-01-11 | 2019-04-09 | Cisco Technology, Inc. | Chandra-Toueg consensus in a content centric network |
US9949301B2 (en) | 2016-01-20 | 2018-04-17 | Palo Alto Research Center Incorporated | Methods for fast, secure and privacy-friendly internet connection discovery in wireless networks |
US10305864B2 (en) | 2016-01-25 | 2019-05-28 | Cisco Technology, Inc. | Method and system for interest encryption in a content centric network |
US10043016B2 (en) | 2016-02-29 | 2018-08-07 | Cisco Technology, Inc. | Method and system for name encryption agreement in a content centric network |
US10038633B2 (en) | 2016-03-04 | 2018-07-31 | Cisco Technology, Inc. | Protocol to query for historical network information in a content centric network |
US10742596B2 (en) | 2016-03-04 | 2020-08-11 | Cisco Technology, Inc. | Method and system for reducing a collision probability of hash-based names using a publisher identifier |
US10051071B2 (en) | 2016-03-04 | 2018-08-14 | Cisco Technology, Inc. | Method and system for collecting historical network information in a content centric network |
US10003507B2 (en) | 2016-03-04 | 2018-06-19 | Cisco Technology, Inc. | Transport session state protocol |
US9832116B2 (en) | 2016-03-14 | 2017-11-28 | Cisco Technology, Inc. | Adjusting entries in a forwarding information base in a content centric network |
US10212196B2 (en) | 2016-03-16 | 2019-02-19 | Cisco Technology, Inc. | Interface discovery and authentication in a name-based network |
US10067948B2 (en) | 2016-03-18 | 2018-09-04 | Cisco Technology, Inc. | Data deduping in content centric networking manifests |
US11436656B2 (en) | 2016-03-18 | 2022-09-06 | Palo Alto Research Center Incorporated | System and method for a real-time egocentric collaborative filter on large datasets |
US10091330B2 (en) | 2016-03-23 | 2018-10-02 | Cisco Technology, Inc. | Interest scheduling by an information and data framework in a content centric network |
US10033639B2 (en) | 2016-03-25 | 2018-07-24 | Cisco Technology, Inc. | System and method for routing packets in a content centric network using anonymous datagrams |
US10320760B2 (en) | 2016-04-01 | 2019-06-11 | Cisco Technology, Inc. | Method and system for mutating and caching content in a content centric network |
US9930146B2 (en) | 2016-04-04 | 2018-03-27 | Cisco Technology, Inc. | System and method for compressing content centric networking messages |
US10425503B2 (en) | 2016-04-07 | 2019-09-24 | Cisco Technology, Inc. | Shared pending interest table in a content centric network |
US10027578B2 (en) | 2016-04-11 | 2018-07-17 | Cisco Technology, Inc. | Method and system for routable prefix queries in a content centric network |
CN105913431A (zh) * | 2016-04-12 | 2016-08-31 | 绍兴文理学院 | 低分辨率医学图像的多图谱分割方法 |
US10404450B2 (en) | 2016-05-02 | 2019-09-03 | Cisco Technology, Inc. | Schematized access control in a content centric network |
US10320675B2 (en) | 2016-05-04 | 2019-06-11 | Cisco Technology, Inc. | System and method for routing packets in a stateless content centric network |
US10547589B2 (en) | 2016-05-09 | 2020-01-28 | Cisco Technology, Inc. | System for implementing a small computer systems interface protocol over a content centric network |
US10084764B2 (en) | 2016-05-13 | 2018-09-25 | Cisco Technology, Inc. | System for a secure encryption proxy in a content centric network |
US10063414B2 (en) | 2016-05-13 | 2018-08-28 | Cisco Technology, Inc. | Updating a transport stack in a content centric network |
US10103989B2 (en) | 2016-06-13 | 2018-10-16 | Cisco Technology, Inc. | Content object return messages in a content centric network |
US10305865B2 (en) | 2016-06-21 | 2019-05-28 | Cisco Technology, Inc. | Permutation-based content encryption with manifests in a content centric network |
US10148572B2 (en) | 2016-06-27 | 2018-12-04 | Cisco Technology, Inc. | Method and system for interest groups in a content centric network |
US10009266B2 (en) | 2016-07-05 | 2018-06-26 | Cisco Technology, Inc. | Method and system for reference counted pending interest tables in a content centric network |
CN106204600A (zh) * | 2016-07-07 | 2016-12-07 | 广东技术师范学院 | 基于多序列mr图像关联信息的脑肿瘤图像分割方法 |
US9992097B2 (en) | 2016-07-11 | 2018-06-05 | Cisco Technology, Inc. | System and method for piggybacking routing information in interests in a content centric network |
US9870614B1 (en) * | 2016-07-25 | 2018-01-16 | Sony Corporation | Automatic 3D brain tumor segmentation and classification |
US10122624B2 (en) | 2016-07-25 | 2018-11-06 | Cisco Technology, Inc. | System and method for ephemeral entries in a forwarding information base in a content centric network |
US10069729B2 (en) | 2016-08-08 | 2018-09-04 | Cisco Technology, Inc. | System and method for throttling traffic based on a forwarding information base in a content centric network |
US10956412B2 (en) | 2016-08-09 | 2021-03-23 | Cisco Technology, Inc. | Method and system for conjunctive normal form attribute matching in a content centric network |
CN106296699A (zh) * | 2016-08-16 | 2017-01-04 | 电子科技大学 | 基于深度神经网络和多模态mri图像的脑肿瘤分割方法 |
US10033642B2 (en) | 2016-09-19 | 2018-07-24 | Cisco Technology, Inc. | System and method for making optimal routing decisions based on device-specific parameters in a content centric network |
US10212248B2 (en) | 2016-10-03 | 2019-02-19 | Cisco Technology, Inc. | Cache management on high availability routers in a content centric network |
US10447805B2 (en) | 2016-10-10 | 2019-10-15 | Cisco Technology, Inc. | Distributed consensus in a content centric network |
US10135948B2 (en) | 2016-10-31 | 2018-11-20 | Cisco Technology, Inc. | System and method for process migration in a content centric network |
US10176570B2 (en) | 2016-11-16 | 2019-01-08 | Sony Corporation | Inter-patient brain registration |
US10243851B2 (en) | 2016-11-21 | 2019-03-26 | Cisco Technology, Inc. | System and method for forwarder connection information in a content centric network |
CN108182687A (zh) * | 2016-12-08 | 2018-06-19 | 复旦大学 | 一种基于脑肿瘤医学影像的交互式三维分割方法 |
CN106780515B (zh) * | 2017-01-04 | 2019-09-27 | 南京审计大学 | 一种脑部核磁共振图像中脑胶质瘤区域提取方法 |
CN107220980B (zh) * | 2017-05-25 | 2019-12-03 | 重庆师范大学 | 一种基于全卷积网络的mri图像脑肿瘤自动分割方法 |
NL2019410B1 (en) * | 2017-08-10 | 2019-02-21 | Aidence B V | Computer-aided diagnostics using deep neural networks |
EP3460751A1 (en) * | 2017-09-22 | 2019-03-27 | Koninklijke Philips N.V. | Automated tumor partitioning |
CN107766857B (zh) * | 2017-10-17 | 2021-08-03 | 天津大学 | 基于图模型构建与标签传播的视觉显著性检测算法 |
US11011275B2 (en) * | 2018-02-12 | 2021-05-18 | Ai.Skopy, Inc. | System and method for diagnosing gastrointestinal neoplasm |
CN109242860B (zh) * | 2018-08-21 | 2021-10-08 | 电子科技大学 | 基于深度学习及权重空间集成的脑肿瘤图像分割方法 |
NL2021559B1 (en) * | 2018-09-04 | 2020-04-30 | Aidence B V | Determination of a growth rate of an object in 3D data sets using deep learning |
KR101996475B1 (ko) * | 2018-10-11 | 2019-10-01 | (주)제이엘케이인스펙션 | 암 영역 검출의 유효성 평가 장치 |
CN109410214B (zh) * | 2018-10-19 | 2019-08-27 | 山东大学 | 一种具有抗噪性和偏场校正的医学图像分割方法 |
CN111354001B (zh) * | 2018-12-20 | 2024-02-02 | 西门子医疗系统有限公司 | 脑肿瘤图像分割方法、装置和存储介质 |
EP3928289A4 (en) * | 2019-02-20 | 2022-11-23 | The Regents Of The University Of California | SYSTEM AND METHOD FOR TISSUE CLASSIFICATION USING QUANTITATIVE IMAGE ANALYSIS OF SERIAL SCANS |
WO2020223962A1 (en) * | 2019-05-09 | 2020-11-12 | Boe Technology Group Co., Ltd. | Computer-implemented method of detecting foreign object on background object in image, apparatus for detecting foreign object on background object in image, and computer-program product |
CN110533667B (zh) * | 2019-07-29 | 2022-12-02 | 西安电子科技大学 | 基于图像金字塔融合的肺部肿瘤ct影像3d分割方法 |
CN112233128B (zh) * | 2020-10-15 | 2021-11-02 | 推想医疗科技股份有限公司 | 图像分割方法及模型的训练方法、装置、介质、电子设备 |
CN112435261B (zh) * | 2020-11-16 | 2023-06-16 | 辽宁师范大学 | 基于超体素的多模态mri脑肿瘤分割方法 |
CN112508953B (zh) * | 2021-02-05 | 2021-05-18 | 四川大学 | 基于深度神经网络的脑膜瘤快速分割定性方法 |
CN113160138B (zh) * | 2021-03-24 | 2022-07-19 | 山西大学 | 一种脑部核磁共振图像分割方法及系统 |
CN113538409B (zh) * | 2021-08-05 | 2023-05-16 | 佳木斯大学 | 基于模糊逻辑和anfis的宫颈癌图像区域分割方法 |
US11526994B1 (en) * | 2021-09-10 | 2022-12-13 | Neosoma, Inc. | Labeling, visualization, and volumetric quantification of high-grade brain glioma from MRI images |
CN114155251B (zh) * | 2021-12-07 | 2024-10-15 | 重庆邮电大学 | 一种上下文感知卷积神经网络的全脑三维解剖结构分割方法 |
CN115568944B (zh) * | 2022-11-21 | 2023-02-24 | 吉林省英华恒瑞生物科技有限公司 | 一种肿瘤治疗仪的模拟消融方法及系统 |
CN116385438B (zh) * | 2023-06-05 | 2023-08-11 | 济南科汛智能科技有限公司 | 一种核磁共振肿瘤区域提取方法 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7194117B2 (en) * | 1999-06-29 | 2007-03-20 | The Research Foundation Of State University Of New York | System and method for performing a three-dimensional virtual examination of objects, such as internal organs |
US6138045A (en) * | 1998-08-07 | 2000-10-24 | Arch Development Corporation | Method and system for the segmentation and classification of lesions |
US6891964B2 (en) * | 2001-11-23 | 2005-05-10 | University Of Chicago | Computerized method for determination of the likelihood of malignancy for pulmonary nodules on low-dose CT |
US8586932B2 (en) * | 2004-11-09 | 2013-11-19 | Spectrum Dynamics Llc | System and method for radioactive emission measurement |
US8265355B2 (en) * | 2004-11-19 | 2012-09-11 | Koninklijke Philips Electronics N.V. | System and method for automated detection and segmentation of tumor boundaries within medical imaging data |
US8218835B2 (en) * | 2005-08-22 | 2012-07-10 | Dai Nippon Printing Co., Ltd. | Method for assisting in diagnosis of cerebral diseases and apparatus thereof |
US8073226B2 (en) * | 2006-06-30 | 2011-12-06 | University Of Louisville Research Foundation, Inc. | Automatic detection and monitoring of nodules and shaped targets in image data |
CN101226155A (zh) * | 2007-12-21 | 2008-07-23 | 中国人民解放军第八一医院 | 智能化肺癌早期细胞病理图像识别处理方法 |
CA2716598A1 (en) * | 2008-03-04 | 2009-09-11 | Tomotherapy Incorporated | Method and system for improved image segmentation |
US8295569B2 (en) * | 2008-06-12 | 2012-10-23 | Siemens Medical Solutions Usa, Inc. | Method and system for automatic detection and measurement of mitral valve inflow patterns in doppler echocardiography |
US8280133B2 (en) * | 2008-08-01 | 2012-10-02 | Siemens Aktiengesellschaft | Method and system for brain tumor segmentation in 3D magnetic resonance images |
WO2010027476A1 (en) * | 2008-09-03 | 2010-03-11 | Rutgers, The State University Of New Jersey | System and method for accurate and rapid identification of diseased regions on biological images with applications to disease diagnosis and prognosis |
CN101515368B (zh) * | 2009-04-01 | 2011-04-13 | 西北工业大学 | 三维大脑磁共振图像的大脑皮层表面上脑沟盆地分割方法 |
CN101596109B (zh) * | 2009-06-12 | 2012-01-25 | 深圳先进技术研究院 | 获取脑部特征参数的方法、系统及溶栓指征生成系统 |
US8724866B2 (en) * | 2009-09-14 | 2014-05-13 | Siemens Medical Solutions Usa, Inc. | Multi-level contextual learning of data |
CN101739681B (zh) * | 2009-12-14 | 2011-09-14 | 西北工业大学 | 基于相关预测模型的磁共振图像中检测结构形变的方法 |
US9129382B2 (en) * | 2010-06-25 | 2015-09-08 | Institute Of Automation, Chinese Academy Of Sciences | Method and system for brain tumor segmentation in multi-parameter 3D MR images via robust statistic information propagation |
-
2011
- 2011-12-21 WO PCT/CN2011/084340 patent/WO2013091186A1/zh active Application Filing
- 2011-12-21 US US13/806,493 patent/US8908948B2/en not_active Expired - Fee Related
- 2011-12-21 CN CN201180030783.2A patent/CN103098090B/zh not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
US8908948B2 (en) | 2014-12-09 |
WO2013091186A1 (zh) | 2013-06-27 |
US20130182931A1 (en) | 2013-07-18 |
CN103098090A (zh) | 2013-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103098090B (zh) | 多参数三维磁共振图像脑肿瘤分割方法 | |
Soltaninejad et al. | Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI | |
CN103353986B (zh) | 一种基于超像素模糊聚类的脑部mr图像分割方法 | |
CN102596025B (zh) | 基于鲁棒统计信息传播的多模态三维磁共振图像脑肿瘤分割方法 | |
CN106886995B (zh) | 多线性示例回归器聚合的图像显著对象分割方法 | |
CN104956397B (zh) | 基于自动空间上下文的3d图像中的多对象分段 | |
CN104123561B (zh) | 基于空间引力模型的模糊c均值遥感影像自动分类方法 | |
Dai et al. | Learning to localize detected objects | |
CN106096561A (zh) | 基于图像块深度学习特征的红外行人检测方法 | |
CN105009171A (zh) | 用于学习增强的基于图谱的自动分割的方法和装置 | |
Shakibapour et al. | An unsupervised metaheuristic search approach for segmentation and volume measurement of pulmonary nodules in lung CT scans | |
CN104217213B (zh) | 一种基于对称性理论的医学图像多阶段分类方法 | |
CN105809175A (zh) | 一种基于支持向量机算法的脑水肿分割方法及系统 | |
CN101479762A (zh) | 用于在包含图像值的图像中确定阈值的方法、系统和计算机程序 | |
CN104573742A (zh) | 医学图像分类方法和系统 | |
CN104537353A (zh) | 基于三维点云的三维人脸年龄分类装置及方法 | |
CN103310227A (zh) | 基于神经网络的自动窗宽窗位提取方法 | |
CN104573707A (zh) | 一种基于多特征融合的车牌汉字识别方法 | |
CN110610472A (zh) | 实现肺结节图像分类检测的计算机装置及方法 | |
CN104281856A (zh) | 用于脑部医学图像分类的图像预处理方法和系统 | |
Ma et al. | A combined learning algorithm for prostate segmentation on 3D CT images | |
Saueressig et al. | Exploring graph-based neural networks for automatic brain tumor segmentation | |
CN110930413A (zh) | 一种基于弱监督多核分类优化合并的图像分割方法 | |
CN104573722A (zh) | 基于三维点云的三维人脸种族分类装置和方法 | |
Telrandhe et al. | Implementation of brain tumor detection using segmentation algorithm & SVM |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150121 Termination date: 20211221 |