VISUAL REPRESENTATION LEARNING FOR BRAIN TUMOR CLASSIFICATION
    21.
    发明申请
    VISUAL REPRESENTATION LEARNING FOR BRAIN TUMOR CLASSIFICATION 审中-公开
    视觉代表学习脑肿瘤分类

    公开(公告)号:WO2017023569A1

    公开(公告)日:2017-02-09

    申请号:PCT/US2016/043466

    申请日:2016-07-22

    Abstract: Independent subspace analysis (ISA) is used to learn (42) filter kernels for CLE images in brain tumor classification. Convolution (46) and stacking are used for unsupervised learning (44, 48) with ISA to derive the filter kernels. A classifier is trained (56) to classify CLE brain images based on features extracted using the filter kernels. The resulting filter kernels and trained classifier are used (60, 64) to assist in diagnosis of occurrence of brain tumors during or as part of neurosurgical resection. The classification may assist a physician in detecting whether CLE examined brain tissue is healthy or not and/or a type of tumor.

    Abstract translation: 独立子空间分析(ISA)用于学习(42)在脑肿瘤分类中过滤CLE图像的内核。 卷积(46)和堆叠用于无监督学习(44,48)与ISA导出过滤器内核。 训练分类器(56),以基于使用滤波器内核提取的特征对CLE脑图像进行分类。 使用所得到的过滤核和训练分类器(60,64)来帮助诊断脑肿瘤在神经外科切除期间或作为神经外科切除术的一部分。 该分类可以帮助医生检测CLE检查的脑组织是否健康,和/或一种类型的肿瘤。

    HIERARCHICAL ATLAS-BASED SEGMENTATION
    25.
    发明申请
    HIERARCHICAL ATLAS-BASED SEGMENTATION 审中-公开
    基于分层的基于ATLAS的分类

    公开(公告)号:WO2011109710A1

    公开(公告)日:2011-09-09

    申请号:PCT/US2011/027189

    申请日:2011-03-04

    Abstract: A method for segmenting an image includes registering an annotated template image to an acquired reference image using only rigid transformations to define a transformation function relating the annotated template image to the acquired reference image (S101). The defined transformation function is refined by registering the annotated template image to the acquired reference image using only affine transformations (S102). The refined transformation function is further refined by registering the annotated template image to the acquired reference image using only multi-affine transformations (S103). The twice refined transformation function is further refined by registering the annotated template image to the acquired reference image using deformation transformations (S104).

    Abstract translation: 用于分割图像的方法包括使用刚性变换将注释的模板图像注册到所获取的参考图像,以定义将所注释的模板图像与所获取的参考图像相关联的变换功能(S101)。 通过使用仿射变换将注释的模板图像注册到所获取的参考图像来改进所定义的变换函数(S102)。 通过仅使用多仿射变换将注释的模板图像注册到所获取的参考图像,进一步改进了精细变换功能(S103)。 通过使用变形变换将所注释的模板图像注册到获取的参考图像来进一步改进两次精化转换函数(S104)。

    METHOD AND SYSTEM FOR AUTOMATED BRAIN TUMOR DIAGNOSIS USING IMAGE CLASSIFICATION
    26.
    发明申请
    METHOD AND SYSTEM FOR AUTOMATED BRAIN TUMOR DIAGNOSIS USING IMAGE CLASSIFICATION 审中-公开
    使用图像分类的自动脑肿瘤诊断方法和系统

    公开(公告)号:WO2016160491A1

    公开(公告)日:2016-10-06

    申请号:PCT/US2016/023929

    申请日:2016-03-24

    Abstract: A method and system for classifying tissue endomicroscopy images are disclosed. Local feature descriptors are extracted from an endomicroscopy image. Each of the local feature descriptors is encoded using a learnt discriminative dictionary. The learnt discriminative dictionary includes class-specific sub-dictionaries and penalizes correlation between bases of sub-dictionaries associated with different classes. Tissue in the endomicroscopy image is classified using a trained machine learning based classifier based on the coded local feature descriptors encoded using a learnt discriminative dictionary.

    Abstract translation: 公开了一种用于分类组织内窥镜图像的方法和系统。 局部特征描述符从内窥镜图像中提取。 每个本地特征描述符使用学习的鉴别词典进行编码。 学习的歧视词典包括特定类别的字典,并惩罚与不同类别相关的子词典的基础之间的相关性。 使用基于经过训练的基于机器学习的分类器基于使用学习的鉴别词典编码的编码的局部特征描述符来对内窥镜图像中的组织进行分类。

    CLASSIFICATION OF CELLULAR IMAGES AND VIDEOS
    27.
    发明申请
    CLASSIFICATION OF CELLULAR IMAGES AND VIDEOS 审中-公开
    细胞图像和视频的分类

    公开(公告)号:WO2016140693A1

    公开(公告)日:2016-09-09

    申请号:PCT/US2015/023231

    申请日:2015-03-30

    Abstract: A method for performing cellular classification includes extracting a plurality of local feature descriptors (220) from a set of input images (210) and applying a coding process to convert each of the plurality of local feature descriptors into a multi-dimensional code (225). A feature pooling operation (230) is applied on each of the plurality of local feature descriptors to yield a plurality of image representations and each image representation is classified as one of a plurality of cell types (240).

    Abstract translation: 一种用于执行蜂窝分类的方法包括从一组输入图像(210)提取多个局部特征描述符(220),并应用编码处理将多个局部特征描述符中的每一个转换为多维码(225) 。 在多个局部特征描述符中的每一个上应用特征集合操作(​​230)以产生多个图像表示,并且每个图像表示被分类为多个小区类型之一(240)。

Patent Agency Ranking