SYSTEMS AND METHODS FOR DECONVOLUTIONAL NETWORK BASED CLASSIFICATION OF CELLULAR IMAGES AND VIDEOS
摘要
A method for performing cellular classification includes using a convolution sparse coding process to generate a plurality of feature maps based on a set of input images and a plurality of biologically-specific filters. A feature pooling operation is applied on each of the plurality of feature maps to yield a plurality of image representations. Each image representation is classified as one of a plurality of cell types.
申请公布号
WO2016144341(A1)
申请公布日期
2016.09.15
申请号
WO2015US19844
申请日期
2015.03.11
申请人
SIEMENS AKTIENGESELLSCHAFT;SIEMENS CORPORATION
发明人
WAN, Shaohua;SUN, Shanhui;CHEN, Terrence;GEORGESCU, Bogdan;KAMEN, Ali