公开(公告)号：US20180122066A1

公开(公告)日：2018-05-03

申请号：US15336475

申请日：2016-10-27

Applicant: Xerox Corporation

Inventor： Prathosh A. PRASAD ,  Sanjay BHARADWAJ ,  Pragathi PRAVEENA ,  Tejaskumar Dipaklal BENGALI ,  Satish Prasad RATH ,  Himanshu Jayantkumar MADHU

IPC: G06T7/00 ,  G06T7/20 ,  G06T5/00 ,  A61B5/00 ,  A61B5/024 ,  A61B5/08 ,  A61B5/11 ,  A61B5/113

CPC classification number: G06T7/0012 ,  A61B5/0022 ,  A61B5/0077 ,  A61B5/024 ,  A61B5/08 ,  A61B5/1102 ,  A61B5/1128 ,  A61B5/113 ,  A61B5/742 ,  G06T5/002 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20024 ,  G06T2207/30048

Abstract: What is disclosed is a system and method for processing a video to extract a periodic signal which was captured by the video imaging device. One embodiment involves the following. First, a video of a subject in a scene is received. The video is acquired by a video imaging device. There is an underlying motion signal in the scene corresponding to cardiac or respiratory function. A time-series signal is generated for each pixel or for each group of pixels in a temporal direction across a plurality of image frames. Time-series signals of interest are selected. The selected time-series signals of interest are then processed to obtain a periodic signal corresponding to cardiac or respiratory function. The present method has a low computational complexity, is robust in the presence of noise, and finds its uses in applications requiring real-time motion quantification of a signal in a video.

公开(公告)号：US20170055920A1

公开(公告)日：2017-03-02

申请号：US14837898

申请日：2015-08-27

Applicant: Xerox Corporation

Inventor： Lalit Keshav MESTHA ,  Sanjay BHARADWAJ ,  Prathosh A. PRASAD ,  Tejaskumar D. BENGALI ,  Himanshu J. MADHU ,  Suresh KUPPUSWAMY

IPC: A61B5/00 ,  A61B5/113 ,  A61B5/11

CPC classification number: A61B5/7285 ,  A61B5/0013 ,  A61B5/0075 ,  A61B5/0077 ,  A61B5/1128 ,  A61B5/113 ,  A61B5/1135 ,  A61B5/4836 ,  A61B5/725 ,  A61B5/7264 ,  A61B5/7292 ,  A61B6/00 ,  A61B6/025 ,  A61B6/032 ,  A61B6/037 ,  A61B6/541 ,  A61B2576/02 ,  G06T7/246 ,  G06T2207/20076 ,  G06T2207/30004

Abstract: What is disclosed is a system and method for generating a respiration gating signal from a video of a subject for gating diagnostic imaging and therapeutic delivery applications which require respiration phase and/or respiration amplitude gating. One embodiment involves receiving a video of a subject and generating a plurality of time-series signals from the video image frames. A set of features are extracted from the time-series signals and multi-dimensional feature vectors are formed. The feature vectors are clustered. Time-series signals corresponding in each of the clusters are averaged in a temporal direction to obtain a representative signal for each cluster. One cluster is selected and a respiration gating signal is generated from that cluster's representative signal. Thereafter, the respiration gating signal is used to gate diagnostic imaging and therapeutic delivery applications which requires gating based on a threshold set with respect to either respiration phase or respiration amplitude.

Abstract translation: 公开的是用于从需要呼吸相位和/或呼吸振幅选通的门诊诊断成像和治疗递送应用的对象视频产生呼吸门控信号的系统和方法。 一个实施例涉及接收对象的视频并从视频图像帧产生多个时间序列信号。 从时间序列信号中提取一组特征，形成多维特征向量。 特征向量是聚类的。 在每个簇中对应的时间序列信号在时间方向上被平均以获得每个簇的代表信号。 选择一个群集，并从该群集的代表信号中生成呼吸门控信号。 此后，呼吸门控信号用于门诊诊断成像和治疗递送应用，其需要基于相对于呼吸相位或呼吸振幅设定的阈值进行门控。