公开(公告)号：US09741116B2

公开(公告)日：2017-08-22

申请号：US14914896

申请日：2014-08-28

申请人： Jianming Liang ,  Nima Tajbakhsh ,  Suryakanth R. Gurudu

发明人： Jianming Liang ,  Nima Tajbakhsh ,  Suryakanth R. Gurudu

IPC分类号： G06K9/00 ,  G06T7/00 ,  A61B1/31 ,  A61B1/00 ,  G06T5/20 ,  G06T7/73 ,  G06T7/12 ,  G06T7/13 ,  G06T7/41 ,  A61B6/02 ,  A61B5/00

CPC分类号： G06T7/0016 ,  A61B1/00009 ,  A61B1/31 ,  A61B5/4255 ,  G06T5/20 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/13 ,  G06T7/41 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10068 ,  G06T2207/20024 ,  G06T2207/20168 ,  G06T2207/30032

摘要： A system and method is provided for automated polyp detection in optical colonoscopy images. The system includes an input configured to acquire a series of optical images, and a processor configured to process the optical images. Processing steps include performing a boundary classification with steps comprising locating a series of edge pixels using at least one acquired optical image, selecting an image patch around each said edge pixel, performing a classification threshold analysis on each image patch of said edge pixels using a set of determined boundary classifiers, and identifying, based on the classification threshold analysis, polyp edge pixels consistent with a polyp edge. Processing steps for the processor also include performing a vote accumulation, using the identified polyp edge pixels, to determine a polyp location. The system also includes an output configured to indicate potential polyps using the determined polyp location.

公开(公告)号：US20160217573A1

公开(公告)日：2016-07-28

申请号：US14914896

申请日：2014-08-28

申请人： Jianming LIANG ,  Nima TAJBAKHSH ,  Suryakanth R. GURUDU

发明人： Jianming Lian ,  Nima Tajbakhsh ,  Suryakanth R. Gurudu

IPC分类号： G06T7/00 ,  A61B1/31 ,  G06T5/20

CPC分类号： G06T7/0016 ,  A61B1/00009 ,  A61B1/31 ,  A61B5/4255 ,  G06T5/20 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/13 ,  G06T7/41 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10068 ,  G06T2207/20024 ,  G06T2207/20168 ,  G06T2207/30032

摘要： A system and method is provided for automated polyp detection in optical colonoscopy images. The system includes an input configured to acquire a series of optical images, and a processor configured to process the optical images. Processing steps include performing a boundary classification with steps comprising locating a series of edge pixels using at least one acquired optical image, selecting an image patch around each said edge pixel, performing a classification threshold analysis on each image patch of said edge pixels using a set of determined boundary classifiers, and identifying, based on the classification threshold analysis, polyp edge pixels consistent with a polyp edge. Processing steps for the processor also include performing a vote accumulation, using the identified polyp edge pixels, to determine a polyp location. The system also includes an output configured to indicate potential polyps using the determined polyp location.

摘要翻译： 提供了一种用于光学结肠镜检查图像中的自动息肉检测的系统和方法。 该系统包括被配置为获取一系列光学图像的输入端和配置成处理光学图像的处理器。 处理步骤包括执行边界分类，步骤包括使用至少一个获取的光学图像来定位一系列边缘像素，在每个所述边缘像素周围选择一个图像块，使用集合对所述边缘像素的每个图像块执行分类阈值分析 确定边界分类器，并根据分类阈值分析识别与息肉边缘一致的息肉边缘像素。 处理器的处理步骤还包括使用所识别的息肉边缘像素执行投票积累以确定息肉位置。 该系统还包括被配置为使用所确定的息肉位置来指示潜在的息肉的输出。