Title:
多段分類器を用いた画像分割のためのシステム及び方法
Document Type and Number:
Japanese Patent JP5185811
Kind Code:
B2
Abstract:
The systems and methods described herein provide for fast and accurate image segmentation through the application of a multi-stage classifier to an image data set. An image processing system is provided having a processor configured to apply a multi-stage classifier to the image data set to identify a distinctive region. The multi-stage classifier can include two or more component classifiers. The first component classifier can have a sensitivity level configured to identify one or more target regions in the image data set and the second component classifier can have a specificity level configured to confirm the presence of the distinctive region in any identified target regions. Also provided is a classification array having multiple multi-stage classifiers for identification and confirmation of more than one distinctive region or for the application of different classification configurations to the image data set to identify a specific distinctive region.
Inventors:
Shashidar Satiana Layana
Application Number:
JP2008505410A
Publication Date:
April 17, 2013
Filing Date:
April 03, 2006
Export Citation:
Assignee:
Boston Scientific Limited
International Classes:
A61B8/00; G06T1/00; G06T7/00
Domestic Patent References:
| JP10192256A | ||||
| JP2004536367A | ||||
| JP2001511372A |
Foreign References:
| WO2004017835A1 | ||||
| US20010031076 |
Other References:
LIN J.S. et al.,Reduction of False Positives in Lung Nodule Detection Using a Two-Level Neural Classification,IEEE TRANSACTIONS ON MEDICAL IMAGING,1996年 4月,Vol.15, No.2,pp. 206-217
Attorney, Agent or Firm:
Sadao Kumakura
Disciple Maru Ken
Ino Sato
Mitsuru Matsushita
Ichiro Kurasawa
Disciple Maru Ken
Ino Sato
Mitsuru Matsushita
Ichiro Kurasawa