Invention Grant
- Patent Title: Image search engine
- Patent Title (中): 图像搜索引擎
-
Application No.: US13824853Application Date: 2011-10-25
-
Publication No.: US09275456B2Publication Date: 2016-03-01
- Inventor: Susumu Mori , Michael I. Miller , Kenichi Oishi , Andreia V. Faria
- Applicant: Susumu Mori , Michael I. Miller , Kenichi Oishi , Andreia V. Faria
- Applicant Address: US MD Baltimore
- Assignee: The Johns Hopkins University
- Current Assignee: The Johns Hopkins University
- Current Assignee Address: US MD Baltimore
- Agency: Venable LLP
- Agent Henry J. Daley; Trent B. Ostler
- International Application: PCT/US2011/057692 WO 20111025
- International Announcement: WO2012/058217 WO 20120503
- Main IPC: G06T7/00
- IPC: G06T7/00 ; A61B5/00 ; A61B5/055 ; G06F17/30 ; G06F19/00 ; A61B6/03 ; A61B6/00 ; A61B8/00

Abstract:
An embodiment of the current invention includes a non-invasive imaging system, comprising: an imaging scanner suitable to generate an image representing a tissue region of a subject under observation, the tissue region having at least one substructure and the image comprising a plurality of image voxels; a signal processing system in communication with the imaging scanner to receive the imaging signal from the imaging scanner; and a data storage unit in communication with the signal processing system, wherein the data storage unit is configured to store: an atlas comprising spatial information of the at least one substructure in the tissue region, and a database comprising a plurality of pre-stored medical images representing the tissue region, and wherein the signal processing system is adapted to: identify, based on the atlas and for each of the at least one substructure, a corresponding portion of image voxels in the image; provide a computed quantification of the corresponding portion of image voxels for each of the at least one substructure of the tissue region by performing spatial filtering on the image; and search the database to provide at least one selected medical image from the plurality of pre-stored medical images, the at least one selected medical image having a corresponding quantification that is substantially similar to the computed quantification.
Public/Granted literature
- US20130223716A1 IMAGE SEARCH ENGINE Public/Granted day:2013-08-29
Information query