Back to results
US 2016/0110160 A1Published application
Context-sensitive identification of regions of interest in a medical image
AssigneeSiemens Medical Solutions USA, Inc.
InventorsJerome Declerck, Matthew David Kelly
Life of this patent
Estimating the term…
Abstract
A voice controlled system uses context-sensitive interpretation of voice comments received by a voice recognition system to identify a region of patient image data identified by a verbal comment.
Claims16
A method for identifying a region of interest within patient functional image data, comprising:
- providing patient functional image data to a computer and, in said computer, automatically identifying and segmenting candidate regions of interests within the patient functional image data;
- displaying the patient functional image data at a user interface of the computer, in at least one view;
- receiving verbal comments, that describe a region of interest, into the computer from a user via a voice input interface of the computer and, in said computer, automatically interpreting said comments by executing a voice recognition algorithm in the computer;
- in said computer, automatically evaluating said interpreted verbal comments, dependent on said at least one view, to identify a region of interest, among said candidate regions of interest, that most closely corresponds to the description of the region of interest in the interpreted verbal comments;
- and
- displaying said most closely corresponding region of interest at said user interface.
3 more elements
A system for context-sensitive identification of regions of interest, comprising:
- a computer provided with patient functional image data to a computer, said computer being configured to automatically identify and segment candidate regions of interests within the patient functional image data;
- a display monitor in communication with said computer, being configured to display the patient functional image data at said display monitor a user interface of the computer, in at least one view;
- said computer comprising a voice input interface, and said computer being configured to receive verbal comments, that describe a region of interest, via said voice input interface, and computer being configured to automatically interpret said comments by executing a voice recognition algorithm in the computer;
- said computer being configured to automatically evaluate said interpreted verbal comments, dependent on said at least one view, to identify a region of interest, among said candidate regions of interest, that most closely corresponds to the description of the region of interest in the interpreted verbal comments;
- and
- said computer being configured to display said most closely corresponding region of interest at said display monitor.
3 more elements
An apparatus for identifying a region of interest in medical imaging data of a subject, comprising:
- a computer provided with patient functional image data, said computer being configured to automatically identify and segment candidate regions of interests within the patient functional image data;
- a display monitor in communication with said computer, said computer being configured to display the patient functional image data at said display monitor, in at least one view;
- a user interface in communication with said computer, said computer being configured to receive a description of a region of interest from a user via said user interface;
- said computer being configured to automatically evaluate said description dependent on said at least one view, to identify a region of interest, among said candidate regions of interest, that most closely corresponds to the description of the region of interest in the description;
- and
- said computer being configured to display said most closely corresponding region of interest at said display monitor.
3 more elements
A non-transitory, computer-readable data storage medium encoded with programming instructions, said storage medium being loaded into a computer and said programming instructions causing said computer to:
- receive patient functional image data and automatically identify and segment candidate regions of interests within the patient functional image data;
- display the patient functional image data at a user interface of the computer, in at least one view;
- receive verbal comments, that describe a region of interest, from a user via a voice input interface of the computer, and automatically interpret said comments by executing a voice recognition algorithm;
- automatically evaluate said interpreted verbal comments, dependent on said at least one view, to identify a region of interest, among said candidate regions of interest, that most closely corresponds to the description of the region of interest in the interpreted verbal comments;
- and
- display said most closely corresponding region of interest at said user interface.
3 more elements
A non-transitory, computer-readable data storage medium encoded with programming instructions, said storage medium being loaded into a computer and said programming instructions causing said computer to:
- receive patient functional image data and automatically identify and segment candidate regions of interests within the patient functional image data;
- display the patient functional image data at a display screen of the computer, in at least one view;
- receive a description of a region of interest from a user interface of the computer;
- automatically evaluate said description, dependent on said at least one view, to identify a region of interest, among said candidate regions of interest, that most closely corresponds to the description of the region of interest;
- and
- display said most closely corresponding region of interest at said display screen.
3 more elements
Dependencies are inferred from the claim text.