Apparatus and method for computer aided diagnosis (CAD) based on eye movement

• US 9,818,029 B2
• Filed: 12/11/2015
• Issued: 11/14/2017
• Est. Priority Date: 12/11/2014
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Ki Yong, Kang, Byung Kon, Kwon, Keun Joo, Seong, Yeong Kyeong, Ryu, Seung Woo
• Primary Examiner(s): Yentrapati, Avinash
• Application Number:
  US14/965,986
• Publication Number:
  US 20160171299A1
• Time in Patent Office: 704 Days
• Field of Search: None
• CPC Class Codes: A61B 2576/00 Medical imaging apparatus involving image processing or analysis A61B1/00009, A61B6/52 and A61B8/52 take precedence; image processing per se G06T; details of algorithms for analysing medical images G06T7/0012
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 8/08 Detecting organic movements or changes, e.g. tumours, cysts, swellings A61B8/02 - A61B8/06 take precedence
• CPC Class Codes: A61B 8/10 Eye inspection
• CPC Class Codes: A61B 8/469 for selection of a region of interest
• CPC Class Codes: A61B 8/5223 for extracting a diagnostic or physiological parameter from medical diagnostic data for algorithms to analyse biomedical images G06T7/0012
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

An apparatus and a method for Computer Aid Diagnosis (CAD) based on eye movement are provided. The apparatus includes a gaze area detector configured to detect, based on eye movement of a user, a gaze area on a medical image on which a region of interest (ROI) is detected, the gaze area being an area at which the user gazes for a period of time. The apparatus further includes an ROI redetector configured to detect another ROI on the gaze area.

Claims

1. A Computer Aided Diagnosis (CAD) apparatus comprising:

a memory configured to store instructions therein; and

at least one processor, upon execution of the instructions, configured to;

detect at least one region of interest (ROI) on a medical image;

detect, based on eye movement of a user, a gaze area on the medical image on which the at least one ROI on the medical image is detected, the gaze area being an area at which the user gazes for a period of time;

detect at least one ROI on the gaze area; and

modify a first detection result of the at least one ROI on the medical image, based on a second detection result of the at least ROI on the gaze area.

2. The CAD apparatus of claim 1, wherein the at least one processor is further configured to detect the at least one ROI on the gaze area, using a lesion detection model that is different from another lesion detection model that is used in the detection of the at least one ROI on the medical image.

3. The CAD apparatus of claim 1, wherein the at least one processor is further configured to:

acquire one or more additional images of the gaze area by adjusting parameters or a frame rate of a probe that is used to acquire the medical image or by transforming a portion where the gaze area is positioned in the medical image; and

detect at least one ROI on each of the one or more additional images.

4. The CAD apparatus of claim 3, wherein the parameters of the probe comprise at least one among a frequency, a bandwidth, a power intensity, a gain, and a depth of focus of an ultrasonic signal.

5. The CAD apparatus of claim 3, wherein the at least one processor is further configured to transform the portion where the gaze area is positioned in the medical image, using at least one among Horizontal Flip, Rotation, Cropping, Scaling, Shearing, Jittering, Stretching, Blurring, Sharpening, Histogram Modification, Restoration, and Noise addition.

6. The CAD apparatus of claim 1, wherein the at least one processor is further configured to classify the at least one ROI on the gaze area.

7. The CAD apparatus of claim 1, further comprising:

a display configured to display the modified first detection result of the at least one ROI on the medical image.

8. The CAD apparatus of claim 1, wherein the at least one processor is further configured to:

determine whether an ROI on the medical image with respect to the gaze area is one among a false positive, a false negative, and a true positive, based on the at least one ROI on the gaze area;

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the false positive, remove a marker for the at least one ROI on the medical image with respect to the gaze area;

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the false negative, add the marker for the at least one ROI on the medical image with respect to the gaze area; and

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the true positive, maintain the marker for the at least one ROI on the medical image with respect to the gaze area.

9. A Computer Aided Diagnosis (CAD) method comprising:

detecting at least one region of interest (ROI) on a medical image;

detecting, based on eye movement of a user, a gaze area on the medical image on which the at least one ROI on the medical image is detected, the gaze area being an area at which the user gazes for a period of time;

detecting at least one ROI on the gaze area; and

modifying a first detection result of the at least one ROI on the medical image based on a second detection result of the at least one ROI on the gaze area.

10. The CAD method of claim 9, wherein the detecting the at least one ROI on the gaze area comprises detecting the at least one ROI on the gaze area, using a lesion detection model that is different from another lesion detection model that is used in the detection of the at least one ROI on the medical image.

11. The CAD method of claim 9, further comprising:

acquiring one or more additional images of the gaze area by adjusting parameters or a frame rate of a probe that is used to acquire the medical image or by transforming a portion where the gaze area is positioned in the medical image,

wherein the detecting the at least one ROI on the gaze area comprises detecting at least one ROI on each of the one or more additional images.

12. The CAD method of claim 11, wherein the parameters of the probe comprise at least one among a frequency, a bandwidth, a power intensity, a gain, and a depth of focus of an ultrasonic signal.

13. The CAD method of claim 11, wherein the acquiring comprises transforming the portion where the gaze area is positioned in the medical image, using at least one among Horizontal Flip, Rotation, Cropping, Scaling, Shearing, Jittering, Stretching, Blurring, Sharpening, Histogram Modification, Restoration, and Noise addition.

14. The CAD method of claim 9, further comprising:

classifying the at least one ROI on the gaze area.

15. The CAD method of claim 9, further comprising:

displaying the modified first detection result of the at least one ROI on the medical image.

16. The CAD method of claim 9, wherein the modifying comprises:

determining whether an ROI on the medical image with respect to the gaze area is one among a false positive, a false negative, and a true positive, based on the at least one ROI on the gaze area;

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the false positive, removing a marker for the at least one ROI on the medical image with respect to the gaze area;

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the false negative, adding the marker for the at least one ROI on the medical image with respect to the gaze area; and

in response to the determining that the at least one ROI on the medical image with respect to the gaze area is the true positive, maintaining the marker for the at least one ROI on the medical image with respect to the gaze area.