Method and system for computer aided detection (CAD) cued reading of medical images
View Patent ↗A method and system for Computer Aided Detection (CAD) of abnormalities in X-ray images in which the features and/or criteria used in the CAD analysis are displayed as coded descriptors on the digital image of the X-ray to provide an indication to a user of the basis underlying the identification of a particular abnormality therefore increasing the reliability of a diagnosis established by the user.
1. A method for displaying results of a computer aided detection (CAD) analysis of a digital image, the method comprising:
i) analyzing the digital image using CAD analysis to identify one or more CAD-detected abnormalities;
ii) generating one or more coded descriptors for said CAD-detected abnormalities wherein said coded descriptors provide information on one or more criteria used by said CAD analysis to identify said CAD-detected abnormalities; and
iii) displaying said digital image with the one or more coded descriptors;
wherein said one or more coded descriptors is selected from visual markers, alpha-numeric information or a combination thereof; and
wherein said visual markers can be displayed with varying degrees transparency.
2. The method as claimed in claim 1 wherein said digital image is a digitized image of an X-ray film.
3. The method as claimed in claim 1 wherein said digital image is a digital mammogram.
4. The method as claimed in claim 1 further comprising visually analyzing said digital image to identify one or more user-detected abnormalities, said visual analysis being performed before said step of displaying and wherein said user-detected abnormalities are re-assessed based on said information provided by said coded descriptors.
5. The method as claimed in claim 4 wherein said digital image is a digitized image of an X-ray film and wherein said visual examination is performed on said X-ray film.
6. The method as claimed in claim 1 further comprising visually analyzing said digital image to identify one or more user-detected abnormalities said visual examination being performed with said coded descriptors being displayed simultaneously such that a user can refer to said coded descriptors while performing said visual analysis.
7. The method as claimed in claim 6 wherein said digital image is a digitized image of an X-ray film and wherein said visual examination is performed on said X-ray film.
8. The method as claimed in claim 1 wherein said one or more coded descriptor displayed in the image is selected by a user.
9. The method as claimed in claim 1 wherein said coded descriptors also provide information on probability that said CAD-detected abnormalities are indicative of a disease state.
10. The method as claimed in claim 1 wherein the alpha-numeric information is based on Breast Imaging Reporting and Data System (BI-RADS).
11. The method as claimed in claim 1 wherein said alpha-numeric information is a sentence describing in medical terms said CAD-detected abnormalities.
12. The method as claimed in claim 1 wherein said visual markers comprise border delineations of regions.
13. The method as claimed in claim 1 wherein said visual markers comprise one or more highlighted feature used by CAD for determining likelihood of abnormality.
14. The method as claimed in claim 13 wherein said highlighted feature is selected from size, brightness, location, density, number and length of spicules.
15. The method as claimed in claim 13 wherein said highlighted feature comprise individual calcifications within a micro-calcification cluster.
16. The method as claimed in claim 1 wherein said visual markers are color coded according to said probability that the CAD-detected abnormalities are indicative of a disease state.
17. The method as claimed in claim 16 wherein said visual markers are of a same color and wherein a level of probability is indicated by a predetermined shade of said same color.
18. The method as claimed in claim 1 wherein said degrees of transparency to display the visual markers vary dynamically.