Considerations when colon segmentation differs between CAD processing and visualization

Abstract

A system and method for preserving CAD marks falling outside the three-dimensional rendering on a visualization display following segmentation of CT medical image slices for review by a user is disclosed. The CT medical images are processed by both a CAD algorithm and a visualization workstation. The CAD algorithm reports detected suspicious regions to the visualization workstation for display on the three-dimensional rendering of the medical images as well as creates a list of the detections to notify the user. If the detected CAD marks are not located on the three-dimensional rendering of the medical images, the user is notified. The user can the view the detected CAD marks on the two-dimensional CT medical images.

Description

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

The following detailed description of specific embodiments of the present invention can be best understood when read in conjunction with the following drawings, where like structure is indicated with like reference numerals and in which:

FIG. 1 is a flow chart illustrating the flow of data according to an embodiment of the present invention.

FIG. 2 illustrates displaying a suspicious CAD mark on a three-dimensional rendering of the CT medical images according to an embodiment of the present invention.

FIG. 3 illustrates marking a suspicious CAD mark on a two-dimensional medical image according to an embodiment of the present invention.

DETAILED DESCRIPTION

In the following detailed description of the embodiments, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration, and not by way of limitation, specific embodiments in which the invention may be practiced. It is to be understood that other embodiments may be utilized and that logical, mechanical and electrical changes may be made without departing from the spirit and scope of the present invention.

Referring initially to FIG. 1, when a CT medical image case is processed in step 100, both the visualization workstation 120 and the CAD algorithm 110 segment the medical images. The CT medical images can be taken from a colon or any other anatomical region that may benefit from CAD processing. The CAD algorithm 110 further examines the medical images for suspicious regions and reports the results to the visualization workstation 120 for display 130. On the workstation 120, the suspicious regions from the CAD algorithm are indicated on display 130 for the three-dimensional rendering or visualization of the anatomical region (for example, referring to FIG. 2, with an arrow pointing to the suspicious region) and for the two-dimensional slices of the anatomical region (for example, referring to FIG. 3, with a box surrounding the suspicious region). Additionally, a complete list of CAD marks found on the CT medical images is provided to the user on the display 130. This list of detections allows the user to jump directly to any CAD mark by selecting, or highlighting, a listed CAD mark.

It is possible for a CAD-mark to not be visible in the displayed three-dimensional rendering, or visualization, particularly if the medical image segmentations of the visualization software and the CAD algorithm differ. In this case, the user can be alerted to CAD marks that fall outside the three-dimensional rendering of the anatomical region and that the CAD marks are not visible in the display of three-dimensional rendering, or visualization, so that the user knows to refer back to the two-dimensional CT medical image slices for the primary read. The CAD marks not visualized on the three-dimensional rendering could be differentiated on the display of the CAD list of detections (for example, in a different color). Additionally, a dialog box alerting the user may pop up in the display 130 if the user selects a CAD mark from the list of detections that falls outside the three-dimensional rendering of the anatomical region segmented by the visualization workstation software.

It is noted that terms like “preferably,” “commonly,” and “typically” are not utilized herein to limit the scope of the claimed invention or to imply that certain features are critical, essential, or even important to the structure or function of the claimed invention. Rather, these terms are merely intended to highlight alternative or additional features that may or may not be utilized in a particular embodiment of the present invention.

Having described the invention in detail and by reference to specific embodiments thereof, it will be apparent that modifications and variations are possible without departing from the scope of the invention defined in the appended claims. More specifically, although some aspects of the present invention are identified herein as preferred or particularly advantageous, it is contemplated that the present invention is not necessarily limited to these preferred aspects of the invention.

Claims

1. A method of displaying computer-aided detection marks on medical imagery, the method comprising: segmenting a series of computed tomography medical images by a computer-aided detection algorithm and visualization workstation software;reporting suspicious regions detected by the computer-aided detection algorithm to the visualization workstation; andalerting a user if a detected suspicious region is not visible on the segmented depiction on the visualization workstation.

2. The method of claim 1, wherein the medical imagery is taken from the colon.

3. The method of claim 1, wherein the step of alerting the user differentiates non-visible suspicious regions by listing the suspicious regions in a different color on a list of suspicious regions than the visible suspicious regions.

4. The method of claim 1, wherein the step of alerting the user pops up a dialog box on the visualization workstation display when the user selects a non-visible suspicious region from a list of suspicious regions.

5. The method of claim 1, further comprising: displaying suspicious regions detected by the computer-aided detection algorithm on the visualization workstation.

6. The method of claim 1, further comprising: displaying suspicious regions as well as a list of all of the suspicious regions detected by the computer-aided detection algorithm on the visualization workstation.

7. The method of claim 1, further comprising: providing a list of suspicious regions to the visualization workstation for display.

8. The method of claim 7, further comprising: selecting a suspicious region to view from the list of suspicious regions; andjumping to a display of that suspicious region on the medical imagery displayed on the visualization workstation after selection of the suspicious region.

9. The method of claim 1, further comprising: providing a list of suspicious regions to the visualization workstation for display;selecting a suspicious region to view from the list of suspicious regions; andjumping to a display of that suspicious region on the medical imagery displayed on the visualization workstation after selection of the suspicious region.

10. The method of claim 9, wherein the step of selecting a suspicious region is through the use of user-invoked controls.

11. The method of claim 10, wherein the user-invoked controls comprise a computer mouse, a touch screen, a pen stylus, a display button, or combinations thereof.

12. The method of claim 1, further comprising: reviewing non-visible suspicious regions on the two-dimensional computed tomography medical images.

13. The method of claim 1, further comprising: displaying both the segmented three-dimensional and two-dimensional renderings of the computed tomography medical images on the workstation display.

14. The method of claim 13, further comprising: marking the computer-aided detected suspicious regions on the segmented three-dimensional and two-dimensional renderings of the computed tomography medical images on the workstation display.

15. The method of claim 14, further comprising: marking the computer-aided detected suspicious regions on the segmented three-dimensional on the workstation display with arrows pointing to the computer-aided detected suspicious regions.

16. The method of claim 14, further comprising: marking the computer-aided detected suspicious regions on the two-dimensional renderings of the computed tomography medical images on the workstation display with boxes surrounding the computer-aided detected suspicious regions.

17. The method of claim 1, further comprising: examining the series of computed tomography medical images for suspicious regions using the computer-aided detection algorithm.

18. A method of displaying computer-aided detection marks on medical imagery, the method comprising: segmenting a series of computed tomography medical images by a computer-aided detection algorithm and visualization workstation software;reporting suspicious regions detected by the computer-aided detection algorithm to the visualization workstation;providing a list of suspicious regions to the visualization workstation;selecting a suspicious region to view from the list of suspicious regions;alerting a user if the selected suspicious region is not visible on the displayed segmented depiction on the visualization workstation; andjumping to a display of that suspicious region on the medical imagery displayed on the visualization workstation after selection of the suspicious region.

19. The method of claim 18, further comprising: displaying suspicious regions detected by the computer-aided detection algorithm on the visualization workstation.

20. The method of claim 18, further comprising: displaying a list of suspicious regions detected by the computer-aided detection algorithm on the visualization workstation.

21. The method of claim 18, further comprising: displaying suspicious regions as well as a list of all of the suspicious regions detected by the computer-aided detection algorithm on the visualization workstation.

22. The method of claim 18, further comprising: examining the series of computed tomography medical images for suspicious regions using the computer-aided detection algorithm.

23. The method of claim 18, further comprising: displaying both three-dimensional segmented and two-dimensional renderings of the computed tomography medical images on the workstation display.

24. The method of claim 23, further comprising: marking the computer-aided detected suspicious regions on the segmented three-dimensional and two-dimensional renderings of the computed tomography medical images on the workstation display.

25. The method of claim 23, further comprising: reviewing the selected non-visible suspicious regions on the two-dimensional computed tomography medical images.

26. A system for displaying computer-aided detection marks on medical imagery, the system comprising: a computed tomography medical images processor for processing the medical imagery;a visualization workstation, wherein the visualization workstation comprises software that segments the computed tomography medical images and wherein the visualization workstation displays the processed segmented computed tomography medical images; anda computer-aided detection algorithm, wherein the computer-aided detection algorithm segments the computed tomography medical images, examines the computed tomography medical images for suspicious regions, reports the suspicious regions to the visualization workstation, and alerts a user if a suspicious region is not visible on the segmented depiction on the visualization workstation.

27. The system of claim 26, wherein the visualization workstation displays both three-dimensional and two-dimensional renderings of the computed tomography medical images.

28. The system of claim 26, wherein the visualization workstation displays both three-dimensional and two-dimensional renderings of the computed tomography medical images with the computer-aided detected suspicious regions marked on the segmented three-dimensional and two-dimensional renderings of the computed tomography medical images on the workstation display.

29. The system of claim 26, wherein the computer-aided detection algorithm provides a list of suspicious regions to the visualization workstation for display

30. The system of claim 29, wherein the computer-aided detection algorithm alerts the user by differentiating non-visible suspicious regions from the visible suspicious regions on the list of suspicious regions by using different colors.

31. The system of claim 29, wherein the computer-aided detection algorithm alerts the user by popping up a dialog box when the user selects a non-visible suspicious region from the list of suspicious regions.