X-ray or gamma ray systems or devices – Specific application – Absorption
Reexamination Certificate
2002-11-27
2003-07-22
Bruce, David V. (Department: 2882)
X-ray or gamma ray systems or devices
Specific application
Absorption
C378S008000, C378S901000
Reexamination Certificate
active
06597762
ABSTRACT:
BACKGROUND OF INVENTION
The present invention relates generally to CT imaging and, more particularly, to a method and apparatus of detecting and validating lesions in a CT image.
CT imaging is commonly used to provide diagnostic images of a medical patient for subsequent review by a radiologist or other health care provider to identify potentially cancerous lesions in the patient. An anatomical region susceptible to cancerous lesions is the lung anatomy and therefore a number of applications have been developed for automatically segmenting and sizing lung lesions that have been identified by a radiologist. Once such application is the CT Advanced Lung Analysis developed by the General Electric Company. Notwithstanding the advances achieved by the CT Advanced Lung Analysis tool, radiology productivity and accuracy may be comprised as the imaging data per anatomical volume increases. That is, advances in CT imaging technology are allowing for thinner image slices and, therefore, more image data per anatomical volume. With the increase of data to be reviewed by the radiologist, assuming a fixed amount of time, the accuracy of the radiologist may also become compromised. Therefore, there is an increasing need for secondary reading reconciliation tools such as computer aided detection schemes as high throughput, large quantity screening data becomes available.
Known detection tools such as the Advanced Lung Analysis provide tremendous capability for radiologist to identify lesions with bookmarks and two-and three-dimensional views. These tools also allow the radiologist to navigate through these bookmarks within a volumetric exam. As such, the radiologist can more effectively and efficiently identify lesions through the display of different view orientations (such as axial, coronal, sagital, or oblique 2D views) and types (maximum intensity projection, volume rendering, and the like) in given layout pre-sets.
Because of the importance of early detection of cancerous lesions, a number of protocols require a secondary review of each diagnostic image generated of the subject. The primary radiologist must then consider the results of the secondary review when making a final determination of lesion presence. However, this secondary review process requires additional review time by the primary radiologist to render a diagnosis; a problem exacerbated as image volume increases.
With the emergence of computer aided detection tools, there increasingly is a need for a graphical user interface (GUI) and a particular layout to visualize secondary reading results of an image to allow a radiologist to compare his or her reading with the reading of a secondary reviewer. Such a tool would provide a logical work flow for the review of CT images and therefore enable a radiologist to efficiently and effectively identify lesions in a CT image.
BRIEF DESCRIPTION OF INVENTION
The present invention is directed to a method and apparatus of detecting and confirming lesions in a CT image overcoming the aforementioned drawbacks. The present invention provides a GUI that allows a radiologist or other medical provider to provide an initial reading of a CT image and thereby indicate those objects of interest that may be lesions. The GUI further allows the radiologist to view those lesions or corresponding bookmarks relative to lesions or objects of interest identified by a secondary user. The secondary review may be completed using a computer aided detection process or the results of a manual review by a separate radiologist. As such, the present invention allows the radiologist to selectively accept or reject those objects of interest identified in the secondary review of the CT image into the primary review of the CT image to generate a final set of bookmarks corresponding to those objects in the CT image that may be considered lesions or other anomalies of concern.
Therefore, in accordance with one aspect of the present invention, an object detection apparatus includes a data acquisition system (DAS) configured to acquire diagnostic data of the subject, an image reconstructor configured to reconstruct at least one image of the subject from the diagnostic data, and a data retrieval device configured to retrieve a first set of bookmarks identifying a first set of objects of interest in the at least one image. The object detection apparatus further includes a computer programmed to display the at least one image on a console and detect input from the user corresponding to a second set of bookmarks identifying a second set of objects of interest in the image. The computer is further programmed to selectively incorporate each bookmark of the first set of bookmarks into the second set of bookmarks.
In accordance with another aspect of the present invention, a computer readable storage medium is provided and has thereon a computer program for determining similarities and differences between separate examinations of a diagnostic image. The computer program includes a set of instructions that when executed by a computer causes the computer to access imaging data from a DAS and display an image of a subject from the imaging data for examination. The computer is further caused to bookmark a primary set of objects of interest based on a set of inputs from a user. The set of instructions further causes the computer to access from memory a secondary set of objects of interest from a separate examination of the image and prompt the user to select each of the secondary set of objects. The computer is also caused to generate a final set of objects of interest from the primary set of objects of interest and the accepted objects of interest from the secondary set of objects of interest.
According to another aspect of the present invention, a method of determining lesion presence in an image of a subject includes the steps of reviewing a diagnostic image of a subject and identifying a first set of lesions in the diagnostic image. The method further includes the steps of bookmarking the first set of lesions and retrieving bookmarks corresponding to a second set of lesions identified in a separate review of the diagnostic image. The method also includes the steps of navigating through the bookmarks for the second set of lesions and selectively incorporating bookmarks from the second set of lesions with bookmarks from the first set of lesions. A final set of bookmarks corresponding to a final set of lesions believed to be present in the diagnostic image is then generated.
In accordance with yet a further aspect of the present invention, a lesion detection tool comprises means for assigning bookmarks to a first set of lesions in a diagnostic image. The lesion detection tool further includes means for retrieving bookmarks for a second set of lesions identified in a separate review of the diagnostic image as well as means for selectively incorporating bookmarks from the second set of lesions into the bookmarks for the first set of lesions.
REFERENCES:
patent: 5255187 (1993-10-01), Sorensen
patent: 5823993 (1998-10-01), Lemelson
patent: 5917929 (1999-06-01), Marshall et al.
patent: 6266435 (2001-07-01), Wang
patent: 6434262 (2002-08-01), Wang
Audet Mirelle
Avila Ricardo S.
Ferrant Matthieu D.
Heckel Beth A.
Jones Cheryl R.
Bruce David V.
Della Penna Michael A.
GE Medical Systems Global Technology Co. LLC
Horton Carl B.
Ziolkowski Patent Solutions Group LLC
LandOfFree
Method and apparatus of lesion detection and validation... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus of lesion detection and validation..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus of lesion detection and validation... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3089591