Image analysis – Applications – Biomedical applications
Reexamination Certificate
2001-11-23
2004-07-20
Mehta, Bhavesh M. (Department: 2625)
Image analysis
Applications
Biomedical applications
C382S173000, C382S199000, C382S257000, C378S062000, C128S922000
Reexamination Certificate
active
06766043
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to nodule detection from digital images. The invention further provides an algorithm for recovering and identifying regions of nodules and systems for using such an algorithm as an aid to medical diagnosis and disease evaluation.
BACKGROUND OF THE INVENTION
The diagnostically superior information available from data acquired from various imaging systems, especially that provided by multidetector CT (multiple slices acquired per single rotation of the gantry) where acquisition speed and volumetric resolution provide exquisite diagnostic value, enables the detection of potential problems at earlier and more treatable stages. Given the vast quantity of detailed data acquirable from imaging systems, various algorithms must be developed to efficiently and accurately process image data. With the aid of computers, advances in image processing are generally performed on digital or digitized images.
Digital acquisition systems for creating digital images include digital X-ray film radiography, computed tomography (“CT”) imaging, magnetic resonance imaging (“MRI”) and nuclear medicine imaging techniques, such as positron emission tomography (“PET”) and single photon emission computed tomography (“SPECT”). Digital images can also be created from analog images by, for example, scanning analog images, such as typical x-rays, into a digitized form. Further information concerning digital acquisition systems is found in our above-referenced copending application “Graphical User Interface for Display of Anatomical Information”.
Digital images are created from an array of numerical values representing a property (such as a grey scale value or magnetic field strength) associable with an anatomical location referenced by a particular array location. In 2-D digital images, or slice sections, the discrete array locations are termed pixels. Three-dimensional digital images can be constructed from stacked slice sections through various construction techniques known in the art. The 3-D images are made up of discrete volume elements, also referred to as voxels, composed of pixels from the 2-D images. The pixel or voxel properties can be processed to ascertain various properties about the anatomy of a patient associated with such pixels or voxels.
Once in a digital or digitized format, various analytical approaches can be applied to process digital anatomical images and to detect, identify, display and highlight regions of interest (ROI). For example, digitized images can be processed through various techniques, such as segmentation. Segmentation generally involves separating irrelevant objects (for example, the background from the foreground) or extracting anatomical surfaces, structures, or regions of interest from images for the purposes of anatomical identification, diagnosis, evaluation, and volumetric measurements. Segmentation often involves classifying and processing, on a per-pixel basis, pixels of image data on the basis of one or more characteristics associable with a pixel value. For example, a pixel or voxel may be examined to determine whether it is a local maximum or minimum based on the intensities of adjacent pixels or voxels.
Once anatomical regions and structures are constructed and evaluated by analyzing pixels and/or voxels, subsequent processing and analysis exploiting regional characteristics and features can be applied to relevant areas, thus improving both accuracy and efficiency of the imaging system. For example, the segmentation of an image into distinct anatomical regions and structures provides perspectives on the spatial relationships between such regions. Segmentation also serves as an essential first stage of other tasks such as visualization and registration for temporal and cross-patient comparisons.
Key issues in digital image processing are speed and accuracy. For example, the size of a detectable tumor or nodule, such as a lung nodule, can be smaller than 2 mm in diameter. Moreover, depending on the particular case, a typical volume data set can include several hundred axial sections, making the total amount of data 200 Megabytes or more. Thus, due to the sheer size of such data sets and the desire to identify small artifacts, computational efficiency and accuracy are of high priority to satisfy the throughput requirements of any digital processing method or system.
Previous work in the area nodule detection as applied to thoracic region includes the following:
Lee et al proposed a template matching technique to detect lung wall nodules (“Pulmonary Nodule Detection in Helical X-Ray CT Images Based on an Improved Template-matching Technique”, RSNA00; Y. Lee; T. Hara; H. Fujita; S. Itoh; T. Ishigaki; M. Tsuzaka). Semicircular models together with information on the tangent of lung wall curves were used in the matching process. This method suffers from inflexibility in dealing with the size variability of nodules.
Armato et al used a technique called rolling-ball (disk) (“A Computer-aided Diagnostic Method for the Detection of Lung Nodules in CT Scans”. RSNA00. Samuel G. Armato et al.) In Armato, on each axial slice of digital lung images, a 2-D disk filter is successively placed tangential to points on the pleura. An indentation is identified when the disk filter contacts a contour at more than one location. Such indentation is then filled and brought back to the lung field as candidates of pleural nodules. A similar rolling-ball technique was used by Fetita in his work on bronchial tree reconstruction (“Three-Dimensional Reconstruction of Human Bronchial Tree in HRCT,” SPIE99. C. Fetita, F. Preteux). Such a technique has difficulty optimizing the disk filter size and in controlling the spacing between test points on the pleura. It also has limitations in its extension to 3-D, and therefore does not fully exploit the smoothness of lung shapes.
It is desirable to provide such systems and methods for imaging that can effectively deal with the size variability of nodules. It is further desirable to provide nodule detection systems and methods that provide accurate results for diagnosis. It is desirable to provide a nodule detection approach for registering and detecting nodules from 2-D and 3-D data sets. It is desirable to provide a nodule detection approach that can be adapted to perform on partial volumes to reduce processing loads. It is further desirable to provide a nodule detection process and system that relies on common attributes such as image edges, texture, shapes and image amplitude. It is further desirable to provide a method and apparatus for improved sensitivity and specificity in lung nodule detection in digital imaging to enable early and accurate diagnosis.
Methods and apparatus in accordance with embodiments of this invention overcome the foregoing and other problems.
SUMMARY OF THE INVENTION
The present invention is directed to a method for detecting nodules that exploits various analytical techniques, including morphological closing and surface fitting with deformable models. An algorithm of the present invention recovers regions of possible nodules or tumors that would have been left out of the organ field or otherwise undetected due to the nature of low level image processing in the organ field. The algorithm uses a morphological dilation with a structuring element to detect nodules within the structuring element. Next, structuring element deformable surface-based analysis is performed in distinctive regions for the identification of larger nodules.
REFERENCES:
patent: 5757953 (1998-05-01), Jang
patent: 5881124 (1999-03-01), Giger et al.
patent: 5982917 (1999-11-01), Clarke et al.
patent: 6058322 (2000-05-01), Nishikawa et al.
patent: 6078680 (2000-06-01), Yoshida et al.
patent: 6125194 (2000-09-01), Yeh et al.
patent: 6138045 (2000-10-01), Kupinski et al.
patent: 6185320 (2001-02-01), Bick et al.
patent: 6335980 (2002-01-01), Armato et al.
patent: 6549646 (2003-04-01), Yeh et al.
patent: 2002/0006216 (2002-01-01), Armato et al.
M.L.Giger, Computerized scheme for the detection of pulmonary no
Zeng Xiaolan
Zhang Wei
Mehta Bhavesh M.
Morgan & Lewis & Bockius, LLP
R2 Technology, Inc.
Sukhaphadhana Christopher
LandOfFree
Pleural nodule detection from CT thoracic images does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pleural nodule detection from CT thoracic images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pleural nodule detection from CT thoracic images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3205878