DENSITY GUIDED ATTENUATION MAP GENERATION IN PET/MR SYSTEMS
First Claim
1. A lung module system, comprising:
- a volume normalization module configured to normalize MR image data that expands intensity values of near zero intensity pixels and compresses intensity values of higher intensity pixels;
a thresholding module configured to generate and apply a threshold for the MR data to differentiate and separate lung pixels from non-lung pixels in a binary volume in three-dimensions;
a lung region of interest (ROI) module generating a lung ROI from the thresholded MR data;
a cropping module configured to crop the initial volume of MR data according to the lung ROI; and
a segmentation module segmenting the MR data to differentiate a lung comprising at least two of lung pixels, lesion pixels, or air pixels.
1 Assignment
0 Petitions
Accused Products
Abstract
A lung segmentation processor (40) is configured to classify magnetic resonance (MR) images based on noise characteristics. The MR segmenatation processor generates a lung region of interest (ROI) and detailed structure segmentation of the lung from the ROI. The MR segmentation processor performs an iterative normalization and region definition approach that captures the entire lung and the soft tissues within the lung accurately. Accuracy of the segmentation relies on artifact classification coming inherently from MR images. The MR segmentation processor (40) correlates segmented lung internal tissue pixels with the lung density to determine the attenuation coefficients based on the correlation. Lung densities are computed using MR data obtained from imaging sequences that minimize echo and acquisition times. The densities differentiate healthy tissues and lesions, which an attenuation map processor (36) uses to create localized attenuation maps for the lung.
-
Citations
20 Claims
-
1. A lung module system, comprising:
-
a volume normalization module configured to normalize MR image data that expands intensity values of near zero intensity pixels and compresses intensity values of higher intensity pixels; a thresholding module configured to generate and apply a threshold for the MR data to differentiate and separate lung pixels from non-lung pixels in a binary volume in three-dimensions; a lung region of interest (ROI) module generating a lung ROI from the thresholded MR data; a cropping module configured to crop the initial volume of MR data according to the lung ROI; and a segmentation module segmenting the MR data to differentiate a lung comprising at least two of lung pixels, lesion pixels, or air pixels. - View Dependent Claims (2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 16, 17, 18)
-
-
8. A lung segmentation system, comprising:
one or more processors configured and programmed to; receive a volume of magnetic resonance (MR) image data; apply a volume normalization function to the MR data to expand intensity values of near zero intensity pixels and compresses intensity values of higher intensity pixels; generate and apply a threshold for the MR data to differentiate and separate lung pixels from non-lung pixels in a binary volume in three-dimensions; generate a lung region of interest (ROI) from the thresholded MR data; crop the initial volume of MR data according to the lung ROI; and segment the MR data to differentiate a lung comprising at least two of lung pixels, lesion pixels, or air pixels.
-
15. A lung segmentation method, comprising:
-
applying a volume normalization function to a MR image to create a normalized volume image; generating and applying a threshold for the MR image to differentiate and separate lung pixels from non-lung pixels in a binary volume in three-dimensions; determining a lung region of interest (ROI) from the thresholded MR image; cropping the MR image according to the lung ROI; and segmenting the MR image to differentiate a lung comprising at least two of lung pixels, lesion pixels, or air pixels.
-
-
19. A method for computing lung densities from MR images, comprising:
-
scanning a lung region of interest using two or more echoes having different echo times to acquire MR data; processing the MR data; calculating lung densities from the MR data; and generating an attenuation map from the lung densities.
-
-
20. A system to generate attenuation maps using MR images comprising:
a segmentation processor having a processor configured to; segment MR images using ROI based localized segmentation accommodating for patient characteristics, image noise, artifact characteristics, and anatomical characters of a ROI; localize at least one organ lesion using density based mapping of intensity values; generate localized attenuation maps based on the density mapping generate an ROI; remove artifacts within the ROI using object tracking across localized regions wherein the object tracking is adapted according to specific MR image characteristics and patient characteristics; test the ROI for correctness; and iteratively repeat ROI generation to optimize the generated ROI.
Specification