Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10902596-B2
Publication Date
2021-01-26
Expiration Date
Abstract
Data from a tomographic scan (14) that provides three-dimensional information about a patient's brain comprises the steps of: filtering and re-sampling (21) the data to produce a three-dimensional image; performing registration (23) to align the three-dimensional image with a reference image (16), using 3-D rigid and/or non-rigid transformations; identifying (25) image features in the aligned image, to identify which voxels or regions of adjacent voxels correspond to image features that represent structures within the brain that are expected to be evident; classifying (26) each voxel within an identified image feature by a voxel score that corresponds to the difference between the attenuation of that voxel and the expected attenuation at that region of the brain; and deducing a cumulative score that combines the voxel scores from all the voxels of at least a region of the brain. This method can provide a medical professional with a rapid indication of the status of the brain tissue, which can be used to guide the selection of treatment to best improve the prospects for a patient, particularly a patient who has had an ischaemic stroke.
Core Innovation
The invention provides a computer-implemented method for deriving a score representative of extent and progression of ischemia in a patient's brain by analyzing data from a tomographic scan that provides three-dimensional information about the patient's brain. The method processes the data to produce a three-dimensional image representative of the patient's brain and performs registration to align the three-dimensional image with a reference image using 3-D rigid and/or non-rigid transformations.
Regions in the aligned image are identified that correspond to normal regions within a brain, and the attenuation of each of a plurality of first voxels or group of adjacent voxels is determined within each identified region. For each first voxel or group of adjacent voxels, the method classifies by a probability value derived from, and indicative of, a difference between the determined attenuation and an expected attenuation of that voxel or group at the region of the brain.
The classification includes determining, from the same aligned image, the attenuation of a respective second voxel or group of voxels in a corresponding region on the opposite side of the brain having the same type of brain structure, comparing the determined attenuations to derive a value for the difference, and generating a voxel score comprising the probability value indicative of the difference. One or more probability values are applied to each identified region to generate a probability map of ischemic changes within the patient's brain, and a cumulative score is then deduced that combines the probability values from all the voxels of at least an identified region of the patient's brain.
The method includes optional weighting based on functional relevance to patient outcome and disability, with visualization by displaying two-dimensional images calculated from the three-dimensional image data with the probability values superimposed.
Claims Coverage
The independent claims are clm-00001, clm-00008, and clm-00013. Across these independent claims, there are 7 inventive features, including 3D image processing and registration, attenuation-based voxel classification with opposite-side comparison, probability map generation, cumulative scoring, and 2D superimposed display.
3D image processing and registration to reference
Processing tomographic scan data to produce a three-dimensional image representative of the patient's brain; performing registration to align the three-dimensional image with a reference image using 3-D rigid and/or non-rigid transformations.
Identifying normal regions and determining voxel attenuation
Identifying regions in the aligned image that correspond to normal regions within a brain; determining, from the aligned image, the attenuation of each of a plurality of first voxels or group of adjacent voxels within each identified region of the brain.
Voxel classification by probability from attenuation difference to expected attenuation
Classifying each first voxel or group of adjacent voxels within each identified region by a probability value derived from, and indicative of, a difference between the determined attenuation and an expected attenuation at that region of the brain, including attenuation on the opposite side of the brain having the same type of brain structure and comparison to derive a difference.
Probability map generation from applied probability values
Applying one or more probability values to each identified region to generate a probability map of ischemic changes within the patient's brain, where each applied probability value is indicative of a strength of evidence of ischemia at a respective identified region.
Cumulative ischemia score combining voxel probability values
Deducing a cumulative score that combines the probability values from all the voxels of at least an identified region of the patient's brain.
Functional relevance weighting and 2D superimposed display
Optional weighting based on functional relevance to patient outcome and disability; displaying two-dimensional images calculated from the three-dimensional image data with the probability values superimposed.
Severity and location assessment via 3D CT and probability-based scoring
Performing a three-dimensional computed-tomography scan of the patient's head; processing data to produce a three-dimensional image representative of the patient's brain; performing registration to align with a reference image using 3-D rigid and/or non-rigid transformations; identifying normal regions; determining attenuation; classifying voxels by probability value derived from attenuation difference to expected attenuation; applying probability values to generate a probability map of ischemic changes; and deducing a cumulative score combining probability values from at least an identified region.
Across the independent claims, ischemic changes are assessed by registering a 3D brain image derived from tomographic/CT data to a reference, determining attenuation for voxels or groups in normal regions, classifying voxels by probability values based on attenuation differences relative to expected attenuation including opposite-side comparison, generating a probability map, and in certain claims deducing a cumulative score and displaying 2D images with the probability values superimposed.
Stated Advantages
Provides a score representative of extent and progression of ischemia in a patient's brain.
Enables assessment of severity and location of a stroke in a patient.
Generates a probability map of ischemic changes within the patient's brain, with strength of evidence of ischemia at identified regions.
Provides a cumulative score combining probability values from voxels of at least an identified region.
Supports visualization by displaying two-dimensional images with probability values superimposed.
Documented Applications
CT-based assessment of ischemic changes in a patient's brain, including deriving a score representative of extent and progression of ischemia.
Assessment of severity and location of a stroke in a patient using 3D CT scanning and probability-based ischemia mapping.
Displaying information about severity and location of stroke by superimposing probability values on 2D images calculated from 3D image data.
Interested in licensing this patent?