Visualization and quantification of lung disease utilizing image registration

• US 10,255,679 B2
• Filed: 09/07/2017
• Issued: 04/09/2019
• Est. Priority Date: 05/15/2014
• Status: Active Grant

• Current Assignee: VIDA Diagnostics, Inc.
• Original Assignee: VIDA Diagnostics, Inc.
• Inventors: Yin, Youbing, Raffy, Philippe, Wood, Susan A.
• Primary Examiner(s): Lu, Tom Y
• Application Number:
  US15/698,179
• Publication Number:
  US 20180068443A1
• Time in Patent Office: 579 Days
• CPC Class Codes: A61B 5/091 Measuring volume of inspired or expired gases, e.g. to determine lung capacity
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/50 specially adapted for specific body parts; specially adapted for specific clinical applications
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: A61B 6/5235 combining images from the same or different ionising radiation imaging techniques, e.g. PET and CT
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/10104 Positron emission tomography [PET]
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 2219/2012 Colour editing, changing, or manipulating; Use of colour codes
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

Methods and systems for assessing lung function using volumetric images obtained at inspiration and expiration. The method may include processing the first and second set of images to identify known anatomical structures of the lungs, registering the first set of images to the second set of images to match voxels of the first set of images to voxels of the second set of images as matched pairs of inspiratory and expiratory voxels, calculating a continuous probability of a lung characteristic at a location of the matched pairs of voxels, and displaying the result on a display. The method may also include classifying lung tissue at each location as normal, having air trapping without emphysema, or being emphysematous.

Claims

1. A method of assessing lung function using a first set of lung volumetric images and a second set of volumetric images, the method comprising:

a) registering the first set of images to the second set of images to match voxels of the first set of images to voxels of the second set of images as matched pairs voxels;

b) calculating a probability of a lung characteristic and/or classifying a severity of a lung abnormality at each of a plurality of locations, each of the plurality of locations corresponding to one of the matched pairs of voxels of step a); and

c) presenting a result of step b) on a display or in a report, the presented result comprising the calculated probability and/or the severity classification of the lung abnormality at each of a plurality of locations of matched pairs of voxels.

2. The method of claim 1 wherein presenting the result comprises generating an image depicting a set of data points, wherein each data point represents the calculated probability of the lung characteristics and/or the severity classification of the lung abnormality of the matched pairs of voxels of steps b).

3. The method of claim 2 wherein the image comprises 3 dimensional representation of the lungs, wherein each data point is depicted in the representation at a location corresponding to the location of the matched pair of voxels.

4. The method of claim 1 further comprising:

d) registering a third set of images to a fourth set of images as matched pairs of voxels, the third and fourth sets of images are obtained at a later time than the first and second sets of images;

e) calculating the probability of the lung characteristic and/or classifying the severity of a lung abnormality at locations of the matched pairs of voxels of step d);

registering the first set of images and/or the second set of images to the third set of image and/or the fourth set of images;

f) comparing the results from step e) to the results from step b) to measure the change in the probability of the lung characteristic and/or the classified severity of the lung abnormality at the plurality of locations over time; and

g) displaying a result of step f) on the display or in a report.

5. The method of claim 1 wherein the probability of a lung characteristic is a combination of a probability of tissue destruction and a probability of a ventilation deficit and/or the classified severity of a lung abnormality comprises the severity of tissue destruction and a severity of ventilation deficit.

6. The method of claim 5 wherein

presenting the result comprises generating a color image depicting a set of data points, wherein the color of each data point represents the calculated probability of the lung characteristic and/or the classified severity of the lung abnormality of the matched pairs of voxels of steps b), and wherein

the color of each data point is a composite of a first color component dependent upon the probability and/or classified severity of a ventilation deficit and a second color component dependent upon the probability and/or classified severity of tissue destruction.

7. The method of claim 6 wherein each data point is displayed on a graph with the probability and/or severity classification of tissue destruction on a first scale and probability and/or severity classification of ventilation deficit on a second scale.

8. The method of claim 7 wherein the graph further comprises a plurality of topographic lines, wherein each topographic line indicates an equal number of data points occurring at all coordinates on each topographic line.

9. The method of claim 6 wherein the color image comprises a 3 dimensional representation of the lungs, wherein each data point in the representation is located at a location corresponding to a location of the matched pair of voxels in the patient'"'"'s lungs.

10. The method of claim 1 wherein step b) comprises calculating a probability of a lung characteristic, and further comprising classifying lung tissue at the location of the matched pairs of voxels step b) by using the calculated probability as being normal or being abnormal.

11. The method of claim 10 further comprising classifying the lung tissue which is abnormal as having air trapping without emphysema, having emphysema without air trapping, or as having emphysema with air trapping.

12. The method of claim 1, wherein displaying the result comprises displaying, in a report, numerical or graphical reports that summarize the result across various lobes of the lung.

13. A system for assessing lung function using a first set of lung volumetric images and a second set of volumetric images from a patient, the system comprising:

a processor;

computer readable medium; and

software executable by the processor, the software configured to;

a) register the first set of images to the second set of images to match voxels of the first set of images to voxels of the second set of images as matched pairs of inspiratory and expiratory voxels;

b) calculate a probability of a lung characteristic and/or classify a severity of a lung abnormality at each of a plurality of locations, each of the plurality of locations corresponding to one of the matched pairs of voxels of step a); and

c) generate an image depicting a set of data points, wherein each data point represents the calculated probability and/or classified severity of each of the matched pairs of voxels of step c) or a different value derived from the probability and/or classified severity of each of the matched pairs of voxels of step c).

14. The system of claim 13 wherein each data point is depicted in the representation at a location corresponding to a location of the matched pair of voxels in the patient'"'"'s lungs.

15. The method of claim 14 wherein the probability of a lung characteristic is a probability of tissue destruction and a probability of a ventilation deficit and/or the classified severity of a lung abnormality corresponds to a severity of tissue destruction and ventilation deficit.

16. The method of claim 15 wherein the image comprises a plurality of colors in a color spectrum, and wherein the color of each data point is a composite of a first color component dependent upon the probability and/or classified severity of a ventilation deficit and a second color component dependent upon the probability and/or classified severity of tissue destruction.

17. The system of claim 13, the software further configured to calculate a probability of a tissue being normal at the location in the lung corresponding to each matched pair of voxels of step b) using the probability of the lung characteristic.

18. The system of claim 17, the software further configured to calculate a probability of the tissue being emphysematous without air trapping, a probability of the tissue being emphysematous with air trapping, and a probability of the tissue having air trapping without emphysema at the location in the lung corresponding to each matched pair of voxels of step b) using the probability of the lung characteristic.

19. The system of claim 18, the software further configured to use the probabilities of the tissue being normal, emphysematous with air trapping, emphysematous without air trapping, or having air trapping without emphysema to classify the tissue as normal, emphysematous with air trapping, emphysematous without air trapping, or having air trapping without emphysema at the location in the lung corresponding to each matched pair of voxels.

20. The system of claim 19 wherein the image comprises a 3 dimensional representation of the lungs using colors corresponding to the classification at the location of each matched pair of voxels.

21. The system of claim 13, wherein the software is further configured to output a numerical or graphical report that summarizes the result across the various lobes of lung.

22. The system of claim 21, further comprising a display, and wherein the software is further configured to present the image and/or the report to a user on the display.