Systems and methods for quantifying regional fissure features

• US 10,165,964 B2
• Filed: 05/06/2016
• Issued: 01/01/2019
• Est. Priority Date: 05/08/2015
• Status: Active Grant

• Current Assignee: VIDA Diagnostics, Inc.
• Original Assignee: VIDA Diagnostics, Inc.
• Inventors: Yin, Youbing, Raffy, Philippe
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US15/148,767
• Publication Number:
  US 20160328850A1
• Time in Patent Office: 970 Days
• CPC Class Codes: A61B 5/004 adapted for image acquisition of a particular organ or body part A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/037 Emission tomography
• 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: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Abstract

Analysis of pulmonary scans representative of a patient'"'"'s pulmonary structure can be used to classify a patient into one or more of a plurality of populations. The patient'"'"'s scan can be mapped to a reference domain and analyzed to determine one or more fissure features associated with a plurality of regions in the reference domain. Comparison of the determined fissure features with a plurality of fissure atlases, each associated with different population, can be performed to classify the patient into one or more of the populations. Data from different fissure atlases can be compared to determine regions in the fissure atlases that distinguish one population from another. Such distinguishing regions can improve the ability to classify the patient while reducing errors based on false classifications.

Claims

1. A method for analyzing a patient based on a volumetric pulmonary scan comprising:

receiving a first volumetric pulmonary scan representative of the patient'"'"'s pulmonary structure;

mapping the first volumetric pulmonary scan to a reference domain;

determining one or more fissure features associated with a plurality of regions in the reference domain and within the first volumetric pulmonary scan;

comparing, in each of the plurality of regions, the determined one or more fissure features to a plurality of fissure atlases, each atlas comprising statistical data associated with the one or more fissure features for a population based on regional analysis of volumetric pulmonary scans of that population;

classifying the patient into one or more of the populations based on the comparison of the determined one or more fissure features.

2. The method of claim 1, further comprising:

after the classifying the patient into the one or more of the populations, adding the mapped first volumetric pulmonary scan to the fissure atlas associated with the one or more of the populations; and

updating the statistical data in the fissure atlas to include the first volumetric pulmonary scan.

3. The method of claim 2, wherein updating the statistical data in the fissure atlas to include the first volumetric pulmonary scan data comprises weighting the contribution from the first volumetric pulmonary scan data in the fissure atlas at each of a plurality of regions.

4. The method of claim 1, wherein the one or more of the populations comprises responders to a particular therapy and non-responders to the particular therapy.

5. The method of claim 1, wherein the one or more of the populations comprises patients with collateral ventilation and patients without collateral ventilation.

6. The method of claim 1, wherein the first volumetric pulmonary scan comprises a CT scan, an MRI scan, or a PET scan.

7. The method of claim 1, further comprising:

identifying, for a given fissure feature, distinguishing regions in the volumetric pulmonary scans wherein the given fissure feature is substantially different among the one or more of the populations; and

wherein

comparing the determined one or more fissure features to a plurality of fissure atlases comprises, for the given fissure feature, comparing the given fissure feature in the first volumetric pulmonary scan data to the plurality of fissure atlases in the identified distinguishing regions.

8. The method of claim 7, wherein a set of distinguishing regions are identified corresponding to a pair of fissure atlases and a single fissure feature;

and wherein

for a given fissure feature and pair of the one or more of the populations, the distinguishing regions comprise regions in which the difference between the fissure feature in the pair of fissure atlases is considered significant.

9. The method of claim 8, further comprising:

in each of a plurality of regions, statistically analyzing the fissure feature in a first fissure atlas and the fissure feature in a second fissure atlas and determining the regions in which the difference between the fissure feature in the two atlases is significant in order to determine distinguishing regions corresponding to the first and second fissure atlases and the first fissure feature.

10. The method of claim 1, wherein the one or more fissure features comprises a feature selected from the group consisting of:

fissure integrity, fissure curvature, airway related measurements, deformation field, local vascularity related measurements, and local parenchymal related features.

11. A system for assessing a volumetric pulmonary scan of a patient comprising:

a database comprising a plurality of fissure atlases, each fissure atlas comprising statistical data regarding one or more fissure features in a plurality of volumetric pulmonary regions for a population; and

a processor configured to;

statistically analyze the one or more fissure features in the plurality of volumetric pulmonary regions to determine, for each fissure feature, one or more distinguishing regions;

receive a first set of volumetric pulmonary scan data representative of the volumetric structure of a patient'"'"'s lungs;

determine the one or more fissure features in the first set of volumetric pulmonary scan data at a plurality of regions;

compare the determined one or more fissure features to the plurality of fissure atlases in the database; and

classify the first set of volumetric pulmonary scan data into one or more of the populations based on the comparison.

12. The system of claim 11, wherein the processor is further configured to:

after the classifying the first set of volumetric pulmonary scan data into the one or more of the populations, add the first volumetric pulmonary scan data to the fissure atlas associated with the one or more of the populations; and

update the statistical data in the fissure atlas to include the first volumetric pulmonary scan data.

13. The system of claim 11, wherein the processor is further configured to:

analyze the one or more fissure features in each of a plurality of volumetric pulmonary regions in each of the plurality of fissure atlases;

determine, for each fissure feature, one or more distinguishing regions in the plurality of regions, the one or more distinguishing regions being regions in which the fissure feature differs significantly between at least two fissure atlases; and

associate the determined distinguishing regions with the corresponding fissure feature and fissure atlases.

14. The system of claim 13, wherein classifying the first set of volumetric pulmonary scan data into the one or more of the populations based on the comparison comprises comparing determined fissure features from the first set of volumetric pulmonary scan data to corresponding fissure atlases in the determined distinguishing regions.

15. The system of claim 11, wherein the statistical data in each of the fissure atlases is associated with regions in a reference domain, and wherein the processor is further configured to map the first set of volumetric pulmonary scan data to the reference domain.

16. The system of claim 11, wherein the processor further configured to identify regions in the reference domain, and wherein the identified regions comprise lobes, sub-lobes, and/or custom-defined regions.

17. A method comprising:

acquiring a first plurality of three-dimensional pulmonary models, each of the models being representative of the pulmonary structure of a patient belonging to a first population;

registering each of the three-dimensional models in the first plurality of three-dimensional models to a reference domain to create a first atlas;

statistically analyzing the first plurality of registered three-dimensional models in the first atlas to determine a first fissure feature at each of a plurality of regions in the first atlas;

acquiring a second plurality of three-dimensional pulmonary models, each of the models being representative of the pulmonary structure of a patient belonging to a second population, the second population being different from the first;

registering each of the three-dimensional models in the second plurality of three-dimensional models to the reference domain to create a second atlas;

statistically analyzing the second plurality of registered three-dimensional models in the second atlas to determine the first fissure feature at each of a plurality of regions in the second atlas;

for each of a plurality of regions in the first and second atlases, comparing the first fissure feature of the first atlas to the first fissure feature of the second atlas to determine regions in which the first fissure feature differs significantly between the first and second populations and considering such regions to be distinguishing regions associated with the first population, the second population, and the first fissure feature;

receiving a diagnostic three-dimensional pulmonary model of a first patient'"'"'s lungs;

registering the received diagnostic three-dimensional pulmonary model to the reference domain;

analyzing the first fissure feature in the distinguishing regions in the diagnostic three-dimensional pulmonary model; and

predicting if the first patient is in the first population or the second population based on the analyzed first fissure feature in the distinguishing regions in the diagnostic three-dimensional pulmonary model.

18. The method of claim 17, wherein:

the first population comprises patients who responded positively to a particular therapy;

the second population comprises patients who did not respond positively to the particular therapy; and

the comparing the first fissure feature of the first atlas to the first fissure feature of the second atlas for each of the plurality of regions comprises determining a correlation between the first fissure feature in each region and the effectiveness of the particular therapy.

19. The method of claim 18, wherein determining a correlation between the first fissure feature in each region and the effectiveness of the particular therapy comprises determining in which of the plurality of regions the difference in the first fissure feature between the first population and the second population is greatest.

20. The method of claim 18, wherein the first fissure feature comprises a feature selected from the group consisting of:

fissure integrity, fissure curvature, airway related measurements, deformation field, local vascularity related measurements, and local parenchymal related features.

21. The method of claim 17, further comprising:

for each of a plurality of regions in the first and second atlases, comparing the each of a plurality of fissure features of the first atlas to a corresponding fissure feature of the second atlas to determine, for each fissure feature, regions in which that fissure feature is most different between the first and second populations and considering such regions to be distinguishing regions with associated with the first population, the second population, and that fissure feature.

22. The method of claim 17, wherein

the first population comprises patients who display at least one diagnostic symptom;

the second population comprises patients who do not display the at least one diagnostic symptom; and

the comparing the first fissure feature of the first atlas to the first fissure feature of the second atlas for each of the plurality of regions comprises determining a correlation between the first fissure feature in each region and the likelihood of a patient displaying the at least one diagnostic symptom.

23. The method of claim 22, wherein the at least one diagnostic symptom comprises collateral ventilation.

24. The method of claim 23, wherein the first fissure feature is based on an airway distance.