Lung Cancer Diagnosis Using Magnetic Resonance Imaging Data Obtained at Three Time Points

• US 20080187200A1
• Filed: 04/28/2005
• Published: 08/07/2008
• Est. Priority Date: 04/28/2005
• Status: Active Grant

• Current Assignee: Yeda Research and Development Co. Ltd. (Weizmann Institute of Science)
• Original Assignee: Yeda Research and Development Co. Ltd. (Weizmann Institute of Science)
• Inventors: Degani, Hadassa, Haran, Edna
• Granted Patent: US 7,949,164 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06V 2201/032 of protuberances, polyps nodules, etc.

Abstract

A malignancy classification method and medium for diagnosing a region of lung tissue based on MRI data are disclosed. The classifying includes: setting time points T₁ and T₂ measured from injection of a contrast agent. T₁ represents a wash-in time point for malignant lung tissue at which a first concentration value of the injected contrast agent is substantially equal to or near a peak for injected contrast agent concentration in the region of lung tissue. Patient concentration values of the contrast agent for the area of lung tissue at time points T₁ and T₂ are obtained, and a malignancy classification for the region of lung tissue is provided by comparing the obtained sample concentration values with a predetermined malignancy profile. A visual representation of the malignancy classification of the region of lung tissue is outputted.

Claims

1. A method of providing a malignancy classification based on MRI data for a region of lung tissue, the method comprising:

setting time points T₁ and T₂ measured from a time point T₀ at or near an injection of a contrast agent, T₁ representing a wash-in time point as detected by MRI for malignant lung tissue at which a first concentration value of the injected contrast agent is substantially equal to or near a peak for injected contrast agent concentration for the malignant lung tissue,

wherein at T₂ a second concentration value of the injected contrast agent for the malignant lung tissue is less than or substantially equal to the first concentration value at T₁, and a third concentration value of the injected contrast agent for non-malignant lung tissue at T₁ is less than or substantially equal to a fourth concentration value of the injected contrast agent concentration for the non-malignant lung tissue at T₂;

obtaining a first sample concentration value of the contrast agent for the region of lung tissue at T₁ and a second sample concentration value of the contrast agent for the region of lung tissue at T₂;

determining a malignancy classification for the region of lung tissue by comparing the obtained sample concentration values with a predetermined malignancy profile; and

outputting a representation of the malignancy classification of the region of lung tissue.

2. The method of claim 1, wherein the second concentration value is greater than the fourth concentration value.

3. The method of claim 1, wherein said determining the malignancy classification comprises judging that the region of lung tissue contains malignancy when the first obtained sample concentration value is greater than the second obtained sample concentration value.

4. The method of claim 1, wherein said determining the malignancy classification comprises judging that the region of lung tissue contains malignancy when the first obtained sample concentration value is substantially equal to the second obtained sample concentration value, and the first obtained sample concentration value is higher than a predetermined first threshold concentration value.

5. The method of claim 1, wherein said determining the malignancy classification comprises judging that the region of lung tissue contains no malignancy when the first obtained sample concentration value is less than the second obtained sample concentration value.

6. The method of claim 1, wherein said determining the malignancy classification comprises judging that the region of lung tissue contains no malignancy when the first obtained sample concentration value is substantially equal to the second obtained sample concentration value, and the first obtained sample concentration value is less than a predetermined second threshold concentration value.

7. The method of claim 1, wherein the setting of the time points T₁ and T₂ comprises:

calculating concentration values of the injected contrast agent at initial time points T₁ and T₂;

finding a maximum intensity for a calibration map comprising a grid with axes K and ν

, K representing a microvascular permeability value and ν

representing an extracellular volume value, and obtaining normalized intensity values of each grid point of the calibration map based on the maximum intensity;

assigning one of multiple categories to each grid point based on a degree of change in concentration values between initial time point T₁ and initial time point T₂;

adjusting the calibration map such that grid points of a first category for grid points with a relatively high degree of change and grid points of a second category for grid points with a relatively low degree of change are approximately equally represented in the calibration map.

8. The method of claim 7, wherein a third category of the multiple categories is assigned to grid points with a degree of change within a predetermined range, the predetermined range being based on a noise level relative to signal strength.

9. The method of claim 8, wherein the predetermined range comprises a range of percent change substantially equal to the noise level relative to signal strength.

10. The method of claim 8, wherein the degree of change falling within the predetermined range is plus or minus 10%.

11. The method of claim 7, wherein said assigning of the one of the multiple categories comprises at least one of coloring and shading the grid point.

12. The method of claim 7, wherein T₁ and T₂ are set such that the first classification is assigned to approximately 75% of grid points representing malignant tissue.

13. The method of claim 1, wherein the representation of the malignancy classification is color-coded image data.

14. The method of claim 1, wherein the representation is a voxel representation.

15. The method of claim 1, wherein the region of lung tissue is evaluated based on the spatial distribution of malignant tissue in the representation.

16. The method of claim 1, wherein registration is used to correct for shifting of the region of tissue in obtaining the concentration values.

17. The method of claim 1, wherein said outputting of the representation comprises outputting a visual representation.

18. The method of claim 1, wherein said outputting of the representation comprises smoothing based on surrounding pixels.

19. A computer-readable medium incorporating a program of instructions for providing a malignancy classification for a region of lung tissue based on MRI data, the program of instructions comprising:

instructions for setting time points T₁ and T₂ measured from a time point T₀ at or near an injection of a contrast agent, T₁ representing a wash-in time point as detected by MRI for malignant lung tissue at which a first concentration value of the injected contrast agent is substantially equal to or near a peak for injected contrast agent concentration for the malignant lung tissue,

wherein at T₂ a second concentration value of the injected contrast agent for the malignant lung tissue is less than or substantially equal to the first concentration value at T₁, and a third concentration value of the injected contrast agent for non-malignant lung tissue at T₁ is less than or substantially equal to a fourth concentration value of the injected contrast agent concentration for the non-malignant lung tissue at T₂;

instructions for obtaining a first sample concentration value of the contrast agent for the region of lung tissue at T₁ and a second concentration value of the contrast agent for the region of lung tissue at T₂;

instructions for determining a malignancy classification for the region of lung tissue by comparing the obtained sample concentration values with a predetermined malignancy profile; and

instructions for outputting a representation of the malignancy classification of the region of lung tissue.

20. The medium of claim 19, wherein the second concentration value is greater than the fourth concentration value.

21. The medium of claim 19, wherein said instructions for determining the malignancy classification comprise instructions for judging that the region of lung tissue contains malignancy when the first obtained sample concentration value is greater than the second obtained sample concentration value.

22. The medium of claim 19, wherein said instructions for determining the malignancy classification comprise instructions for judging that the region of lung tissue contains malignancy when the first obtained sample concentration value is substantially equal to the second obtained sample concentration value, and the first obtained sample concentration value is higher than a predetermined first threshold concentration value.

23. The medium of claim 19, wherein said instructions for determining the malignancy classification comprise instructions for judging that the region of lung tissue contains no malignancy when the first obtained sample concentration value is less than the second obtained sample concentration value.

24. The medium of claim 19, wherein said instructions for determining the malignancy classification comprise instructions for judging that the region of lung tissue contains no malignancy when the first obtained sample concentration value is substantially equal to the second obtained sample concentration value, and the first obtained sample concentration value is less than a predetermined second threshold concentration value.

25. The medium of claim 19, wherein said instructions for setting of the time points T₁ and T₂ comprises:

instructions for calculating concentration values of the injected contrast agent at initial time points T₁ and T₂;

instructions for finding a maximum intensity for a calibration map comprising a grid with axes K and ν

, K representing a microvascular permeability value and ν

representing an extracellular volume value, and obtaining normalized intensity values of each grid point of the calibration map based on the maximum intensity;

instructions for assigning one of multiple categories to each grid point based on a degree of change in concentration values between initial time point T₁ and initial time point T₂;

instructions for adjusting the calibration map such that grid points of a first category for grid points with a relatively high degree of change and grid points of a second category for grid points with a relatively low degree of change are approximately equally represented in the calibration map.

26. The medium of claim 25, wherein a third category of the multiple categories is assigned to grid points with a degree of change within a predetermined range, the predetermined range being based on a noise level relative to signal strength.

27. The medium of claim 26, wherein the predetermined range comprises a range of percent change substantially equal to the noise level relative to signal strength.

28. The medium of claim 26, wherein the degree of change falling within the predetermined range is plus or minus 10%.

29. The medium of claim 25, wherein said instructions for assigning of the one of the three categories comprise at least one of coloring and shading the grid point.

30. The medium of claim 25, wherein T₁ and T₂ are set such that the first classification is assigned to approximately 75% of grid points representing malignant tissue.

31. The medium of claim 19, wherein the representation of the malignancy classification is color-coded image data.

32. The medium of claim 19, wherein the representation is a voxel representation.

33. The medium of claim 19, wherein the region of lung tissue is evaluated based on the spatial distribution of malignant tissue in the representation.

34. The medium of claim 19, wherein registration is used to correct for shifting of the region of tissue in obtaining the concentration values.

35. The method of claim 19, wherein said instructions for outputting the representation comprise instructions for outputting a visual representation.

36. The medium of claim 19, wherein said instructions for outputting the representation comprise instructions for smoothing based on surrounding pixels.