Method and system of computer-aided quantitative and qualitative analysis of medical images from multiple modalities

• US 8,391,574 B2
• Filed: 07/13/2011
• Issued: 03/05/2013
• Est. Priority Date: 11/23/2005
• Status: Active Grant

• Current Assignee: Salient Imaging, Inc.
• Original Assignee: The Medipattern Corp.
• Inventors: Collins, Jeffrey, Lachmann, Frederic, Saghatelyan, Karen, Stapleton, Sandra
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): ANSARI, TAHMINA N
• Application Number:
  US13/182,132
• Publication Number:
  US 20110268338A1
• Time in Patent Office: 601 Days
• Field of Search: None
• US Class Current: 382/128
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 6/03 Computed tomography [CT] echo-tomography A61B8/14
• CPC Class Codes: A61B 6/5247 combining images from an ionising-radiation diagnostic technique and a non-ionising radiation diagnostic technique, e.g. X-ray and ultrasound
• CPC Class Codes: A61B 8/08 Detecting organic movements or changes, e.g. tumours, cysts, swellings A61B8/02 - A61B8/06 take precedence
• CPC Class Codes: G01R 33/5601 involving use of a contrast agent for contrast manipulation, e.g. a paramagnetic, super-paramagnetic, ferromagnetic or hyperpolarised contrast agent
• CPC Class Codes: G01R 33/5608 Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels image data processing or generation, in general G06T
• CPC Class Codes: G01R 33/56366 Perfusion imaging
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20036 Morphological image processing
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 2201/032 of protuberances, polyps nodules, etc.

Abstract

A system and method of computer aided analysis of medical images and detection of malignant lesions is described. Medical images obtained from multiple modalities are analyzed. Morphological features as well as temporal, i.e., kinetics features, are combined to compute a consolidated assessment of a possible lesion detected in the medical images. The system includes at least one kinetics module, which is capable of extracting kinetics features from a time sequence of MRI images or MRS data taken after administering a contrast enhancement agent to a patient. The consolidated assessment is presented to a user for confirmation or modification.

Claims

1. A method of analyzing a plurality of medical image data of a region in an anatomy and detecting abnormalities in the region, at least a set of the plurality of medical image data containing temporal information responsive to administering of a contrast enhancement agent, the method comprising the steps of:

obtaining the plurality of medical image data;

identifying from the plurality of medical image data a set of data points representing a possible lesion in said region;

extracting from the plurality of medical image data features associated with said set of data points, said features including at least two sets of a set of morphological features, a set of kinetics characteristics of the temporal information, and a set of biochemical characteristics;

combining features from said at least two sets of features to arrive at a consolidated classification, a consolidated lesion type and a consolidated lesion extent and computing a staging assessment from a combination of said consolidated classification, said consolidated lesion type and said consolidated lesion extent;

computing an initial diagnostic assessment of said possible lesion from said at least two sets of features, said initial diagnostic assessment incorporating information from said staging assessment; and

providing said initial assessment to a user for evaluation.

2. The method of claim 1, further comprising the steps of:

receiving a modification to said at least two sets of features from the user, and

computing a modified assessment, said modified assessment being computed further incorporating said modification; and

providing said modified assessment to the user for further evaluation.

3. The method of claim 1, wherein the kinetics characteristics are extracted from a contrast variation curve corresponding to time-dependent local contrast variation in a subset of said set of data points.

4. The method of claim 3, wherein the kinetics characteristics include a classification of the contrast variation curve into one of continued enhancement, plateau and washout types.

5. The method of claim 3, wherein the step of extracting the kinetics characteristics includes identifying an envelope enclosing the possible lesion and wherein the contrast variation curve is extracted by identifying said time-dependent local contrast variation in data points enclosed within said envelope.

6. The method of claim 3, further comprising the step of obtaining a plurality of rules associating the set of morphological features, the set of kinetics characteristics of the temporal information, and the set of spectral characteristics with possible diagnosis, said initial assessment and said modified assessment being computed from said plurality of rules and said at least two sets of features.

8. The method of claim 2, wherein the plurality of medical image data includes medical image data acquired from at least two modalities, said computation and re-computation further comprising the steps of:

for each modality of said at least two modalities, computing a modality decision from features extracted from medical image data of said each modality,

correlating said modality decisions in said computation and re-computation.

9. The method of claim 1, wherein the biochemical characteristics are extracted from a spectral analysis of an MRS subset of said set of data points.

10. The method of claim 9, wherein the biochemical characteristics include at least a concentration distribution of a marker chemical.

11. The method of claim 9, wherein the biochemical characteristics include at least relative strength of two or more marker chemicals obtained from a spectroscopic analysis.

12. The method of claim 1, wherein the plurality of medical image data includes at least a set of image data selected from the group of X-ray image data, ultrasound image data, MRI image data, MRS data, CT image data, PET image data, PET/CT image data, digital tomosynthesis image data, and nuclear image data.

13. The method of claim 1, further comprising the step of retrieving patient risk profile information, wherein said evaluation process incorporates said patient risk profile information.

7. The method of 1, wherein the plurality of medical image data includes medical image data acquired from at least two modalities, said computation and re-computation further comprising the steps of:

for each modality of said at least two modalities, computing a modality decision from features extracted from medical image data of said each modality,

correlating said modality decisions in said computation and re-computation.

14. A system for analyzing a plurality of medical image data of a region in an anatomy, at least a set of the plurality of medical image data containing temporal information responsive to administering of a contrast enhancement agent, the system comprising:

an image data module for retrieving the plurality of medical image data;

a morphology module for identifying a possible lesion in said medical image data and extracting and classifying morphological features associated with said possible lesion;

a kinetic module, said kinetics module extracting from the plurality of medical image data kinetics characteristics of the temporal information associated with said possible lesion;

a spectroscopic analysis module, said spectroscopic analysis module extracting from the plurality of medical image data biochemical characteristics relating to one or more marker chemicals;

a consolidation decision engine, said consolidation decision engine receiving said extracted and classified morphological features from said morphology module, said extracted kinetics characteristics of said temporal information from said kinetics module, and said biochemical characteristics from the spectroscopic analysis module, combining features from at least two sets of a set of said extracted and classified morphological features, a set of said extracted kinetics characteristics, and a set of said biochemical characteristics to arrive at a consolidated classification, a consolidated lesion type and a consolidated lesion extent, computing a staging assessment from a combination of said consolidated classification, said consolidated lesion type and said consolidated lesion extent, and computing an initial diagnostic assessment of said possible lesion from said at least two sets of features, said initial diagnostic assessment incorporating information from said staging assessment; and

a graphical user interface for displaying at least a portion of said plurality of medical image data along with said initial diagnostic assessment for user evaluation and modification.

15. The system of claim 14, further comprising:

a morphology decision engine for deriving a morphology assessment from said extracted and classified morphological features;

a kinetics decision engine for deriving a kinetics assessment from said extracted kinetics characteristics; and

a spectroscopic analysis decision engine for deriving a spectroscopic assessment from said biochemical characteristics,

wherein said consolidation decision engine correlates and incorporates said morphology assessment, said kinetics assessment and said spectroscopic assessment in its computation.

16. The system of claim 14, further comprising an annotation module for receiving through said graphical user interface a modification to at least one of said extracted and classified morphological features, said kinetics characteristics and said biochemical characteristics, wherein said consolidation decision engine re-computes a modified diagnostic assessment upon receiving said modification.

17. The system of claim 14, wherein the kinetics module comprises a curve construction module for constructing a contrast variation curve corresponding to time-dependent local contrast variation in a subset of said set of data points and a kinetics analytic module for extracting said kinetics characteristics from said contrast variation curve.

18. The system of claim 14, wherein the image data module is configured for retrieving medical image data of multiple modalities and said consolidation decision engine comprises modules for receiving morphological features and kinetics characteristics extracted from medical image data of each one of said multiple modalities.

19. The system of claim 18, wherein the multiple modalities include X-ray image data, ultrasound image data, MRI image data, MRS data, CT image data, PET image data, PET/CT image data, digital tomosynthesis image data, and nuclear image data.

20. The system of claim 17, wherein the kinetics analytic module is configured to classify the contrast variation curve into one of continued enhancement, plateau and washout types and wherein said kinetics characteristics include said curve type.

21. The system of claim 14, further comprising:

a patient risk profile module for retrieving patient risk profile information from a data base; and

a patient history module for retrieving patient history information;

wherein said evaluation of said assessment incorporates said patient risk profile information and said patient history information.

22. A system for analyzing medical image data of a region in an anatomy, the medical image data being acquired from a plurality of modalities, the system comprising:

an image data module for receiving the medical image data;

a plurality of image processing modules, each for processing image data acquired from one of said plurality of modalities, said each module identifying a possible lesion in said medical image data and extracting and classifying a set of modality characteristics associated with said possible lesion;

a plurality of modality decision engines, each of said modality decision engines computing a modality diagnosis assessment of said possible lesion for a modality of said plurality of modalities from said set of modality characteristics associated with the modality;

a consolidation decision engine, said consolidation decision engine combining said modality diagnosis assessments and computing an initial diagnostic assessment of said possible lesion from said modality diagnosis assessments; and

a graphical user interface for displaying at least a portion of said medical image data along with said initial diagnostic assessment for user evaluation and modification.

23. The system of claim 22, wherein at least part of the medical image data contains temporal information responsive to administering of a contrast enhancement agent to the patient and said set of modality characteristics includes at least one of a set of morphological features and a set of kinetics characteristics of the temporal information.

24. The system of claim 22, wherein at least part of the medical image data contains spectroscopic information obtained from an MRS data acquisition, and said set of modality characteristics includes at least biochemical characteristics of one or more marker chemicals.

25. The system of claim 24, wherein said biochemical characteristics include at least a concentration distribution of said one or more marker chemicals.

26. The system of claim 22, wherein, in identifying the possible lesion, one of the plurality of image processing modules receives input from at least one of another image processing module of the plurality of image processing modules and another modality decision engine of the plurality of modality decision engines.

27. The system of claim 26, wherein said input is a reference to a set of lesion data points corresponding to the possible lesion.