METHOD AND SYSTEM OF CLASSIFYING MEDICAL IMAGES

• US 20110317892A1
• Filed: 06/28/2011
• Published: 12/29/2011
• Est. Priority Date: 06/28/2010
• Status: Active Grant

• Current Assignee: BAR ILAN University, Ramot at Tel Aviv University Limited (Tel Aviv University), Tel Hashomer Medical Research Infrastructure And Services Ltd.
• Original Assignee: BAR ILAN University, Ramot at Tel Aviv University Limited (Tel Aviv University), TEL Hashomer Medical Research Infrastructure and Services Limited
• Inventors: GREENSPAN, Hayit, GOLDBERGER, Jacob, AVNI, Uri, KONEN, Eli, SHARON, Michal
• Granted Patent: US 9,122,955 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 6/503 for diagnosis of the heart
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 3/10 Selection of transformation methods according to the characteristics of the input images
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/464 using a plurality of salient features, e.g. bag-of-words [BoW] representations

Abstract

A method of generating a category model for classifying medical images. The method comprises providing a plurality of medical images each categorized as one of a plurality of categorized groups, generating an index of a plurality of visual words according to a distribution of a plurality of local descriptors in each the image, modeling a category model mapping a relation between each visual word and at least one of the categorized groups according to the index, and outputting the category model for facilitating the categorization of an image based on local descriptors thereof.

Claims

1. A method of generating a category model for classifying medical images, comprising:

providing a plurality of medical images each categorized as one of a plurality of categorized groups;

generating an index of a plurality of visual words according to a distribution of a plurality of local descriptors in each said image;

modeling a category model mapping a relation between each said visual word and at least one of said plurality of categorized groups according to said index; and

outputting said category model for facilitating the categorization of an image based on local descriptors thereof.

2. The method of claim 1, further comprising dividing said plurality of medical images among said plurality of categorized groups.

3. The method of claim 1, wherein said index comprises less than 700 visual words.

4. The method of claim 1, wherein said plurality of medical images are part of a training set having more than 10,000 medical images.

5. The method of claim 1, wherein said generating comprises clustering said plurality of local descriptors in a plurality of clusters, said plurality of visual words being defined according to said plurality of clusters.

6. The method of claim 5, wherein said clustering is performed according to a principal component analysis (PCA).

7. The method of claim 1, wherein said modeling is performed using a support vector machine (SVM) training procedure.

8. The method of claim 1, wherein said SVM training procedure is a multi-class SVM with a radial basis function (RBF) kernel.

9. The method of claim 1, wherein said plurality of medical images are provided from a picture archiving communication system (PACS).

10. The method of claim 1, wherein said plurality of categorized groups define a plurality of pathologies.

11. The method of claim 1, further comprising automatically categorizing said plurality of medical images.

12. A method of classifying a medical image using a category model, comprising:

providing a category model which maps a plurality of visual-words in a space, each said visual-word being associated with at least one of a plurality of image categories;

receiving an examined medical image;

identifying a group of said plurality of visual-words in said examined medical image;

using said category model to match said group with an image category of said plurality of image categories; and

outputting said image category.

13. The method of claim 12, wherein said outputting comprises presenting said image category in a client terminal used to provide said examined medical image.

14. The method of claim 12, wherein identifying is performed without segmenting said examined medical image.

15. The method of claim 12, wherein identifying is performed without registering said examined medical image.

16. The method of claim 12, further comprising updating said category model according to said matching.

17. A medical image analysis system of classifying a medical image using a category model, the medical image analysis system comprising:

a repository which stores a category model mapping a plurality of visual-words in a space, each said visual-word being associated with at least one of a plurality of image categories;

an input unit which receives an examined medical image;

a categorization module which identifies a group of said plurality of visual-words in said examined medical image and uses said category model to match said group with an image category of said plurality of image categories; and

a presentation unit which present said image category in response to the receiving of said examined medical image.