Computer aided disease detection system for multiple organ systems

• US 7,672,497 B2
• Filed: 10/31/2006
• Issued: 03/02/2010
• Est. Priority Date: 12/29/2005
• Status: Active Grant

• Current Assignee: Philips Healthcare Informatics Incorporated (Koninklijke Philips N.V.)
• Original Assignee: CareStream Health Incorporated
• Inventors: Nicponski, Henry
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US11/554,647
• Publication Number:
  US 20070165924A1
• Time in Patent Office: 1,218 Days
• Field of Search: 382/100, 382/128, 382/129, 382/130, 382/131, 382/132, 382/133, 382/134, 382/154, 382/168, 382/170, 382/173, 382/181, 382/193, 382/194, 382/199, 382/203, 382/232, 382/254, 382/274, 382/276, 382286-295, 382/305, 382/312, 707/10, 600/300, 600/408, 378/4
• US Class Current: 382/128
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

A computer aided disease detection system and method for multiple organ systems. The method performs computer aided examination of digital medical images. A patient exam type of a digital medical image is determined. Based on the patient exam type, one or more of a plurality of knowledge based anatomical segmentation blocks are invoked, each block performing image segmentation for a single organ or organ system present in the image. Based on the patient exam type, for each successfully segmented organ or organ system, one or more of a plurality of knowledge based computer aided detection blocks are invoked, each block of which is designed to search for and locate potential disease foci in a particular organ or organ system.

Claims

1. A method of performing computer aided examination of digital medical images, comprising:

determining a patient exam type of a digital medical image;

based on the patient exam type, invoking one or more of a plurality of knowledge based anatomical segmentation blocks, each block performing image segmentation for a single organ or organ system present in the image; and

based on the patient exam type, for each successfully segmented organ or organ system, invoking one or more of a plurality of knowledge based computer aided detection blocks, each block of which is designed to search for and locate potential disease loci in a particular organ or organ systems,

wherein the results from the previous blocks are reported to results reporting blocks suitable for each of the specific organ or organ system in view, for interpretation of the results.

2. The method as claimed in claim 1, further comprising the step of:

invoking, based on the patient exam type, one or more of a plurality of computer aided disease diagnosis blocks, each block of which is designed to evaluate potential disease foci in a particular organ or organ system, to assess the likelihood of the organ containing actual disease processes.

3. The method as claimed in claim 1, wherein the determination of the patient exam type is performed by an automated classification means.

4. The method as claimed in claim 1, wherein the determination of the patient exam type is a result of a user input.

5. The method as claimed in claim 1, wherein the determination of the patient exam type is a result of information contained in the digital image header.

6. The method as claimed in claim 1, wherein the images are pre-processed prior to being classified as to exam type.

7. The method as claimed in claim 1, wherein segmentation includes the creation of digital geometric models of the surfaces or volumes of the organ or organ systems.

8. The method as claimed in claim 1, wherein the detection blocks identify spatial locations and/or detection scores of regions of the image deemed likely to contain a disease process.

9. The method as claimed in claim 8, wherein the detection blocks identify volumetric centers around which fixed length vectors cluster.

10. The method as claimed in claim 9, wherein the diagnosis blocks provide an estimated size of detected abnormalities.

11. The method as claimed in claim 10, wherein each diagnosis block is designed to evaluate and display the type and severity of disease processes detected to be present.

12. The method as claimed in claim 11, wherein a confidence score is provided for each case of diagnosis.

13. The method as claimed in claim 12, wherein the results reporting blocks report the results by two dimensional and three dimensional displays simultaneously.

14. The method as claimed in claim 13, wherein the results are presented together with the original digital medical images.

15. A system for performing computer aided examination of digital medical images, comprising:

means for the determination of a patient exam type of a digital medical image;

an exam control module;

a plurality of knowledge based anatomical segmentation blocks, each performing image segmentation of a single organ or organ system known to be present in the digital image;

a plurality of knowledge based computer aided detection blocks, each with specific anatomical knowledge tailored to a target organ/organ system;

and a plurality of reporting and display blocks providing display of the results from the previous blocks to allow interpretation of the results, each tailored to visualization techniques best representing information concerning each specific anatomical target.

16. The system as claimed in claim 15, further including:

a plurality of computer aided disease diagnosis blocks each with specific anatomical knowledge tailored to a target organ/organ system.

17. The system as claimed in claim 16, further including automated classification means for the determination of the patient exam type.

18. The system as claimed in claim 17, further including means for pre-processing the images prior to being classified as to exam type.