Multiple algorithm lesion segmentation

• US 10,176,569 B2
• Filed: 09/07/2016
• Issued: 01/08/2019
• Est. Priority Date: 09/07/2016
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Bronkalla, Mark, Park, Sun Young, Sargent, Dustin
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): Torres, Jose M
• Application Number:
  US15/258,832
• Publication Number:
  US 20180068436A1
• Time in Patent Office: 853 Days
• Field of Search: None
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/5264 due to motion
• CPC Class Codes: A61B 6/566 involving communication between diagnostic systems
• CPC Class Codes: A61B 8/5276 due to motion
• CPC Class Codes: A61B 8/565 involving data transmission via a network
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/20112 Image segmentation details
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

Multiple algorithm lesion segmentation using an atlas is provided. In various embodiments, a plurality of medical images are read from an image repository. Each of the plurality of medical images has a source modality. Each of the plurality of medical images is registered to an anatomical atlas. An anatomical region depicted in each of the plurality of medical images is determined thereby. Based upon the source modality and the anatomical region depicted in each of the plurality of medical images, one of a plurality of segmentation algorithms is selected for each of the plurality of medical images. The selected segmentation algorithms are applied to each of the plurality of medical images. The results of the selected segmentation algorithms are displayed.

Claims

1. A method comprising:

reading a plurality of medical images from an image repository, a first of the plurality of medical images corresponding to a first body part and having a first source modality, and a second of the plurality of medical images corresponding to a second body part and having a second source modality different from the first source modality, the plurality of medical images being from sequential studies;

registering each of the plurality of medical images to an anatomical atlas, thereby determining an anatomical region depicted in each of the plurality of medical images;

based upon the first source modality and the anatomical region depicted in the first of the plurality of medical images, selecting a first segmentation algorithm for the first of the plurality of medical images;

based upon the second source modality and the anatomical region depicted in the second of the plurality of medical images, selecting a second segmentation algorithm for the second of the plurality of medical images, the second segmentation algorithm different from the first segmentation algorithm;

applying the first segmentation algorithm to the first of the plurality of medical images and the second segmentation algorithm to the second of the plurality of medical images, to annotate a lesion within the first and second of the plurality of medical images;

displaying the results of the first and second segmentation algorithms, thereby providing aggregate results of the sequential studies.

2. The method of claim 1, wherein displaying the results of the first and second segmentation algorithms comprises displaying a time series of the plurality of medical images with the results of the first and second segmentation algorithms displayed thereon.

3. The method of claim 1, wherein the first and second segmentation algorithms are modular.

4. The method of claim 1, further comprising preprocessing the image prior to applying the first segmentation algorithm.

5. The method of claim 4, wherein preprocessing the image comprises dynamic contrast enhancement, diffusion weighted imaging, or contrast subtraction.

6. The method of claim 4, wherein preprocessing the image comprises registration to correct for motion artifacts.

7. The method of claim 1, wherein the first and second segmentation algorithms each comprises 2D segmentation.

8. The method of claim 7, wherein 2D segmentation comprises thresholding and morphological filtering.

9. The method of claim 7, wherein 2D segmentation comprises applying a level set algorithm.

10. The method of claim 7, wherein 2D segmentation comprises single or dual snakes.

11. The method of claim 7, wherein 2D segmentation comprises application of a support vector machine.

12. The method of claim 1, wherein the first and second segmentation algorithms each comprises building a 3D volume from 2D segmentation by propagation.

13. The method of claim 12, wherein the propagation is tunable by propagation and termination parameters.

14. The method of claim 13, wherein the parameters comprise threshold, texture, cost function, or propagation energy analysis parameters.

15. The method of claim 1, wherein the first and second segmentation algorithms each comprises volumetric segmentation.

16. The method of claim 15, wherein volumetric segmentation comprises fuzzy connectedness, watershed, or surface extraction by dynamic programming.

17. The method of claim 1, wherein selecting the first segmentation algorithm and selecting the second segmentation algorithm are based on an anatomy of interest, a modality, or an acquisition parameter.

18. The method of claim 1, wherein applying the first segmentation algorithm comprises applying tuning parameters based on the anatomical region depicted in the first of the plurality of medical images, an acquisition modality, or an acquisition protocol;

and

wherein applying the second segmentation algorithm comprises applying tuning parameters based on the anatomical region depicted in the second of the plurality of medical images, an acquisition modality, or an acquisition protocol.

19. A computer program product for lesion segmentation, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

reading a plurality of medical images from an image repository, a first of the plurality of medical images corresponding to a first body part and having a first source modality, and a second of the plurality of medical images corresponding to a second body part and having a second source modality different from the first source modality, the plurality of medical images being from sequential studies;

registering each of the plurality of medical images to an anatomical atlas, thereby determining an anatomical region depicted in each of the plurality of medical images;

based upon the first source modality and the anatomical region depicted in the first of the plurality of medical images, selecting a first segmentation algorithm for the first of the plurality of medical images;

based upon the second source modality and the anatomical region depicted in the second of the plurality of medical images, selecting a second segmentation algorithm for the second of the plurality of medical images, the second segmentation algorithm different from the first segmentation algorithm;

applying the first segmentation algorithm to the first of the plurality of medical images and the second segmentation algorithm to the second of the plurality of medical images, to annotate a lesion within the first and second of the plurality of medical images;

displaying the results of the first and second segmentation algorithms, thereby providing aggregate results of the sequential studies.

20. A system comprising:

an image repository;

an anatomical atlas;

a computing node having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising;

reading a plurality of medical images from the image repository, of the plurality of medical images corresponding to a first body part and having a first source modality, and a second of the plurality of medical images corresponding to a second body part and having a second source modality different from the first source modality, the plurality of medical images being from sequential studies;

registering each of the plurality of medical images to the anatomical atlas, thereby determining an anatomical region depicted in each of the plurality of medical images;

based upon the first source modality and the anatomical region depicted in the first of the plurality of medical images, selecting a first segmentation algorithm for the first of the plurality of medical images;

based upon the second source modality and the anatomical region depicted in the second of the plurality of medical images, selecting a second segmentation algorithm for the second of the plurality of medical images, the second segmentation algorithm different from the first segmentation algorithm;

applying the first segmentation algorithm to the first of the plurality of medical images and the second segmentation algorithm to the second of the plurality of medical images, to annotate a lesion within the first and second of the plurality of images;

displaying the results of the first and second segmentation algorithms on a display of the computing node, thereby providing aggregate results of the sequential studies.