Apparatus and method for analyzing medical image

• US 9,424,638 B2
• Filed: 10/10/2013
• Issued: 08/23/2016
• Est. Priority Date: 10/12/2012
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Jae-Cheol, Woo, Kyoung-Gu, Seong, Yeong-Kyeong
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): SHIN, SOO JUNG
• Application Number:
  US14/050,900
• Publication Number:
  US 20140105474A1
• Time in Patent Office: 1,048 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/10132 Ultrasound image
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/33 using feature-based methods

Abstract

An apparatus for analyzing a medical image includes an image receiving unit configured to receive two or more medical images from a medical device; a image registration unit configured to register the two or more received medical images; an overlapped area detecting unit configured to detect overlapped areas in the two or more registered medical images; and a lesion analyzing unit configured to analyze lesions in the two or more registered medical images by employing different analysis techniques in the detected overlapped areas.

Claims

1. An apparatus for analyzing a medical image, the apparatus comprising:

a processor configured to;

register two or more medical images received from a medical device, the two or more medical images comprising a first image and a second image;

detect, based on overlap information, overlapped areas in the first image and the second image;

analyze lesions in the first image using a first analysis technique;

analyze, using the first analysis technique, lesions in the second image excluding the overlapped areas;

select, using the overlap information, a different analysis technique; and

analyze lesions in the overlapped areas in the second image using the selected different analysis technique.

2. The apparatus of claim 1, further comprising a result display configured to display the registered medical images and analysis results obtained by the processor on a screen.

3. The apparatus of claim 1, further comprising an image receiver configured to sequentially receive the two or more medical images from the medical device.

4. The apparatus of claim 1, wherein the overlap information comprises coordinate information received from the medical device and corresponding to the first image and to the second image.

5. The apparatus of claim 1, wherein the overlap information comprises information about a measurement range of the first image and the second image measured by the medical device, and information about a distance that the medical device has moved between a first time of capture of the first image and a second time of capture of the second image.

6. The apparatus of claim 1, wherein the overlap information comprises structural feature information of the first image and the second image, and

wherein the processor is further configured to measure a similarity level between the first image and the second image based on the structural feature, and to detect the overlapped areas based on the measured similarity level.

7. The apparatus of claim 6, wherein the processor is further configured to generate one or more cluster objects by clustering objects included in the first image and the second image, and extract the structural feature information from the generated one or more cluster objects.

8. The apparatus of claim 7, wherein the structural feature information is distribution information of the cluster objects, or graphs in which objects in the cluster objects are connected to one another.

9. The apparatus of claim 6, wherein the different analysis technique comprises analyzing the first image and the second image except for detected overlapped areas included in the second image when a similarity level of the detected overlapped areas is greater than a predetermined reference level.

10. The apparatus of claim 6, wherein the measured similarity level is further used to select the different analysis technique, or to select the different analysis technique to be the first analysis technique performed for a different number of features within the overlapped areas.

11. The apparatus of claim 1, wherein the different analysis technique comprises analyzing the first image and the second image except for detected overlapped areas included in the second image.

12. The apparatus of claim 1, wherein the different analysis technique comprises analyzing the detected overlapped areas included in the second image using the first analysis technique for a different number of features.

13. A method of analyzing a medical image, the method comprising:

receiving two or more medical images from a medical device, the two or more medical images comprising a first image and a second image;

registering the two or more received medical images;

detecting, based on overlap information, overlapped areas in the first image and the second image;

analyzing lesions in the first image using a first analysis technique;

analyzing, using the first analysis technique, lesions in the second image excluding the overlapped areas;

selecting, using the overlap information, a different analysis technique; and

analyzing lesions in the overlapped areas in the second image using the selected different analysis technique.

14. The method of claim 13, further comprising displaying the registered medical images and analysis results obtained by the analyzing of the lesions on a screen.

15. The method of claim 13, wherein the receiving of the two or more medical images comprises sequentially receiving the two or more medical images from the medical device.

16. The method of claim 13, wherein the overlap information comprises coordinate information received from the medical device and corresponding to the first image and to the second image.

17. The method of claim 13, wherein the overlap information comprises information about a measurement range of the first image and the second image measured by the medical device, and information about a distance that the medical device has moved during a time between a first time of capture of the first image and a second time of capture of the second image.

18. The method of claim 13, wherein the overlap information comprises structural feature information of the first image and the second image, and

wherein detecting of the overlapped areas comprises:

measuring a similarity level between the first image and the second image based on the structural feature information; and

detecting the overlapped areas based on the measured similarity level.

19. The method of claim 18, wherein the detecting of the overlapped areas further comprises:

generating one or more cluster objects by clustering objects included in the first image and the second image; and

extracting the structural feature information from the generated one or more cluster objects.

20. The method of claim 19, wherein the structural feature information comprises distribution information of the cluster objects, or graphs in which objects in the cluster objects are connected to one another.

21. The method of claim 18, wherein the different analysis technique comprises analyzing the first image and the second image except for the detected overlapped areas included in the second image when a similarity level of the detected overlapped areas is greater than a predetermined reference level.

22. The method of claim 18, wherein the measured similarity level is further used to select the different analysis technique, or the select the different analysis technique to be the first analysis technique performed for a different number of features within the overlapped areas.

23. The method of claim 13, wherein the different analysis technique comprises analyzing the first image and the second image except for the detected overlapped areas included in the second image.

24. The method of claim 13, wherein the different analysis technique comprises analyzing the detected overlapped areas included in the second image using the first analysis technique for a different number of features.

25. A method of analyzing a medical image, the method comprising:

receiving a first medical image and a second medical image that partially overlaps the first medical image from a medical device;

analyzing the first medical image for lesions by employing a first analysis technique; and

analyzing a portion of the second medical image that overlaps the first medical image for lesions by employing a second analysis technique different from the first analysis technique,

wherein the second analysis technique is selected based on overlap information used to detect the portion of the second medical image that overlaps the first medical image.

26. The method of claim 25, further comprising analyzing a remaining portion of the second medical image excluding the portion of the second medical image that overlaps the first medical image for lesions using the first analysis technique.

27. The method of claim 25, wherein the overlap information comprises a level of similarity between a portion of the first medical image that is overlapped by the second medical image and the portion of the second medical image that overlaps the first medical image, and

where the second analysis technique is selected from among a plurality of different analysis techniques based on the level of similarity.