Method and apparatus for performing registration of medical images

• US 10,362,941 B2
• Filed: 02/11/2014
• Issued: 07/30/2019
• Est. Priority Date: 02/21/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Jung-bae, Hwang, Young-kyoo, Kim, Do-kyoon, Bang, Won-chul, Oh, Young-taek
• Primary Examiner(s): Turchen, Rochelle D
• Application Number:
  US14/177,897
• Publication Number:
  US 20140235998A1
• Time in Patent Office: 1,995 Days
• CPC Class Codes: A61B 2090/364 Correlation of different images or relation of image positions in respect to the body
• CPC Class Codes: A61B 5/0035 adapted for acquisition of images from more than one imaging mode, e.g. combining MRI and optical tomography
• CPC Class Codes: A61B 5/113 occurring during breathing
• 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 8/5261 combining images from different diagnostic modalities, e.g. ultrasound and X-ray
• CPC Class Codes: G06T 2200/04 involving 3D image data
• 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 2207/30056 Liver; Hepatic
• CPC Class Codes: G06T 7/33 using feature-based methods

Abstract

A method and apparatus for performing registration of medical images includes mapping a virtual coordinate system used by a first medical apparatus and a virtual coordinate system used by a second medical apparatus to one another. The coordinate systems are associated with a real-time medical image captured by the first medical apparatus and a three-dimensional (3D) medical image previously captured by the second medical apparatus, respectively. The method further includes detecting a position of a probe of the first medical apparatus from a coordinate system used by the second medical apparatus, based on a result of the mapping, determining a volume image corresponding to the detected position of the probe from the previously captured 3D medical image, and extracting from the determined volume image a cross-sectional image corresponding to the real-time medical image, where the real-time medical image changes according to a patient'"'"'s physical movement.

Claims

1. A method of performing registration of medical images, comprising:

mapping, by a processor, a virtual coordinate system used by a first medical apparatus and a virtual coordinate system used by a second medical apparatus to each other, wherein a real-time medical image is captured in a first position of a patient by the first medical apparatus and a three-dimensional (3D) medical image is previously captured in a second position of the patient by the second medical apparatus;

detecting, by the processor, a position of a probe of the first medical apparatus in the virtual coordinate system used by the second medical apparatus, based on a result of the mapping;

determining, by the processor, a volume image, corresponding to the detected position of the probe, from the previously captured 3D medical image;

selecting a reference cross-section from the determined volume image using the detected position of the probe;

estimating a relative movement range of a scanning plane of the probe from the reference cross-section according to a patient'"'"'s physical movement with the probe being static relative to the virtual coordinate system used by the second medical apparatus and by using previously stored information about a range in which an organ can be moved by the patient'"'"'s physical movement;

selecting neighboring cross-sections that exist in the estimated relative movement range of the scanning plane;

reconstructing a volume image by accumulating the reference cross-section and the neighboring cross-sections; and

extracting, by the processor, from the reconstructed volume image a cross-sectional image corresponding to the real-time medical image, wherein the cross-sectional image changes according to the patient'"'"'s physical movement, and

wherein the determined volume image comprises a volume image smaller than the previously captured 3D medical image and has a dimension determined by the estimated relative movement range of the scanning plane of the probe from the reference cross-section.

2. The method of claim 1, wherein, in the extracting of the cross-sectional image, the cross-sectional image is updated when the scanning plane of the probe is moved relative to the patient'"'"'s body according to the patient'"'"'s physical movement.

3. The method of claim 1, wherein the mapping of the virtual coordinate systems comprises:

generating a first cross-sectional image of the real-time medical image;

selecting a two-dimensional (2D) medical image corresponding to the first cross-sectional image among a plurality of 2D medical images forming the 3D medical image based on an anatomical feature appearing in the first cross-sectional image; and

generating a coordinate conversion function to convert the coordinate system used by the first medical apparatus to the coordinate system used by the second medical apparatus based on the selected 2D medical image and the first cross-sectional image.

4. The method of claim 1, wherein the detecting of the position of the probe comprises:

receiving a coordinate value of the probe that is moved in the coordinate system used by the first medical apparatus, when the probe is moved; and

converting the coordinate value of the probe that is moved to a coordinate value of the coordinate system used by the second medical apparatus, by using the mapping result.

5. The method of claim 1, wherein the extracting of the cross-sectional image comprises:

acquiring a real-time medical image that changes in a state when the probe remains still; and

extracting the cross-sectional image considering an anatomical feature appearing on the acquired real-time medical image.

12. The method of claim 1, wherein the extracting of the cross-sectional image comprises extracting the cross-sectional image based on a similarity between anatomical features appearing on the real-time medical image and the determined volume image.

13. The method of claim 1, wherein the extracting of the cross-sectional image comprises:

performing segmentation on each of anatomical objects appearing on the real-time medical image and the cross-sectional images of the determined volume image; and

extracting from the determined volume image a selected cross-sectional image of the cross-sectional images having a largest similarity between the anatomical objects segmented in the real-time medical image and anatomical objects in the selected cross-sectional image of the determined volume image.

6. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform a method of registration of medical images, the method comprising:

mapping a virtual coordinate system used by a first medical apparatus and a virtual coordinate system used by a second medical apparatus to each other, wherein a real-time medical image is captured in a first position of a patient by the first medical apparatus and a three-dimensional (3D) medical image is previously captured in a second position of the patient by the second medical apparatus;

detecting a position of a probe of the first medical apparatus in the virtual coordinate system used by the second medical apparatus, based on a result of the mapping;

determining a volume image, corresponding to the detected position of the probe, from the previously captured 3D medical image;

selecting a reference cross-section from the determined volume image using the detected position of the probe;

estimating a relative movement range of a scanning plane of the probe from the reference cross-section according to a patient'"'"'s physical movement with the probe being static relative to the virtual coordinate system used by the second medical apparatus and by using previously stored information about a range in which an organ can be moved by the patient'"'"'s physical movement;

selecting neighboring cross-sections that exist in the estimated relative movement range of the scanning plane;

reconstructing a volume image by accumulating the reference cross-section and the neighboring cross-sections; and

extracting, by the processor, from the reconstructed volume image a cross-sectional image corresponding to the real-time medical image, wherein the cross-sectional image changes according to the patient'"'"'s physical movement, and

wherein the determined volume image comprises a volume image smaller than the previously captured 3D-medical image and has a dimension determined by the estimated relative movement range of the scanning plane of the probe from the reference cross-section.

7. An apparatus for performing registration of medical images comprising:

a processor configured to;

map a virtual coordinate system used by a first medical apparatus and a virtual coordinate system by a second medical apparatus to each other, and detect a position of a probe of the first medical apparatus in the virtual coordinate system used by the second medical apparatus based on a result of the mapping;

determine a volume image corresponding to the detected position from a previously captured 3D medical image;

select a reference cross-section from the determined volume image using the detected position of the probe;

estimate a relative movement range of a scanning plane of the probe from the reference cross-section according to a patient'"'"'s physical movement with the probe being static relative to the virtual coordinate system used by the second medical apparatus and by using previously stored information about a range in which an organ can be moved by the patient'"'"'s physical movement;

select neighboring cross-sections that exist in the estimated relative movement range of the scanning plane;

reconstruct a volume image by accumulating the reference cross-section and the neighboring cross-sections; and

extract from the reconstructed volume image a cross-sectional image corresponding to a real-time medical image, wherein the cross-sectional image changes according to the patient'"'"'s physical movement, and

wherein the determined volume image comprises a volume image smaller than the previously captured 3D medical image and has a dimension determined by the estimated relative movement range of the scanning plane of the probe from the reference cross-section.

8. The apparatus of claim 7, wherein the cross-sectional image is updated when the scanning plane of the probe is moved relative to a patient'"'"'s body according to the patient'"'"'s physical movement.

9. The apparatus of claim 7, wherein the processor is further configured to generate a first cross-sectional image of the real-time medical image, select a 2D medical image corresponding to the first cross-sectional image among a plurality of 2D medical images forming the 3D medical image based on an anatomical feature appearing in the first cross-sectional image, and generate a coordinate conversion function to convert a coordinate system used by the first medical apparatus to the coordinate system used by the second medical apparatus based on a selected 2D medical image and the first cross-sectional image.

10. The apparatus of claim 7, wherein, when the probe is moved, the processor receives a coordinate value of the probe that is moved in the coordinate system used by the first medical apparatus, and converts the coordinate value of the probe that is moved to a coordinate value of the coordinate system used by the second medical apparatus, by using the mapping result.

11. The apparatus of claim 7, wherein the processor is further configured to acquire the real-time medical image captured by the first medical apparatus.

14. The apparatus of claim 7, wherein the processor is further configured to extract the cross-sectional image based on a similarity between anatomical features appearing on the real-time medical image and the determined volume image.

15. The apparatus of claim 7, wherein the processor is further configured to perform segmentation on each of anatomical objects appearing on the real-time medical image and the volume image, and extract from the volume image a cross-section having a largest similarity between the anatomical objects segmented in the real-time medical image and the volume image.