WO2020240995A1 - マッチング装置、方法およびプログラム - Google Patents

マッチング装置、方法およびプログラム Download PDF

Info

Publication number
WO2020240995A1
WO2020240995A1 PCT/JP2020/011576 JP2020011576W WO2020240995A1 WO 2020240995 A1 WO2020240995 A1 WO 2020240995A1 JP 2020011576 W JP2020011576 W JP 2020011576W WO 2020240995 A1 WO2020240995 A1 WO 2020240995A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
position information
abnormal
matching
unit
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/011576
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
テックチュアン ベー
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujifilm Corp
Original Assignee
Fujifilm Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujifilm Corp filed Critical Fujifilm Corp
Priority to JP2021522650A priority Critical patent/JP7098835B2/ja
Publication of WO2020240995A1 publication Critical patent/WO2020240995A1/ja
Priority to US17/505,632 priority patent/US12033366B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
    • A61B6/03—Computed tomography [CT]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01T—MEASUREMENT OF NUCLEAR OR X-RADIATION
    • G01T1/00—Measuring X-radiation, gamma radiation, corpuscular radiation, or cosmic radiation
    • G01T1/16—Measuring radiation intensity
    • G01T1/161—Applications in the field of nuclear medicine, e.g. in vivo counting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10104—Positron emission tomography [PET]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G06T2207/30012—Spine; Backbone
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion

Definitions

  • the present disclosure relates to a matching device, method and program for matching abnormal parts included in images acquired at different shooting times for the same subject between images.
  • CT Computer Tomography
  • MRI Magnetic Resonance Imaging
  • an image is analyzed by CAD (Computer-Aided Diagnosis) to extract an abnormal site such as a tumor, and the size and type of the abnormal site are acquired as an analysis result.
  • CAD Computer-Aided Diagnosis
  • time-lapse comparative observation is performed using past medical images of the same patient. For example, when observing a liver tumor, a work is performed in which three-dimensional images of the abdomen taken at different times are displayed side by side, and the two displayed three-dimensional images are viewed to confirm changes in the tumor over time. ..
  • the alignment method a method such as rigid body alignment or non-rigid body alignment is used.
  • a method for aligning images for example, the method described in Patent Document 1 has also been proposed. In the method described in Patent Document 1, a plurality of sets of feature points associated with each other are selected from a plurality of feature points extracted in each of the two three-dimensional images, and a plurality of selected feature points are selected. It is a method of specifying the corresponding cross section in two three-dimensional images by using the position information of each set of.
  • the present disclosure is made in view of the above circumstances, and an object of the present disclosure is to enable accurate matching of abnormal parts included in images between images taken at different shooting times with a small amount of calculation.
  • the matching device includes a reference site extraction unit that extracts at least one reference site that is common to each other from each of the first image and the second image that have different shooting times for the same subject.
  • a first position information deriving unit that derives first position information representing the relative position of at least one abnormal part specified in the first image with respect to at least one reference part in the first image.
  • a second position information deriving unit that derives second position information representing the relative position of at least one abnormal part identified in the second image with respect to at least one reference part in the second image. Based on the difference between the first position information and the second position information, a matching unit for associating an abnormal portion included in each of the first image and the second image is provided.
  • the "reference part” means a part whose position, size, shape, etc. do not change with time.
  • the reference site for example, bone can be used.
  • the first position information deriving unit derives a vector from the reference site to the abnormal site as the first position information.
  • the second position information deriving unit may derive a vector from the reference portion to the abnormal portion as the second position information.
  • the matching unit includes an abnormal portion included in the first image and an abnormal portion included in the second image based on the first position information and the second position information.
  • the distance may be derived as a difference.
  • the matching unit may associate abnormal parts whose distance difference is less than a predetermined threshold value.
  • the reference site extraction unit may extract a plurality of reference sites.
  • the reference site may be a bone, and in particular, a vertebra.
  • the matching device may further include an abnormal part extraction unit that extracts at least one abnormal part from each of the first image and the second image.
  • the reference portion included in the first image and the reference portion included in the second image when the sizes of the reference portion included in the first image and the reference portion included in the second image are different, the reference portion included in the first image and the second image A resizing portion that matches the size with the reference portion included in the above may be further provided.
  • the matching device may further include a display control unit that emphasizes the associated abnormal portion and displays the first image and the second image on the display unit.
  • At least one reference portion common to each other is extracted from each of the first image and the second image of the same subject at different shooting times.
  • First position information representing the relative position of at least one abnormal part identified in the first image with respect to at least one reference part in the first image is derived.
  • second position information representing the relative position of at least one abnormal site identified in the second image with respect to at least one reference site in the second image is derived. Based on the difference between the first position information and the second position information, the abnormal parts contained in each of the first image and the second image are associated with each other.
  • the matching method according to the present disclosure may be provided as a program for executing the matching method on a computer.
  • Other matching devices include a memory for storing instructions to be executed by a computer and a memory.
  • the processor comprises a processor configured to execute a stored instruction.
  • At least one reference site common to each other is extracted from each of the first image and the second image of the same subject at different shooting times.
  • First position information representing the relative position of at least one abnormal part identified in the first image with respect to at least one reference part in the first image is derived.
  • second position information representing the relative position of at least one abnormal site identified in the second image with respect to at least one reference site in the second image. Based on the difference between the first position information and the second position information, a process of associating the abnormal portion included in each of the first image and the second image is executed.
  • the figure for demonstrating the derivation of the 1st and 2nd position information The figure for demonstrating the derivation of the distance between the abnormal part included in the 1st 3D image and the abnormal part included in a 2nd 3D image.
  • FIG. 1 is a hardware configuration diagram showing an outline of a diagnostic support system to which the matching device according to the embodiment of the present disclosure is applied.
  • the matching device 1 the three-dimensional image capturing device 2, and the image storage server 3 according to the present embodiment are connected in a communicable state via the network 4.
  • the three-dimensional image capturing apparatus 2 is an apparatus that generates a three-dimensional image representing the portion by photographing a portion to be diagnosed of the subject, and specifically, a CT apparatus, an MRI apparatus, and a PET (PET). Positron Emission Tomography) Equipment, etc.
  • the three-dimensional image generated by the three-dimensional image capturing device 2 is transmitted to the image storage server 3 and stored.
  • the diagnosis target site of the subject is the liver
  • the three-dimensional image capturing device 2 is a CT device
  • the three-dimensional image is a CT image of the abdomen of the subject.
  • the image storage server 3 is a computer that stores and manages various data, and is equipped with a large-capacity external storage device and database management software.
  • the image storage server 3 communicates with other devices via a wired or wireless network 4 to send and receive image data and the like.
  • image data such as a three-dimensional image generated by the three-dimensional image capturing device 2 is acquired via a network and stored in a recording medium such as a large-capacity external storage device for management.
  • the storage format of the image data and the communication between the devices via the network 4 are based on a protocol such as DICOM (Digital Imaging and Communication in Medicine).
  • DICOM Digital Imaging and Communication in Medicine
  • a tag based on the DICOM standard is attached to the three-dimensional image.
  • the tag includes information such as a patient name, information representing an imaging device, an imaging date and time, and an imaging site.
  • the matching device 1 is configured by installing the matching program of the present disclosure on one computer.
  • the computer may be a workstation or personal computer directly operated by the diagnosing doctor, or a server computer connected to them via a network.
  • the matching program is stored in the storage device of a server computer connected to the network or in the network storage in a state of being accessible from the outside, and is downloaded and installed on the computer used by the doctor upon request. Alternatively, it is recorded and distributed on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory), and is installed on a computer from the recording medium.
  • a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory)
  • FIG. 2 is a diagram showing a schematic configuration of a matching device realized by installing a matching program on a computer.
  • the matching device 1 includes a CPU 11, a memory 12, and a storage 13 as a standard workstation configuration. Further, the matching device 1 is connected to a display unit 14 such as a liquid crystal display and an input unit 15 such as a mouse and a keyboard. A touch panel that also serves as the display unit 14 and the input unit 15 may be used.
  • the storage 13 stores various information including a three-dimensional image acquired from the image storage server 3 via the network 4 and an image generated by processing by the matching device 1.
  • the matching program is stored in the memory 12.
  • the matching program is an image acquisition process for acquiring a first three-dimensional image S1 and a second three-dimensional image S2 at different shooting times for the same subject, a first three-dimensional image S1 and a first process to be executed by the CPU 11.
  • An abnormal part extraction process for extracting at least one abnormal part from each of the two three-dimensional images S2, and at least one reference part common to each other from each of the first three-dimensional image S1 and the second three-dimensional image S2.
  • the matching process for associating the abnormal parts included in the above and the display control process for displaying the first three-dimensional image S1 and the second three-dimensional image S2 on the display unit 14 by emphasizing the associated abnormal parts are defined. To do.
  • the first three-dimensional image S1 is an example of the first image
  • the second three-dimensional image S2 is an example of the second image.
  • the computer performs the image acquisition unit 21, the abnormal part extraction unit 22, the reference part extraction unit 23, the first position information derivation unit 24, and the second position information derivation. It functions as a unit 25, a matching unit 26, and a display control unit 27.
  • the image acquisition unit 21 obtains the first three-dimensional image S1 and the second three-dimensional image S2 of the same subject at different shooting times from the image storage server 3 via an interface (not shown) connected to the network. get.
  • the first three-dimensional image S1 is a three-dimensional image acquired by the latest inspection
  • the second three-dimensional image S2 is a three-dimensional image acquired by the previous inspection. , Not limited to this.
  • the image acquisition unit 21 acquires the first and second three-dimensional images S1 and S2 from the storage 13 when the first and second three-dimensional images S1 and S2 are already stored in the storage 13. You may try to do it.
  • the abnormal part extraction unit 22 extracts at least one abnormal part from each of the first three-dimensional image S1 and the second three-dimensional image S2.
  • the diagnosis target site is the liver. Therefore, the abnormal site extraction unit 22 first extracts the liver region from each of the first and second three-dimensional images S1 and S2.
  • a method for extracting the liver region for example, there are a method using a histogram of pixel values of three-dimensional images described in Japanese Patent Application Laid-Open No. 2002-345807, and livers in the first and second three-dimensional images S1 and S2. Any method can be used, such as a method of estimating the range of CT values to be performed, performing threshold processing using the values, and applying a morphology filter to the region extracted by this.
  • the abnormal site extraction unit 22 may have a trained model in which machine learning is performed so as to extract the liver region, and the liver region may be extracted by the trained model. The method for extracting the liver region is not limited to these methods, and any method can be used.
  • the abnormal site extraction unit 22 extracts an abnormal site such as a tumor contained in the extracted liver region.
  • the abnormal site extraction unit 22 includes a learned model in which machine learning is performed so as to extract an abnormal site such as a mass contained in the liver.
  • the abnormal site extraction unit 22 extracts an abnormal site from the liver region using the trained model in which machine learning has been performed in this way.
  • FIG. 3 is a diagram showing first and second three-dimensional images in which abnormal parts are extracted. Note that FIG. 3 shows tomographic images of one corresponding tomographic surface in the first and second three-dimensional images S1 and S2 for ease of illustration and explanation. As shown in FIG.
  • the extraction of the abnormal part in the abnormal part extraction unit 22 is not limited to the configuration including the trained model.
  • the image of the abnormal part extraction unit 22 may be analyzed by CAD to extract the abnormal part.
  • the reference site extraction unit 23 extracts at least one reference site common to each other from each of the first and second three-dimensional images S1 and S2.
  • the reference portion is a portion whose position, size, shape, etc. do not change with time.
  • the first and second three-dimensional images S1 and S2 are CT images of the abdomen of the same subject. The abdomen contains the spine. Therefore, in the present embodiment, at least one vertebra of the spine is extracted as a reference site.
  • the CT value is different between the bone and the soft tissue such as an organ. Therefore, in the present embodiment, the bone region is extracted from each of the first and second three-dimensional images S1 and S2 by performing threshold processing on the CT value. Further, the vertebrae are extracted by performing template matching using, for example, a template having the shape of the vertebrae on the extracted bone region. Since the three-dimensional images S1 and S2 include a plurality of vertebrae, the reference site extraction unit 23 extracts all of the plurality of vertebrae. Alternatively, the vertebrae may be extracted by using a trained model that has been trained to extract the vertebrae.
  • the reference site extraction unit 23 extracts two vertebrae near the liver as reference sites among the plurality of vertebrae included in the first and second three-dimensional images S1 and S2.
  • FIG. 4 is a diagram for explaining the identification of the vertebra, which is a reference site. Note that FIG. 4 is a view of the first and second three-dimensional images S1 and S2 as viewed from the coronal direction. As shown in FIG. 4, a plurality of vertebrae are extracted from the first and second three-dimensional images S1 and S2, respectively.
  • the reference site extraction unit 23 derives the center of gravity positions LG1 and LG2 of the liver regions 33 and 34 extracted by the above-mentioned abnormal site extraction unit 22, and uses two vertebrae located close to the derived center of gravity positions LG1 and LG2 as reference sites. Extract as 31A, 31B, 32A and 32B.
  • the first position information deriving unit 24 represents the relative positions of the abnormal parts A11 and A12 specified in the first three-dimensional image S1 with respect to the reference parts 31A and 31B in the first three-dimensional image S1. Derivation of the position information of. For this purpose, the first position information deriving unit 24 derives the center of gravity positions BG11 and BG12 of the vertebrae, which are the reference sites 31A and 31B, as shown in FIG. Further, the center-of-gravity positions AG11 and AG12 of the abnormal parts A11 and A12 extracted in the first three-dimensional image S1 are also derived.
  • the first position information deriving unit 24 has a vector V11 from the center of gravity position BG11 toward the center of gravity position AG11 of the abnormal portion A11 and a vector V12 from the center of gravity position BG11 toward the center of gravity position AG12 of the abnormal portion A12.
  • the vector V13 from the center of gravity position BG12 toward the center of gravity position AG11 of the abnormal portion A11 and the vector V14 from the center of gravity position BG12 toward the center of gravity position AG12 of the abnormal portion A12 are derived as the first position information.
  • the second position information deriving unit 25 represents the relative positions of the abnormal parts A21 and A22 identified in the second three-dimensional image S2 with respect to the reference parts 32A and 32B in the second three-dimensional image S2. Derivation of the position information of. For this purpose, the second position information deriving unit 25 derives the center of gravity positions BG21 and BG22 of the vertebrae, which are the reference sites 32A and 32B, as shown in FIG. In addition, the center of gravity positions AG21 and AG22 of the abnormal parts A21 and A22 extracted in the second three-dimensional image S2 are also derived.
  • the second position information deriving unit 25 has a vector V21 from the center of gravity position BG21 toward the center of gravity position AG21 of the abnormal portion A21, and a vector V22 from the center of gravity position BG21 toward the center of gravity position AG22 of the abnormal portion A22.
  • the vector V23 from the center of gravity position BG22 toward the center of gravity position AG21 of the abnormal portion A21 and the vector V24 from the center of gravity position BG22 toward the center of gravity position AG22 of the abnormal portion A22 are derived as the second position information.
  • the matching unit 26 associates the abnormal parts included in the first three-dimensional image S1 and the second three-dimensional image S2 based on the difference between the first position information and the second position information. I do.
  • the matching unit 26 uses the first position information and the second position information to form an abnormal portion included in the first three-dimensional image S1 and an abnormal portion included in the second three-dimensional image S2.
  • the matching unit 26 sets the distance between the abnormal portion included in the first three-dimensional image S1 and the abnormal portion included in the second three-dimensional image S2 as the distance between the first position information and the second position information. Derived as a difference.
  • FIG. 7 is a diagram for explaining the derivation of the distance between the abnormal portion included in the first three-dimensional image S1 and the abnormal portion included in the second three-dimensional image S2.
  • the matching unit 26 refers to the abnormal portion A11 included in the first three-dimensional image S1 with respect to the center of gravity position AG11 of the abnormal portion A11 and the second three-dimensional image S2 based on the vector V11 and the vectors V21 and V22.
  • the distances L11 and L12 between the center of gravity positions AG21 and AG22 of the abnormal parts A21 and A22 included in the above are derived by the following equations (1) and (2).
  • the distances L13 and L14 between the center of gravity position AG11 of the abnormal portion A11 and the center of gravity positions AG21 and AG22 of the abnormal portions A21 and A22 included in the second three-dimensional image S2 are determined. , Derived by the following equations (3) and (4).
  • (x11, y11, z11) is the vector V11
  • (x21, y21, z21) is the vector V21
  • (x22, y22, z22) is the vector V22
  • (x13, y13, z13) is the vector V13
  • (x23, y23, z23) is the vector V23
  • (x24, y24, z24) is the vector V24.
  • L11 ⁇ ⁇ (x11-x21) 2 + (y11-y21) 2 + (z11-z21) 2 ⁇ (1)
  • L12 ⁇ ⁇ (x11-x22) 2 + (y11-y22) 2 + (z11-z22) 2 ⁇ (2)
  • L13 ⁇ ⁇ (x13-x23) 2 + (y13-y23) 2 + (z13-z23) 2 ⁇ (3)
  • L14 ⁇ ⁇ (x13-x24) 2 + (y13-y24) 2 + (z13-z24) 2 ⁇ (4)
  • the matching unit 26 compares the distances L11, L12, L13 and L14 with the predetermined threshold Th1.
  • the threshold value Th1 may be, for example, a value of about 10 pixels in the three-dimensional images S1 and S2, but is not limited thereto.
  • a value such as mm may be used instead of the pixel.
  • the matching unit 26 associates the abnormal portion A11 included in the first three-dimensional image S1 with the abnormal portion A21 included in the second three-dimensional image S2.
  • the abnormal parts having the closest distance may be associated with each other.
  • the center of gravity position AG12 of the abnormal portion A12 and the second three-dimensional image S2 are based on the vector V12 and the vectors V21 and V22.
  • the distances L21 and L22 between the center of gravity positions AG21 and AG22 of the abnormal parts A21 and A22 included in the above are derived by the following equations (5) and (6).
  • the distances L23 and L24 between the center of gravity positions AG12 of the abnormal portion A12 and the center of gravity positions AG21 and AG22 of the abnormal portions A21 and A22 included in the second three-dimensional image S2 are determined. , Derived by the following equations (7) and (8).
  • L21 ⁇ ⁇ (x12-x21) 2 + (y12-y21) 2 + (z12-z21) 2 ⁇ (5)
  • L22 ⁇ ⁇ (x12-x22) 2 + (y12-y22) 2 + (z12-z22) 2 ⁇ (6)
  • L23 ⁇ ⁇ (x14-x23) 2 + (y14-y23) 2 + (z14-z23) 2 ⁇ (7)
  • L24 ⁇ ⁇ (x14-x24) 2 + (y14-y24) 2 + (z14-z24) 2 ⁇ (8)
  • the matching unit 26 compares the distances L21, L22, L23, and L24 with the predetermined threshold value Th1. Then, the abnormal parts whose distances are less than the threshold value Th1 are associated with each other. For the abnormal portion A12, the distances L22 and L24 are less than the threshold Th1. Therefore, the matching unit 26 associates the abnormal portion A12 included in the first three-dimensional image S1 with the abnormal portion A22 included in the second three-dimensional image S2.
  • the display control unit 27 emphasizes the associated abnormal portion and displays the first three-dimensional image S1 and the second three-dimensional image S2 on the display unit 14.
  • FIG. 8 is a diagram showing a display screen of the first three-dimensional image S1 and the second three-dimensional image S2 displayed on the display unit 14. As shown in FIG. 8, the display screen 40 displays tomographic images of the corresponding tomographic planes of the first three-dimensional image S1 and the second three-dimensional image S2. Further, in FIG. 8, it is found in the abnormal parts A11 and A21 that the abnormal part A11 included in the first three-dimensional image S1 and the abnormal part A21 included in the second three-dimensional image S2 are associated with each other. It is emphasized by adding a solid line frame 41.
  • abnormal part A12 included in the first three-dimensional image S1 and the abnormal part A22 included in the second three-dimensional image S2 are associated with each other means that the abnormal parts A12 and A12 are marked with a broken line frame 42. It is emphasized by giving.
  • FIG. 9 is a flowchart showing the processing performed in the present embodiment.
  • the image acquisition unit 21 acquires the first and second three-dimensional images S1 and S2 to be diagnosed from the image storage server 3 (step ST1).
  • the abnormal site extraction unit 22 extracts at least one abnormal site from each of the first three-dimensional image S1 and the second three-dimensional image S2 (step ST2).
  • the reference site extraction unit 23 extracts at least one reference site common to each other from each of the first three-dimensional image S1 and the second three-dimensional image S2 (step ST3).
  • the process of step ST3 may be performed before the process of step ST2, or the process of step ST2 and the process of step ST3 may be performed in parallel.
  • the first position information deriving unit 24 represents the relative position of at least one abnormal part specified in the first three-dimensional image S1 with respect to at least one reference part in the first three-dimensional image S1.
  • the first position information is derived (step ST4).
  • the second position information representing the relative position of the at least one abnormal part specified in the second three-dimensional image S2 with respect to at least one reference part in the second three-dimensional image S2 is derived (step). ST5).
  • the matching unit 26 associates the abnormal parts included in each of the first three-dimensional image S1 and the second three-dimensional image S2 based on the difference between the first position information and the second position information. (Matching process; step ST6).
  • the display control unit 27 emphasizes the associated abnormal portion, displays the first three-dimensional image S1 and the second three-dimensional image S2 on the display unit 14 (step ST7), and ends the process. ..
  • the abnormal portion included in each of the first three-dimensional image S1 and the second three-dimensional image S2 based on the difference between the first position information and the second position information. was made to correspond. Therefore, the amount of calculation for matching the abnormal parts can be reduced. Further, as in the case where the first 3D image S1 is acquired by the CT apparatus and the second 3D image S2 is acquired by the MRI apparatus, the first 3D image S1 and the second 3D image S2 However, even when the images are acquired by different imaging methods, the abnormal parts are associated with each other based on the difference between the first position information and the second position information, so that the abnormality is compared with the conventional method. The accuracy of matching does not decrease. Therefore, according to the present embodiment, it is possible to accurately match an abnormal portion included in an image between images at different shooting times with a small amount of calculation.
  • the size of the vertebrae included in the first three-dimensional image S1 and the second three-dimensional image S2, that is, the reference portion is different due to the difference in the imaging method or the imaging magnification.
  • the matching unit 26 cannot accurately derive the difference between the first position information and the second position information. Therefore, as shown in FIG. 10, a size changing unit 28 for matching the sizes of the reference portions included in the first three-dimensional image S1 and the second three-dimensional image S2 may be further provided.
  • the reference site extraction unit 23 compares the sizes of the vertebral bones extracted from the first three-dimensional image S1 and the second three-dimensional image S2, and if the sizes are different, extracts from the first three-dimensional image S1.
  • the size changing unit 28 may change the size of the first three-dimensional image S1 so that the size of the reference portion is matched with the size of the reference portion extracted from the second three-dimensional image S2.
  • the size of the second three-dimensional image S2 is changed so that the size of the reference portion extracted from the second three-dimensional image S2 matches the size of the reference portion extracted from the first three-dimensional image S1. You may.
  • the matching unit 26 by deriving the first position information and the second position information based on the first three-dimensional image S1 and the second three-dimensional image S2 after the size change, the matching unit 26 first It is possible to accurately derive the difference between the position information of the above and the second position information. Therefore, matching of abnormal parts included in the first three-dimensional image S1 and the second three-dimensional image S2 can be performed more accurately.
  • the abnormal site extraction unit 22 is provided, but the present invention is not limited to this.
  • An external device other than the matching device 1 according to the present embodiment may perform a process of extracting an abnormal portion.
  • the information representing the extracted abnormal portion is acquired by the image acquisition unit 21 together with the first and second three-dimensional images S1 and S2.
  • the diagnosis target site is the liver, but the diagnosis is not limited to this. It is possible to use parts other than the liver such as the heart, blood vessels, lungs and bronchi in the chest and abdomen of the human body as the diagnosis target parts.
  • the brain may be a diagnosis target site.
  • the three-dimensional image is an image of the head of the subject. In this case, the skull can be used as the reference site.
  • the vertebrae constituting the spine are extracted as a reference site, but the present invention is not limited to this.
  • a site whose position, size and shape do not change with time can be used as a reference site.
  • a plurality of reference sites are extracted, but the present invention is not limited to this. There may be only one reference site.
  • the abnormal part included in the first three-dimensional image S1 and the abnormal part included in the second three-dimensional image S2 The distance is derived as a difference, but it is not limited to this.
  • the absolute value of the difference between the first position information and the vector, which is the second position information, may be derived as a difference.
  • various processors include a CPU, which is a general-purpose processor that executes software (program) and functions as various processing units, and a circuit after manufacturing an FPGA (Field Programmable Gate Array) or the like.
  • Dedicated electricity which is a processor with a circuit configuration specially designed to execute specific processing such as programmable logic device (PLD), ASIC (Application Specific Integrated Circuit), which is a processor whose configuration can be changed. Circuits and the like are included.
  • One processing unit may be composed of one of these various processors, or a combination of two or more processors of the same type or different types (for example, a combination of a plurality of FPGAs or a combination of a CPU and an FPGA). ) May be configured. Further, a plurality of processing units may be configured by one processor.
  • one processor is configured by combining one or more CPUs and software. There is a form in which this processor functions as a plurality of processing units.
  • SoC System On Chip
  • the various processing units are configured by using one or more of the various processors as a hardware structure.
  • circuitry in which circuit elements such as semiconductor elements are combined can be used.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Optics & Photonics (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)
PCT/JP2020/011576 2019-05-28 2020-03-17 マッチング装置、方法およびプログラム Ceased WO2020240995A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2021522650A JP7098835B2 (ja) 2019-05-28 2020-03-17 マッチング装置、方法およびプログラム
US17/505,632 US12033366B2 (en) 2019-05-28 2021-10-20 Matching apparatus, matching method, and matching program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019099177 2019-05-28
JP2019-099177 2019-05-28

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/505,632 Continuation US12033366B2 (en) 2019-05-28 2021-10-20 Matching apparatus, matching method, and matching program

Publications (1)

Publication Number Publication Date
WO2020240995A1 true WO2020240995A1 (ja) 2020-12-03

Family

ID=73552889

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/011576 Ceased WO2020240995A1 (ja) 2019-05-28 2020-03-17 マッチング装置、方法およびプログラム

Country Status (3)

Country Link
US (1) US12033366B2 (https=)
JP (1) JP7098835B2 (https=)
WO (1) WO2020240995A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023129826A (ja) * 2022-03-07 2023-09-20 キヤノン株式会社 画像処理装置、方法、プログラム及び記憶媒体

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011177494A (ja) * 2010-02-04 2011-09-15 Toshiba Corp 画像処理装置、超音波診断装置、及び画像処理方法
JP2013123528A (ja) * 2011-12-14 2013-06-24 Hitachi Ltd 画像診断支援装置、画像診断支援方法
JP2019013724A (ja) * 2017-07-03 2019-01-31 株式会社リコー 診断支援システム、診断支援方法及び診断支援プログラム

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8194947B2 (en) * 2006-11-21 2012-06-05 Hologic, Inc. Facilitating comparison of medical images
JP5159301B2 (ja) 2007-12-28 2013-03-06 株式会社東芝 医用画像表示装置および画像表示方法
RU2015121699A (ru) * 2012-11-06 2016-12-27 Конинклейке Филипс Н.В. Улучшение ультразвуковых изображений
JP6112291B2 (ja) * 2012-12-11 2017-04-12 パナソニックＩｐマネジメント株式会社 診断支援装置および診断支援方法
JP6382036B2 (ja) * 2013-09-30 2018-08-29 キヤノンメディカルシステムズ株式会社 超音波診断装置及び画像処理装置
JP6346445B2 (ja) * 2014-01-10 2018-06-20 キヤノン株式会社 処理装置、処理装置の制御方法、およびプログラム
DE102015208929B3 (de) * 2015-05-13 2016-06-09 Friedrich-Alexander-Universität Erlangen-Nürnberg Verfahren zur 2D-3D-Registrierung, Recheneinrichtung und Computerprogramm
EP3416560A4 (en) * 2015-12-28 2019-12-25 Metritrack, Inc. SYSTEM AND METHOD FOR CO-REGISTERING MEDICAL IMAGE DATA
JP2018175227A (ja) * 2017-04-10 2018-11-15 富士フイルム株式会社 医用画像表示装置、方法およびプログラム
US11138746B2 (en) 2017-07-03 2021-10-05 Ricoh Company, Ltd. Diagnostic support system and diagnostic support method
EP3677181B1 (en) * 2017-08-28 2021-10-13 FUJIFILM Corporation Medical image processing apparatus, medical image processing method, and medical image processing program

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011177494A (ja) * 2010-02-04 2011-09-15 Toshiba Corp 画像処理装置、超音波診断装置、及び画像処理方法
JP2013123528A (ja) * 2011-12-14 2013-06-24 Hitachi Ltd 画像診断支援装置、画像診断支援方法
JP2019013724A (ja) * 2017-07-03 2019-01-31 株式会社リコー 診断支援システム、診断支援方法及び診断支援プログラム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023129826A (ja) * 2022-03-07 2023-09-20 キヤノン株式会社 画像処理装置、方法、プログラム及び記憶媒体

Also Published As

Publication number Publication date
US12033366B2 (en) 2024-07-09
JPWO2020240995A1 (https=) 2020-12-03
JP7098835B2 (ja) 2022-07-11
US20220044052A1 (en) 2022-02-10

Similar Documents

Publication Publication Date Title
US20200058098A1 (en) Image processing apparatus, image processing method, and image processing program
US10803354B2 (en) Cross-modality image synthesis
CN102525534B (zh) 医用图像处理装置、医用图像处理方法
JP6363575B2 (ja) 画像位置合わせ装置および方法並びにプログラム
EP3164075B1 (en) Unified coordinate system for multiple ct scans of patient lungs
EP1719078B1 (en) Device and process for multimodal registration of images
EP2189942A2 (en) Method and system for registering a medical image
JP6967983B2 (ja) 画像処理装置、画像処理方法、及びプログラム
JPH08131403A (ja) 医用画像処理装置
US20190012805A1 (en) Automatic detection of an artifact in patient image data
Alam et al. Medical image registration: Classification, applications and issues
EP2821968B1 (en) Processing model data representing a biological body section having a defect portion
Alam et al. Evaluation of medical image registration techniques based on nature and domain of the transformation
Alam et al. A review on extrinsic registration methods for medical images
JP6788113B2 (ja) 医用画像処理装置、方法およびプログラム
JP6821036B2 (ja) 医用画像処理装置、方法およびプログラム
KR20160057024A (ko) 마커리스 ３차원 객체추적 장치 및 그 방법
JP7098835B2 (ja) マッチング装置、方法およびプログラム
US10580136B2 (en) Mapping image generation device, method, and program
US12488479B2 (en) Image alignment apparatus, method, and program
JP7394959B2 (ja) 医用画像処理装置、医用画像処理方法及びプログラム、医用画像表示システム
EP4494085B1 (en) Providing normalised medical images
KR20210013384A (ko) 수술위치 정보제공방법 및 수술위치 정보제공장치
JP7015351B2 (ja) 医用画像処理装置、医用画像処理方法
Shanthana et al. 1 Medical Image Processing: A Multimodal Fusion Technique

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20815151

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021522650

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20815151

Country of ref document: EP

Kind code of ref document: A1