KR101963650B1 - Method for correcting medical images, apparatus, and recording medium thereof - Google Patents

Abstract

The present invention relates to a medical image correcting method, an apparatus therefor, and a recording medium on which the medical image correcting method is performed. According to the medical image correcting method of the present invention, reference information on the position and direction of an anatomical structure in a non- An error is detected by comparing the position and the direction in the image with each other.
Accordingly, errors such as left / right and up / down / down / up / down of the image at the time of image loading can be quickly identified and corrected, and accurate diagnosis and operation can be attained and the convenience of the user can be improved because the image error is automatically corrected.

Description

TECHNICAL FIELD The present invention relates to a medical image correcting method, a device for the same, and a recording medium on which the medical image correcting method,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a medical image correcting method, an apparatus therefor, and a recording medium on which the medical image correcting method is performed. More particularly, the present invention relates to a medical image correcting method, And a recording medium on which the medical image correction method and the medical image correction method are applied.

Various kinds of medical image image files including computerized tomography (CT) and magnetic resonance imaging (Magnetic Resonance Imaging) are stored and managed according to the DICOM standard. DICOM has been proposed for the easy exchange / distribution of medical images such as CT, MRI, and ultrasonic wave as a standard for medical image transmission and storage defined by the DICOM Committee composed of the American Radiological Society (ACR) and the American Electrical Manufacturers Association (NEMA) .

The DICOM file format consists mainly of a header and an image data part. However, in the case of CT and MRI images, an attribute value such as an image orientation (Image Orientation) and an image position (Image Position) related to an image plane module (image plane module) Is stored.

For reference, the image direction represents the direction cosine of the first row and the first column with respect to the patient, and the image position represents the x, y, and z axes of the upper left corner of the image, The image is reconstructed on the basis of the tag value related to the image direction and the image position stored in the DICOM header.

Therefore, if the information is stored incorrectly in the DICOM header, or the information actually photographed and the information stored in the DICOM header do not match, the direction or position is wrong and the image is displayed. If the doctor does not recognize such an error, Is very high.

In order to solve such an error, Korean Patent No. 10-1477128 has proposed a method of correcting a unilateral error by comparing a medical examination name with a medical image. Such a conventional technique has a limit that can not be applied at a point in time when a diagnosis can not be made by a method that can be performed after a medical examination name is already issued.

Korean Patent No. 10-1477128 (December 22, 2014)

The present invention has been proposed in order to solve the problem of the prior art in which there is a risk of misinformation or erroneous operation due to the fact that the information is erroneously stored in the DICOM header or the actual shooting information and the stored information are inconsistent with each other, A medical image correcting method capable of quickly grasping and correcting an error in a medical image correction apparatus, an apparatus therefor, and a recording medium on which the same is recorded.

According to an aspect of the present invention, there is provided a method of correcting a medical image using a medical image correcting apparatus, the method comprising: storing reference information on an anatomical structure in a first medical image, which is a non-defective medical image; Recognizing a position and a direction of an anatomical structure corresponding to the reference information in a second medical image that is a loaded medical image; Detecting an error of the second medical image by comparing the position and orientation of the anatomical structure according to the reference information with the position and orientation of the anatomical structure recognized in the second medical image; And performing a correction on the second medical image in response to an error of the second medical image.

Here, the step of storing the reference information may store the position or direction of the anatomical structure in the image according to at least one of the sectional image and the three-dimensional image as the reference information.

The step of performing the correction on the second medical image may be performed by modifying the tag value of the DICOM header of the second medical image or by changing the position and direction of the volume of the second medical image.

According to another aspect of the present invention, there is provided a medical image correcting apparatus comprising: a memory including a reference information storage unit for storing reference information on the position and orientation of an anatomical structure in a first medical image, which is a non-defective medical image; Comparing the position and orientation of the anatomical structure corresponding to the reference information recognized in the second medical image, which is the loaded medical image, with the position and direction of the anatomical structure according to the reference information, A first error detecting unit for detecting an error; And an image correcting unit for correcting the second medical image in response to an error of the second medical image according to the first error detecting unit.

Here, the memory may further include a statistical information storage unit for storing statistical information related to the anatomical structure, and the medical image correcting apparatus may further include a statistical information storage unit storing information about the anatomical structure corresponding to the statistical information recognized in the second medical image And a second error detector for detecting an error of the second medical image by comparing the statistical information with the statistical information, wherein the image corrector corrects the error of the second medical image according to the second error detector, The correction for the medical image can be performed.

The apparatus may further include a third error detector for detecting a marker attached to the examinee at the time of photographing to determine whether the second medical image is erroneous and detecting an error of the second medical image based on the recognized marker And the image correction unit may perform the correction on the second medical image corresponding to the error of the second medical image according to the third error detection unit.

When the second medical image is an image of the oral contraception, the first error detecting unit detects the position and orientation of the cortical bone in the second medical image based on the position and orientation of the intraoral cortex in the axial cross- And the first error detecting unit can detect an error in the sagittal image of the second medical image based on the position and direction of the tooth region and the cervical vertebrae in the second medical image .

The image correction unit may modify the tag value of the DICOM header of the second medical image or change the position and the direction of the volume of the second medical image.

As described above, according to the present invention, it is possible to quickly identify and correct an error such as a left / right or an upside / downside of an image at the time of image loading, thereby correct diagnosis and operation can be achieved.

According to the present invention, it is possible to improve the accuracy of error detection by detecting errors through various methods based on reference information, statistical information, and markers.

In addition, according to the present invention, since the video error is corrected automatically, the convenience of the user can be improved.

1 is a block diagram showing a configuration of a medical image correction apparatus according to an embodiment of the present invention;
2 is a block diagram including a detailed configuration of a medical image correcting apparatus according to an embodiment of the present invention;
FIG. 3 is a reference diagram for explaining reference information according to an embodiment of the present invention; FIG.
4 is a flowchart of a medical image correcting method according to an embodiment of the present invention; And
5 is a reference diagram for explaining a method of detecting an error in a medical image based on reference information.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed to be limited to ordinary or dictionary meanings and the inventor is not limited to the concept of terminology for describing his or her invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

The medical image described in the present specification is an image in which the data is generated and stored in accordance with the DICOM format and includes a computer tomography (CT), a magnetic resonance imaging (MRI), a computerized radiography (CR) (DICOM) standards such as Ultrasound Imaging (US), Digital Radiography (X-ray), and Digital Oral Radiographic Imaging.

Hereinafter, a CT image will be described as an example of a medical image.

FIG. 1 is a block diagram showing a configuration of a medical image correcting apparatus according to an embodiment of the present invention, and FIG. 2 is a block diagram including a detailed configuration of a medical image correcting apparatus according to FIG.

1, a medical image correction apparatus 100 according to an embodiment of the present invention includes a user interface unit 10, a memory 20, an error detection module 30, and an image correction unit 40 .

The user interface unit 10 receives necessary information from a user and displays input information for inputting information such as a mouse, a keyboard, a button, and a keypad, a medical image to be loaded, an input menu, A display unit for displaying various information, a touch screen for providing input and output through a single device, and the like.

Referring to FIG. 2, the memory 20 includes a reference information storage unit 21 and a statistical information storage unit 22 (FIG. 2). The memory 20 stores various types of information, ).

The reference information storage unit 21 stores reference information on the position and orientation of the anatomical structure in the defect-free medical image. Here, the defect-free medical image is a medical image corresponding to the case where the subject is photographed according to the correct setting, the image data obtained through photographing is stored in accordance with the DICOM format, and the reference information is the corresponding anatomical And information on the position and direction in which the structure normally appears.

3 is a reference diagram for explaining reference information according to an embodiment of the present invention.

Referring to FIG. 3, there is shown an example of a defect-free medical image that is normally loaded as a CT image of a part of the oral maxillofacial region and has no error.

In FIG. 3, A1 to C1 are sectional images, A1 is a coronal image, B1 is an axial image, C1 is a sagittal image, D1 is a three-dimensional reconstructed image .

When the medical image is normally displayed, the cortical bone 301 including the tooth or not including the teeth as shown in the axial cross-sectional image of B1 appears as a convex parabolic shape upward, and in the sagittal image of C1, the cervical vertebrae region 303 appears on the right side of the screen and a tooth region 305 appears on the left side of the screen. In the three-dimensional image of D1, the teeth region 307 is displayed so as to be directed forward.

As described above, when the image is correctly photographed and normally stored in the DICOM format, there is a specific position and direction in which each anatomical structure is displayed in the image, and the reference information storage unit 21 normally stores the corresponding cross- It stores information about the location and orientation of a particular anatomical structure in the image. At this time, information about the same anatomical structure can be stored irrespective of kinds of images such as an axial cross-sectional image, a sagittal image, and a three-dimensional image, but the anatomical structures appearing in each image are different, Information about the enemy structure may be stored.

Although the position and direction of the tooth region are exemplified in the oral maxillofacial region in the above description, the reference information storage unit 21 is not limited to this, and the position and direction in which the specific anatomical structure is normally displayed Can be stored. At this time, the anatomical structure can be variously selected as a reference region for recognizing errors such as whether the medical image is upside-down, left-right reversed, rotated, or skewed. For example, the anatomical structure existing only on one side of the left and right sides can be used to determine whether the image is reversed left and right, and information about a plurality of anatomical structures can be stored as reference information.

Then, the statistical information storage unit 22 of the memory 20 stores statistical information on the anatomical structure. The stored statistical information may be, for example, statistical information of the anatomical structure according to the variables related to the examinee such as the age, sex, nationality, and race of the examinee, or statistical information on the difference between the left and right of the anatomical structure, / It is statistical information that can detect errors such as whether to turn left / right, turn, or skew.

The error detection module 30 analyzes the loaded medical image according to a predetermined error detection standard including reference information and statistical information stored in the memory 20 to detect errors such as up / down / left / right inversion, rotation, do.

Referring to FIG. 2, the error detection module 30 includes a first error detection unit 31, a second error detection unit 32, and a third error detection unit.

The first error detection unit 31 recognizes the position and direction of a specific anatomical structure according to the reference information stored in the reference information storage unit 21 of the memory 20 in the loaded medical image, And detects errors in the medical image by comparing positions and directions according to the information. At this time, the position and direction of the anatomical structure in the loaded medical image can be recognized using various image recognition algorithms, or recognition can be performed based on user input through the user interface unit 10. [

If the position and orientation of the first error detection unit 31 and the position and direction according to the recognized position and direction differ from the predetermined error range as a result of the comparison, the first error detection unit 31 determines that the medical image is upside down, It is determined that an error such as an angle inclination or a rotation is generated.

The second error detection unit 32 detects an error in the medical image based on the statistical information about the anatomical structure stored in the statistical information storage unit 22 of the memory 20. For example, when there is statistical information that the left jaw joint is relatively larger than the left jaw joint, the right jaw joint is recognized as larger than the right jaw joint, It can be determined that the left and right sides are reversed.

As described above, the second error detecting unit 32 compares the information about the anatomical structure recognized in the loaded medical image with the statistical information, and if the statistical information is different from the predetermined error range, the second error detecting unit 32 performs a left / right inversion, It is determined that an error such as a tilt or rotation at a predetermined angle has occurred.

The third error detecting unit 33 detects a marker in the medical image and detects an error in the medical image. Therefore, the processing through the third error detecting unit 33 assumes that a marker for determining the presence or absence of error is attached to the examinee and the image is photographed. For example, in the case of the image relating to the maxillofacial region, it is possible to distinguish the left and right sides by producing the left and right sides with different thicknesses or materials, or embossing or cathodically processing the left and right side markings such as L and R, respectively The bite block processed by the examinee can be mounted and taken. Alternatively, an impermeable radioactive substance attached to a body-specific region of a subject to be photographed, for example, a body region including soft tissues such as bilateral balls or gums, can be used as a marker. In addition, various types of markers that can identify the position and direction of a medical image can be applied so that errors such as left / right / upside / downside, rotation, and tilting of the medical image can be grasped.

The third error detecting unit 33 recognizes the marker in the medical image based on various image recognition algorithms and judges that there is an error in the medical image when the marker is in a state different from the original position or direction.

The first error detecting unit 31, the second error detecting unit 32 and the third error detecting unit 33 of the error detecting module 30 described above may be activated at the same time, Only some of the above three configurations may be selectively activated based on user input or the like. In addition, it is possible to set the priorities for the above three configurations, determine that the configuration having a higher priority is activated first, and determine whether to activate the configuration of the next level according to the determination result.

If it is determined through the error detection module 30 that there is an error in the medical image, the image correcting unit 40 corrects the medical image.

At this time, when an error is detected by the first error detecting unit 31, the correction is performed so that the position and direction of the anatomical structure that does not match the reference information match the reference information, and the second error detecting unit 32 When an error is detected, the image is corrected so that the anatomical structure conforms to the statistical information. Further, when an error is detected by the third error detecting section 33, the image is corrected so that the marker coincides with the original position and direction.

The image correcting unit 40 may correct the tag value of the DICOM header of the medical image or change the position and the direction of the volume of the medical image and display the changed value. For example, if it is determined that there is an error in the left-right reversal in the medical image, the image correcting unit 40 may correct the direction of the volume of the medical image so that the volume is rotated 180 degrees with respect to the Z- It is also possible to change the tag value corresponding to the attribute related to the image direction or position in the header so that the tag value is changed in the current state to be loaded. If the data of the DICOM header is changed, it is possible to utilize the corrected image even in another hospital in the future, so that it is possible to effectively prevent the same error from recurring.

If it is determined that there is an error through the error detection module 30, the error notification message is displayed through the user interface unit 10, and the correction is performed through the user interface unit 10 Or may be implemented manually in response to user input through the user interface.

 4 is a flowchart of a medical image correcting method according to an embodiment of the present invention. Hereinafter, with reference to FIG. 4, an organic operation of the medical image correcting apparatus 100 will be described.

Referring to FIG. 4, it is premised that a database is constructed by storing reference information and statistical information as a basis for judging whether or not an error of a medical image exists in the memory 20 in advance (S10). As described above, the reference information is information on the position and direction of a specific anatomical structure in a non-defective medical image, and statistical information is statistical information on an anatomical structure according to the characteristics of the examinee, the position of the anatomical structure, Is used to detect errors such as whether the medical image is upside-down, left-right reversed, rotated or skewed in the reference coordinate system, and the like.

The error detection module 30 loads the target medical image to be determined as an error, recognizes the position and direction of the anatomical structure corresponding to the reference information in the medical image (S11), and outputs the recognized position and orientation to the reference information And detects the error of the medical image (S13).

5 is a reference diagram for explaining a method of detecting an error in a medical image based on reference information.

FIG. 5 shows a CT image of the oral maxillofacial region in which a coronal image A2, an axial sectional image B2, a sagittal image C2, and a three-dimensional image D2 are displayed.

Referring to the axial sectional view B2, an intraoral cortical bone 501 including teeth or no teeth is shown as a downward convex parabola at the lower end. As shown in FIG. 3, in the defect-free medical image, the cortical bone appears to be convex upward in the upper part, so that it differs from the reference information. The error detection module 30 detects that there is an error in up- Can be distinguished.

In the sagittal image C2, the cervical vertebrae area 503 is shown on the left side of the screen and the tooth area 505 is shown on the right side, which is opposite to the normal image, It is possible to determine that there is an error in the left-right reversal in the sagittal plane image C2.

In addition, in the three-dimensional image D2, the teeth region 507 faces backward and differs from the forward reference information, so that it can be determined that there is an error.

If it is determined that there is an error in the medical image, the image correcting unit 40 corrects the medical image so that the anatomical structure is displayed according to the position and direction according to the reference information (S15, S17). The correction may be done by changing the tag value associated with the position or direction of the image in the DICOM header, or by modifying the position or orientation of the volume.

Here, when the medical image itself is corrected in such a manner that the position and direction of the volume are corrected, the image data obtained through the same imaging as the images A2, B2, C2, and D2 shown in FIG. 5 is reconstructed If an error is found in one of the plurality of images obtained by the image correction unit 40, the image correction unit 40 can perform correction on not only the image in which the error is found, but also other images.

Meanwhile, in the above-described step, only the first method of correcting the medical image based on the reference information about the position and direction of the anatomical structure is described. However, as described above, based on the statistical information stored in the memory 20 A second method of detecting and correcting an error by comparing information recognized in the medical information with statistical information, a third method of detecting and correcting an error of the medical image based on the position and direction of the marker mounted on the examinee from the time of shooting It is needless to say that the correction may be performed.

The above three correction methods may be applied according to user selection or setting, or may be selectively applied or may be determined depending on a situation depending on a result of error detection by any one method.

Therefore, the first to third methods are not necessarily limited to the respective steps of the medical image correcting method according to FIG. 4, but may be applied in appropriate combination, and may be flexibly changed according to setting or user selection.

As described above, according to the medical image correcting apparatus 100 and method according to the embodiment of the present invention, it is possible to quickly grasp and correct errors such as left / right, upside / downside, Diagnosis and treatment can be planned. Further, according to the present invention, since the image error is automatically corrected, the convenience of the user can be improved, and the accuracy of error detection can be improved by detecting errors through various methods based on reference information, statistical information, and markers .

Meanwhile, the medical image correcting method according to the embodiment of the present invention may be embodied as a program that can be executed by a computer, and may be embodied as various recording media such as a magnetic storage medium, an optical reading medium, and a digital storage medium.

Implementations of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or combinations thereof. Implementations may be implemented in a computer program product, such as an information carrier, e.g., a machine readable storage device, such as a computer readable storage medium, for example, for processing by a data processing apparatus, Apparatus (computer readable medium) or as a computer program tangibly embodied in a propagation signal. A computer program, such as the computer program (s) described above, may be written in any form of programming language, including compiled or interpreted languages, and may be stored as a stand-alone program or in a module, component, subroutine, As other units suitable for use in the present invention. A computer program may be deployed to be processed on one computer or multiple computers at one site or distributed across multiple sites and interconnected by a communications network.

Processors suitable for processing a computer program include, by way of example, both general purpose and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The elements of a computer may include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer may include one or more mass storage devices for storing data, such as magnetic, magneto-optical disks, or optical disks, or may receive data from them, transmit data to them, . ≪ / RTI > Information carriers suitable for embodying computer program instructions and data include, for example, semiconductor memory devices, for example, magnetic media such as hard disks, floppy disks and magnetic tape, compact disk read only memory A magneto-optical medium such as a floppy disk, an optical disk such as a DVD (Digital Video Disk), a ROM (Read Only Memory), a RAM , Random Access Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and the like. The processor and memory may be supplemented or included by special purpose logic circuitry.

While the specification contains a number of specific implementation details, it should be understood that they are not to be construed as limitations on the scope of any invention or claim, but rather on the description of features that may be specific to a particular embodiment of a particular invention Should be understood. Certain features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments, either individually or in any suitable subcombination. Further, although the features may operate in a particular combination and may be initially described as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, Or a variant of a subcombination.

Likewise, although the operations are depicted in the drawings in a particular order, it should be understood that such operations must be performed in that particular order or sequential order shown to achieve the desired result, or that all illustrated operations should be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various device components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and devices will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

It should be noted that the embodiments of the present invention disclosed in the present specification and drawings are only illustrative of specific examples for the purpose of understanding and are not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

10: user interface unit 20: memory
21: Reference information storage unit 22: Statistical information storage unit
30: error detection module 31: first error detection module
32: second error detection module 33: third error detection module
40: image correction unit

Claims (10)

A medical image correction method using a medical image correction device,
Storing reference information about a position and a direction of an anatomical structure in a first medical image which is a non-defective medical image;
Recognizing a position and a direction of an anatomical structure corresponding to the reference information in a second medical image that is a loaded medical image;
Detecting an error of the second medical image by comparing the position and orientation of the anatomical structure according to the reference information with the position and orientation of the anatomical structure recognized in the second medical image; And
And performing correction for the second medical image in response to an error of the second medical image,
Wherein the second medical image is a video image of a mouth surface,
Wherein the step of detecting an error in the second medical image detects an error in an axial sectional image of the second medical image based on a position and a direction of an intraoral cortical bone in the second medical image, Correction method.
The method according to claim 1,
Wherein the step of storing the reference information comprises:
Wherein the position or direction of the anatomical structure in the image according to at least one of the sectional image and the three-dimensional image is stored as the reference information.
The method according to claim 1,
Wherein performing the correction on the second medical image comprises:
Wherein the tag value of the DICOM header of the second medical image is modified or the position and direction of the volume of the second medical image is changed and displayed.
A computer-readable recording medium on which a program for executing the medical image correction method according to any one of claims 1 to 3 is recorded.
A memory including a reference information storage unit for storing reference information about a position and direction of an anatomical structure in a first medical image which is a non-defective medical image;
Comparing the position and orientation of the anatomical structure corresponding to the reference information recognized in the second medical image, which is the loaded medical image, with the position and direction of the anatomical structure according to the reference information, A first error detecting unit for detecting an error; And
And an image correcting unit for correcting the second medical image in response to an error of the second medical image according to the first error detecting unit,
Wherein the second medical image is a video image of a mouth surface,
Wherein the first error detecting unit detects an error in an axial sectional image of the second medical image based on a position and a direction of an intraoral cortical bone in the second medical image.
6. The method of claim 5,
The memory may further include a statistical information storage unit for storing statistical information related to an anatomical structure,
The medical image correcting device may further include a second error detecting unit for comparing the statistical information with the information about the anatomical structure corresponding to the statistical information recognized in the second medical image to detect an error of the second medical image ≪ / RTI &
Wherein the image correction unit performs the correction on the second medical image in response to an error of the second medical image according to the second error detection unit.
6. The method of claim 5,
Further comprising a third error detecting unit for recognizing a marker attached to the examinee at the time of photographing to determine the presence or absence of an error in the second medical image and for detecting an error of the second medical image based on the recognized marker,
Wherein the image correction unit performs the correction on the second medical image corresponding to the error of the second medical image according to the third error detection unit.
delete 6. The method of claim 5,
Wherein the first error detecting unit detects an error in a sagittal image of the second medical image based on a position and a direction of a tooth region and a cervical vertebra in the second medical image.
6. The method of claim 5,
Wherein the image correction unit comprises:
And corrects the tag value of the DICOM header of the second medical image or changes the position and direction of the volume of the second medical image and displays the modified medical image.

Images