KR20150141832A - Apparatus and method for bone density diagnosis based on noise of ct image - Google Patents

Abstract

The present invention relates to a bone density diagnosis apparatus and method using the dispersion noise of a medical image to measure bone density by using a noise included in a medical image and to diagnose various kinds of bone diseases therefrom. The method may include a step of detecting an object region which is a photographed skeletal structure of a person by analyzing the medical image; a step of selecting a region located in a predetermined distance from the edge of the object region as a peripheral region; a step of detecting a noise value for the peripheral region; and a step of changing the degree of noise into bone density, in reference to information on a correlation between the noise value and the bone density.

Description

TECHNICAL FIELD [0001] The present invention relates to an apparatus and a method for diagnosing a bone mineral density using a distributed image noise of a medical image,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an apparatus and a method for diagnosing a bone density using a distributed image noise of a medical image for acquiring medical information of a patient using noise included in a CT (Computed Tomography) image.

CTmputed Tomography (CT) is a technique in which a person enters a large circular machine with an X-ray generator and takes a cross-sectional image of the human body, unlike a simple X-ray.

CT imaging has the advantage that structures and lesions can be clearly seen because the structures do not overlap with each other compared with simple X-ray. When most of organs and diseases are suspected and need to be examined, As a test method.

However, since CT imaging acquires images by irradiating human body with X-rays, an X-ray scattering phenomenon occurs. Accordingly, medical images obtained through CT imaging basically have various noise noise may be included.

FIG. 1 is a view showing images of a user bone having a high bone density and a user bone having a low bone density.

Fig. 1 (a) is an image of a skeleton specimen having a high bone density, Fig. 2 (b) is an image of a skeleton specimen having a low bone density. When these two images are compared, A large amount of noise is generated around the sponge bone, whereas when the bone mineral density of the sponge bone is low, only a small amount of noise is generated around the sponge bone.

This is because, when X-rays for CT imaging are irradiated to the human body, the X-rays are reflected again after reaching the human skeleton. When the bone density is high, the X- The amount of noise scattered around the skeleton increases, while the amount of noise scattered around the skeleton decreases when the bone density is low.

That is, when the human body is irradiated with the X-ray for CT scan, it can be seen that the image characteristic that the amount of noise scattered around the human skeleton increases according to the bone density of the sponge bone.

In other words, it can be seen that the noise included in the medical image can also have information available for medical image analysis.

However, as disclosed in Korean Patent Laid-Open Publication No. 10-2000-0056228, a conventional medical image analysis technique is concerned with removing noise included in a medical image, and there is no concern about a method for utilizing the noise. I did.

Therefore, in the past, such image features have not been utilized at all, and the noise is removed unconditionally, resulting in a problem that the diversity of image analysis is degraded.

Accordingly, the present invention provides an apparatus and a method for diagnosing a bone mineral density using a distributed image noise of a medical image, which is capable of measuring bone density using the noise included in a medical image and diagnosing various bone diseases from the measured bone density.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method for analyzing a medical image, the method comprising: detecting an object region in which a human skeleton is photographed; Selecting an area located within a predetermined distance from an outer periphery of the object area as a peripheral area; Detecting a noise value for the peripheral region; And a step of referring to information on the correlation between the noise value and the bone density to convert the degree of noise into bone density.

The noise value is characterized by a noise intensity or a sharpness of a noise pattern.

Wherein the step of detecting the noise value comprises the steps of: detecting and collecting, as a noise pixel, a pixel having a brightness value greater than or equal to a noise detection reference level and not belonging to the object area, when the noise value is a noise intensity; And the noise intensity is calculated by dividing the noise intensity by the area of the surrounding area.

Wherein the step of detecting the noise value includes the steps of detecting a noise pattern by performing edge filtering on the surrounding area when the noise value is a sharpness of the noise pattern and determining the sharpness of the noise pattern based on the detection area of the noise pattern .

According to another aspect of the present invention, there is provided a medical imaging apparatus comprising: an image obtaining unit that obtains a medical image of a skeleton of a user; An object detection reference, a storage unit for storing information on a correlation between a noise value and a bone density; And analyzing the medical image based on the object detection criterion to detect an object region in which a human skeleton is photographed and calculating and reporting the bone density of the user based on noise values existing in a peripheral region of the object region The present invention provides a diagnostic apparatus for a bone density using a distributed image noise of a medical image.

As described above, in the present invention, medical information such as bone density can be obtained by utilizing noise information that was a target of removal in the conventional image analysis operation. Therefore, the present invention provides an effect of acquiring new medical information that can not be obtained in the past, while reducing the cost and time required for noise removal.

FIG. 1 is a view showing images of a user bone having a high bone density and a user bone having a low bone density.
FIGS. 2 and 3 are diagrams for explaining the correlation between noise in a medical image and bone density.
FIG. 4 is a diagram illustrating an apparatus for diagnosing a bone mineral density using a distributed image noise of a medical image according to an embodiment of the present invention.
5 is a diagram illustrating a method of diagnosing a bone density using a distributed image noise of a medical image according to an embodiment of the present invention.
6 is a view for explaining a method of setting an object region and a surrounding region according to a method of diagnosing a bone density using a distributed image noise of a medical image according to an embodiment of the present invention.
7 is a diagram illustrating a method of diagnosing a bone density using a distributed image noise of a medical image according to another embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

The following terms are defined in consideration of the functions of the present invention, and these may be changed according to the intention of the user, the operator, or the like.

The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art to which the present invention pertains. Only. Therefore, the definition should be based on the contents throughout this specification.

Before describing the present invention, the correlation between the noise in the medical image and the bone mineral density will be described again.

FIGS. 2 and 3 are diagrams for explaining the correlation between noise in the medical image and the bone mineral density. FIG. 2 (a) is a CT image showing the actual radius of six osteoporosis users and eight normal persons, (b) shows CT images of six osteoporosis users and eight normal ovaries.

Referring to FIG. 2, it can be seen that the noise intensity included in the CT image of the osteoporosis user is relatively small compared with the noise intensity included in the CT image of the normal person (the red line represents the osteoporosis users U11 to U16) The blue line represents the noise intensity obtained from the image of the normal person (U21 ~ U28), and x represents the number of users).

From this, it can be easily deduced that the bone density and the noise intensity have a proportional relationship as shown in FIG.

In addition, as described above, when an X-ray for a CT scan is irradiated to a human body, the X-ray reaches a human skeleton and then is reflected back a certain amount. At this time, the reflected X- Pattern.

However, the sharpness of the noise pattern varies depending on the density of the sponge bone. When the density of the sponge bone is high, the amount of noise scattered around the sponge bone increases and the noise pattern of the stripe shape becomes blurred (See noise in the red box), and when the density of the sponge bone is low, the amount of noise scattered around the sponge bone is relatively small and the sharpness of the line-shaped noise pattern is maintained (see noise in the blue box in FIG. 2) .

That is, it can be seen that as the density of sponge bone (i.e., bone density) is increased, the sharpness of the noise pattern is further lowered.

Therefore, the present invention utilizes the above-described image features to variously diagnose bone density, osteoporosis, and spinal disease based on the noise included in the CT image.

FIG. 4 is a diagram illustrating an apparatus for diagnosing a bone mineral density using a distributed image noise of a medical image according to an embodiment of the present invention.

4, the BMD diagnostic apparatus 100 of the present invention includes an image acquisition unit 110, a storage unit 120, an image analysis unit 130, a data output unit 140, and the like .

The image acquiring unit 110 receives and acquires a medical image obtained by photographing a human skeleton through a CT photographing apparatus, an X-ray apparatus, or the like.

The storage unit 120 stores information on a skeleton model obtained by three-dimensionally modeling the shape of a human skeleton, a reference for detecting an object corresponding to the skeleton (i.e., pixel brightness value and pixel density corresponding to the skeleton) An object detection reference storage unit 121, a diagnostic information storage unit 123 for storing information on a correlation between a noise value (noise intensity or noise pattern sharpness) and a bone density, a correlation between a bone density and a bone disease, And various data necessary for the image analysis operation of the BMD diagnostic apparatus are stored through these.

The image analysis unit 130 controls the operations of the image acquisition unit 110, the storage unit 120 and the data output unit 140 to measure the bone density of the user using the noise included in the medical image, And performs various arithmetic operations to diagnose and notify various bone diseases. That is, the medical image is analyzed based on the object detection criterion to detect the object region where the human skeleton is photographed, and then the noise value existing in the peripheral region of the object region is calculated. Based on the correlation between the noise value and the bone density, the noise value is converted into the bone density of the user, and the user is notified.

The data output unit 140 includes a monitor, a printer, and the like, and configures and outputs various screens (images and text) for notifying the user of the operation state and the operation result of the medical image analysis apparatus 100.

FIG. 5 is a diagram illustrating a method for diagnosing a bone density using a distributed image noise of a medical image according to an embodiment of the present invention, which relates to a method for measuring bone density using noise intensity.

First, a user's body (in particular, a user's skeleton) is photographed through a CT photographing device or the like to acquire a medical image to be used for bone disease analysis (S11).

Then, the entire region of the medical image is sequentially scanned, and a pixel having a brightness value equal to or higher than a reference value is detected as an object candidate region having a density higher than a reference density. And, only if the shape of the object candidate region has a shape corresponding to the skeleton model acquired in advance, the object candidate region is finally acquired as an object region as shown in FIG. 6A (S12). At this time, the reference value and the reference density are preferably defined and registered before the medical image analysis operation, and are adjustable values by a medical staff or an external apparatus, if necessary.

When an object area is obtained through step S12, an area located within a predetermined distance d from the outline of the object area is acquired as a peripheral area of the object area as shown in FIG. 6B (S13) . At this time, the selection criterion of the peripheral region, that is, the distance d is preferably defined and registered before the medical image analysis operation, and is a value adjustable by a medical staff or an external apparatus, if necessary.

After detecting and collecting the noise pixels existing in the surrounding area, the number of collected noise pixels is divided by the area of the surrounding area to obtain the noise intensity value of the surrounding area (S14). At this time, the noise pixel means a pixel having a predetermined brightness value, which can not form an object candidate region, or does not have a shape corresponding to a skeleton model even if an object candidate region is formed.

After referring to the correlation between the previously defined noise intensity and the bone density, the noise intensity obtained in step S14 is converted into bone density (step S15), and the user is notified of the noise intensity (step S16).

However, if necessary, information on the user's body characteristics (i.e., age, gender, measurement site, etc.) is additionally input from the user, and then the information and the BMD diagnostic value The risk of osteoporosis and the degree of progression of osteoporosis may additionally be considered together with guidance on diagnosis of bone mineral density.

FIG. 7 is a diagram illustrating a method of diagnosing a bone density using a distributed image noise of a medical image according to another embodiment of the present invention, and it relates to a method of measuring a bone density using a noise generation pattern instead of a noise intensity.

First, a medical image to be used for bone disease analysis is acquired (S21), and the entire region of the medical image is sequentially scanned, and a region having a brightness value equal to or higher than a reference value is detected as an object candidate region. Only when the shape of the object candidate region has a shape corresponding to a previously obtained skeleton model, the object candidate region is finally acquired as an object region (S22).

When the object region is acquired through step S22, the peripheral region of the object region is selected as an area located within a predetermined distance from the outer periphery of the object region (S23).

Considering that the noise pattern amount detected through the edge filtering operation may be changed according to the sharpness of the noise pattern, edge filtering for the surrounding area is performed to detect a noise pattern existing in the surrounding area (S24) The sharpness of the noise pattern is determined based on the detection area of the pattern (S25).

The noise pattern detection amount detected in step S25 is converted into bone density (S26) by referring to the correlation between the defined noise pattern sharpness and the bone density, and the user is notified (S27). Of course, at this time, diagnostic information about the risk of osteoporosis inferred from the diagnostic value of bone density, degree of progression of osteoporosis, etc. may be additionally calculated, and this information may be used together with the diagnostic value of bone density.

The computer-readable recording medium on which the program commands are recorded may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, Media storage devices.

The computer-readable recording medium on which the above-described program is recorded may be distributed to a computer apparatus connected via a network so that computer-readable codes can be stored and executed in a distributed manner. In this case, one or more of the plurality of distributed computers may execute some of the functions presented above and send the results of the execution to one or more of the other distributed computers, The computer may also perform some of the functions described above and provide the results to other distributed computers as well.

A computer for reading a recording medium on which an application that is a program for driving a BMD diagnostic apparatus and method utilizing distributed image noise of a medical image according to each embodiment of the present invention can be read is a general PC such as a general desktop or a notebook computer A mobile terminal such as a smart phone, a tablet PC, a PDA (Personal Digital Assistants), and a mobile communication terminal, and it should be interpreted as all devices capable of computing (CTmputing).

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to perform a part or all of the functions in one or a plurality of hardware. As shown in FIG. The codes and code segments constituting the computer program may be easily deduced by those skilled in the art. Such a computer program can be stored in a computer-readable storage medium (CTmputer Readable Media), read and executed by a computer, thereby realizing an embodiment of the present invention. As a storage medium of the computer program, a magnetic recording medium, an optical recording medium, or the like can be included.

It is also to be understood that the terms such as " comprises, "" comprising," or "having ", as used herein, mean that a component can be implanted unless specifically stated to the contrary. But should be construed as including other elements. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used terms, such as predefined terms, should be interpreted to be consistent with the contextual meanings of the related art, and are not to be construed as ideal or overly formal, unless expressly defined to the contrary.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

Claims (6)

Analyzing a medical image to detect an object region in which a human skeleton is photographed;
Selecting an area located within a predetermined distance from an outer periphery of the object area as a peripheral area;
Detecting a noise value for the peripheral region; And
A method for diagnosing bone mineral density using a distributed image noise of a medical image, comprising the step of referring to information on a correlation between a noise value and a bone density to convert the noise level to a bone density.
2. The method of claim 1,
Wherein the noise image is a noise intensity or a noise pattern sharpness.
3. The method of claim 2, wherein detecting the noise value comprises:
Wherein when the noise value is a noise intensity, a pixel having a brightness value equal to or higher than a noise detection reference and not belonging to the object region is detected and collected as a noise pixel, the number of the collected noise pixels is divided by the area of the peripheral region, And calculating the intensity of the image. The method of diagnosing bone mineral density using distributed image noise of a medical image.
3. The method of claim 2, wherein detecting the noise value comprises:
Wherein edge filtering is performed on the peripheral region to detect a noise pattern and the sharpness of the noise pattern is recognized based on the detection area of the noise pattern when the noise value is the sharpness of the noise pattern A Method of Diagnosing Bone Mineral Density Using Distributed Image Noise.
A computer-readable recording medium on which a program for executing the touch screen control method according to any one of claims 1 to 4 is recorded.
An image acquiring unit acquiring a medical image of a skeleton of a user;
An object detection reference, a storage unit for storing information on a correlation between a noise value and a bone density; And
An image analysis unit for analyzing the medical image based on the object detection criterion to detect an object region in which a human skeleton is photographed and calculating and reporting a bone density of the user based on a noise value existing in a peripheral region of the object region, Bone density diagnostic system using distributed image noise of medical images.

Images