KR101886936B1 - The method and apparatus for enhancing contrast of ultrasound image using probabilistic edge map - Google Patents

Abstract

A method of improving contrast in an ultrasound image using a probabilistic edge map according to an embodiment of the present invention includes acquiring an ultrasound original image for a target object into a plurality of frames, determining a degree of similarity between the acquired plurality of frames, Matching a plurality of frames of the ultrasound image determined to be similar to each other, extracting a portion estimated as an edge from the plurality of ultrasound-matched images generated by matching, generating a probability edge map for the extracted portion, And applying the generated probability edge map to the ultrasound original image.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and apparatus for enhancing contrast in an ultrasound image using a probability edge map,

The present invention relates to a method and apparatus for improving contrast in an ultrasound image using a probabilistic edge map.

In general, the audio frequency refers to a range band of 16 Hz to 20 kHz, and the ultrasonic wave refers to a frequency band of 20 kHz or more. The ultrasound diagnostic apparatus irradiates an ultrasound signal generated from a transducer of a probe to a target object, receives information of an echo signal reflected from the target object, and obtains an image of a site inside the target object. In particular, the ultrasonic diagnostic apparatus is used for medical purposes such as observation of an object, foreign object detection, and injury measurement. Such an ultrasonic diagnostic apparatus is more stable than the diagnostic apparatus using X-ray, is capable of displaying an image in real time, and is safe because there is no radiation exposure, so that it is widely used with other diagnostic apparatuses.

Conventional ultrasonic diagnostic apparatuses are expensive and have a problem in that their size and volume are large and are not suitable for quick and flexible use in case of an emergency. In addition, there is not much opportunity for the public to see or operate ultrasonic diagnostic devices other than the video specialist. As a result, the general public was forced to shoot ultrasound images only at medical institutions in case of illness or the like.

As a countermeasure against such a problem, there is a tendency that a wireless ultrasonic imaging apparatus is developed. However, such a wireless small-sized ultrasound imaging apparatus is required to continuously research and develop techniques for improving the image quality in terms of image quality compared to conventional ultrasound diagnostic apparatuses.

1. Korean Patent Publication No. 10-2004-0070404 (Published on August, 2004)

An object of the present invention is to provide a method and apparatus for effectively improving contrast in an ultrasound image obtained wirelessly using a portable ultrasound imaging apparatus or the like. In other words, it is intended to provide a method and apparatus for effectively achieving contrast enhancement and edge preservation in an ultrasound image.

As an embodiment of the present invention, a method and apparatus for improving contrast in an ultrasound image using a probability edge map can be provided.

A method of improving contrast in an ultrasound image using a probabilistic edge map according to an embodiment of the present invention includes acquiring an ultrasound original image for a target object into a plurality of frames, determining a degree of similarity between the acquired plurality of frames, Matching a plurality of frames of the ultrasound image determined to be similar to each other, extracting a portion estimated as an edge from the plurality of ultrasound-matched images generated by matching, generating a probability edge map for the extracted portion, And applying the generated probability edge map to the ultrasound original image.

The determination of similarity between the plurality of acquired frames is performed according to a mean structural similarity measure (MSSIM), and a plurality of frames of the ultrasound image determined to be similar, the measured structural similarity value being equal to or greater than a first reference value Can be matched.

In the step of matching a plurality of frames of the ultrasound image determined to be similar, the ultrasound original image according to an exemplary embodiment of the present invention can be acquired as N frames, and N is a positive integer, The first ultrasonic-matched image is generated by matching the frames, the second ultrasonic-matched image is generated by matching the first ultrasonic-mapped image and the third frame, the matching between the frames is sequentially performed up to the Nth frame, In the step of extracting a portion estimated as an edge from the plurality of ultrasound-matched images generated by the plurality of ultrasound-matched images, portions estimated as edges from the plurality of ultrasound-matched images can be respectively extracted.

In the step of generating the probability edge map for the extracted part, a weighted edge is generated by weighting and summation of the extracted part from each of the ultrasound-matched images, and a probability edge map is generated for the extracted part. In the step of generating the map, a portion estimated as an edge based on at least one of the brightness value of the portion estimated as the edge included in the probability edge map and the signal applied from the user may be re-extracted.

The step of generating a probability edge map for the extracted portion according to an embodiment of the present invention further includes correcting the probability edge map based on the size of the re-extracted portion, Lt; / RTI > can be performed by removing from the probability edge map.

The step of applying the generated probability edge map to the ultrasound original image according to an embodiment of the present invention includes generating a first composite image by combining the corrected probabilistic edge map with the ultrasound original image, The second composite image may be an image having an improved contrast compared to the original image of the ultrasound.

An apparatus for enhancing contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention includes an image acquiring unit for acquiring an ultrasound original image for a target object into a plurality of frames, An edge matching unit for matching a plurality of frames of the ultrasound image determined to be similar, an edge estimating unit for extracting a portion estimated as an edge from the plurality of ultrasound matching images generated by matching, A probability edge map generating unit for generating a probability edge map for the portion and an imge learning for applying the generated probability edge map to the ultrasound original image.

Meanwhile, as an embodiment of the present invention, a computer program stored in a medium may be provided in combination with hardware such as a computer to execute the above-described method.

According to an embodiment of the present invention, contrast can be effectively improved in a wireless ultrasound image using a portable ultrasound imaging apparatus or the like. In other words, contrast enhancement and edge preservation in the ultrasound image can be achieved at the same time.

In addition, a probability edge map can be generated using a plurality of frames of a diagnostic region image for a target object. The generated probability edge map can be utilized for improving contrast and the like.

According to an embodiment of the present invention, edge determination and contrast enhancement can be achieved with respect to an ultrasound image obtained in a wirelessly operable portable ultrasound imaging apparatus, and the quality of an ultrasound image can be remarkably improved.

FIG. 1 is a schematic diagram of an ultrasound system according to an embodiment of the present invention. Referring to FIG. 1, (a) is an ultrasound original image, (b) is an ultrasound image using a Lee filter, (c) This is a comparative example of an ultrasound image.
2 is a flowchart illustrating a method for improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention.
Figures 3 to 10 illustrate an implementation of a method according to an embodiment of the present invention.
11 is a comparative example of an ultrasound original image and an ultrasound image with improved contrast according to an embodiment of the present invention.
12 shows a comparison example of the contrast ratio (CR) and the contrast-to-noise ratio (CNR) of an ultrasound original image and an ultrasound image with improved contrast according to an embodiment of the present invention.
13 shows a block diagram of an apparatus for improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

The terms used in this specification will be briefly described and the present invention will be described in detail.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. Also, in certain cases, there may be a term selected arbitrarily by the applicant, in which case the meaning thereof will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term, not on the name of a simple term, but on the entire contents of the present invention.

When an element is referred to as "including" an element throughout the specification, it is to be understood that the element may include other elements as well, without departing from the spirit or scope of the present invention. Also, the terms "part," " module, "and the like described in the specification mean units for processing at least one function or operation, which may be implemented in hardware or software or a combination of hardware and software . In addition, when a part is referred to as being "connected" to another part throughout the specification, it includes not only "directly connected" but also "connected with other part in between".

The term "ultrasound image " in the entire specification refers to an image of an object obtained using ultrasound.

Throughout the specification, the term "user" may refer to a medical professional, such as a physician, a dentist, a technician, a clinician, a radiologist, a sonographer, But is not limited thereto. In other words, a "user" may include a general person with a normal level of knowledge that can handle electronic devices without difficulty. In addition, "subject" may include animals not only for patients who need medical imaging for diagnosis but also for veterinary use. The object may include a part of the body. For example, the subject may include organs such as oral cavity, liver, heart, uterus, brain, breast, abdomen, or blood vessels. In addition, the object may comprise a phantom, and the phantom means a material having a volume very close to the biological density and the effective atomic number.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of an ultrasound system according to an embodiment of the present invention. Referring to FIG. 1, (a) is an ultrasound original image, (b) is an ultrasound image using a Lee filter, (c) FIG. 2 is a flowchart illustrating a method for improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention. FIGS. 3 to 10 are flowcharts illustrating a method of improving contrast in an ultrasound image according to an embodiment As shown in FIG.

In order to improve the contrast in the ultrasound image, there is a multiscale morphological method as a conventional technique. The conventional contrast enhancement technique tries to improve the contrast by using a single ultrasound image, and thus there is still a problem that the effect of improving the contrast of the ultrasound image is not high. To overcome this problem, there is a conventional FUZZY anisotropic diffusion method as a technique. Such a technique also uses a single ultrasound image to reduce the speckle and improve the contrast. However, such a conventional technique is still problematic in that a speckle is reduced and a boundary (e.g., an edge) of an object is blurred in an ultrasound image. Referring to FIG. 1, it can be seen that these conventional techniques have limitations in improving the contrast of an original image of an ultrasonic wave (see FIGS. 1B and 1C). Also, as a conventional technique, there is a speckle reduction algorithm using multi-frame, and the Speckle reduction method using a plurality of frames as a temporal averaging method is referred to. Although this technique uses a plurality of frames, the contrast improvement effect is still not achieved.

Referring to FIG. 2, a method of improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention includes acquiring an ultrasound original image for a target object as a plurality of frames (S100) A step S200 of determining the similarity between the frames, a step of matching a plurality of frames of the ultrasound image determined to be similar (S300), a step of extracting a portion estimated as an edge from the plurality of ultrasound- A step S500 of generating a probability edge map for the extracted portion, and a step S600 of applying the generated probability edge map to the ultrasound original image.

Referring to FIGS. 2 and 3, an ultrasound original image may be obtained by a plurality of frames (S100). The obtained plurality of frames (for example, 1 to 15) can be judged with respect to each other. The similarity determination between the plurality of frames is performed by a mean structural similarity measure (MSSIM) according to Equation (1) below, and the similarity value between the acquired ultrasound images The plurality of frames of the frame may be registered as shown in FIG.

According to an exemplary embodiment of the present invention, when the degree of similarity between the obtained plurality of frames is determined (S200), the similarity is determined to be different from a predetermined reference (for example, 0.9) It may start generating a signal to inform the original image to be acquired again.

In the step S300 of matching the plurality of frames of the ultrasound image determined to be similar, the ultrasound original image according to an embodiment of the present invention is obtainable with N frames, N is a positive integer, The first and second frames are matched to generate a first ultrasound-matched image R1, a second ultrasound-matched image R2 is generated by matching the first and third frames, Lt; / RTI > can be performed. When the matching is performed, for example, a total of N-1 ultrasonic matching images can be generated.

In addition, in step S400 of extracting a portion estimated as an edge from a plurality of ultrasound-matched images (for example, R1 to R14) generated by such matching, a portion estimated as an edge from a plurality of ultrasound- Can be extracted.

Referring to FIG. 5, in step S500 of generating a probability edge map for the extracted portion, weighted and summated portions are extracted from each of the ultrasound-matched images to generate a probability edge map 110 Can be generated. The weights assigned to the respective ultrasound matching images may be partly the same or different, and the sum of the weights given may be one. The weight can be determined according to the following equation (2). As shown in FIG. 6, the weights can be expressed in the form of a log graph.

7, in step S500 of generating a probability edge map for the extracted portion, at least one of brightness values of a portion estimated as an edge included in the probability edge map 110 and signals applied from the user A portion estimated as an edge can be re-extracted. In other words, a probability edge map 120 in which a portion estimated as an edge has been re-extracted can be generated.

일 수 있다.For example, when the brightness value of a portion estimated as an edge included in the probability edge map 110 is smaller than the second reference value, the portion is not determined as an edge, and only the re-extracted portion is included A probabilistic edge map 120 may be generated. The second reference value may be, for example, 0.65. Also, the range of the second reference value is

Lt; / RTI >

In addition, according to an embodiment of the present invention, a portion estimated as an edge may be re-extracted based on a signal applied from a user through a user device or the like. That is, a portion estimated as an edge can be re-extracted and a new probability edge map 120 can be generated. The user can perform edge detection in which the skill of the user is reflected by applying a signal for selecting a portion determined to be not an edge (e.g., clicking or the like) or selecting a portion determined as an edge through a user device or the like.

The step S500 of generating a probability edge map for the extracted portion according to an embodiment of the present invention may further include correcting the probability edge map based on the size of the re-extracted portion have. The probability edge map 120 can be newly generated through the re-extraction of the edge as described above and the probability edge map 120 is corrected based on the size of the portion determined as the edge in the new probability edge map 120 . Such a correction can be performed by removing the re-extracted portion whose size is less than the reference size from the probability edge map. For example, if the size of a portion determined as an edge is less than five pixels (e.g., a red arrow portion in FIG. 8), the portion may be removed as being not an edge. Conversely, if the size of the portion determined as an edge is 5 pixels or more (for example, a red arrow portion in FIG. 8, etc.), the portion can be regarded as an edge and can be maintained on the probability edge map. Based on this size determination, the probability edge map 120 may be calibrated and a calibrated probability edge map 130 may be obtained.

In step S600 of applying the generated probability edge map according to an embodiment of the present invention to the ultrasound original image, a first composite image e10 is generated by combining the corrected probabilistic edge map 130 with the ultrasound original image And the second composite image e20 is generated by synthesizing the ultrasound original image and the image extracted from the first composite image e10, .

Referring to FIG. 9, the corrected probabilistic edge map 130 may be combined with an ultrasound original image (e.g., 15) after Gaussian smoothing. The first synthesized image e10 can be generated through such a synthesis. The ultrasound original image may be the image itself taken from a portable ultrasound imaging apparatus, or an ultrasound image in which at least one image filter is applied as shown in FIG. The above-described composite image can be generated by the following Equation (3).

는 예를 들면 3.5,

는 1일 수 있지만, 이에 반드시 제한되는 것은 아니다. 예컨대,

는 콘트라스트를 강조하고자 하는 만큼 조절(예컨대, 증가 또는 감소)될 수 있다.According to an embodiment of the present invention,

For example, 3.5,

May be 1, but is not necessarily limited thereto. for example,

May be adjusted (e.g., increased or decreased) as desired to emphasize the contrast.

Referring to FIG. 10, an image extracted from the first composite image e10 and an ultrasound original image are synthesized to generate a second composite image e20, and a second composite image e20 is generated according to an embodiment of the present invention. May be an image having an improved contrast compared to the original image of the ultrasound. The above-described composite image can be generated by the following Equation (4).

는 예를 들면 3.5,

는 1일 수 있지만, 이에 반드시 제한되는 것은 아니다. 예컨대,

는 콘트라스트를 강조하고자 하는 만큼 조절(예컨대, 증가 또는 감소)될 수 있다.According to an embodiment of the present invention,

For example, 3.5,

May be 1, but is not necessarily limited thereto. for example,

May be adjusted (e.g., increased or decreased) as desired to emphasize the contrast.

11 is a comparative example of an ultrasound original image and an ultrasound image with improved contrast according to an embodiment of the present invention.

Referring to FIG. 11, the contrast difference in the region of interest (ROI) in each of the ultrasound original image 15 and the ultrasound image e20 improved in contrast according to an embodiment of the present invention is clearly displayed can confirm.

12 shows a comparison example of the contrast ratio (CR) and the contrast-to-noise ratio (CNR) of an ultrasound original image and an ultrasound image with improved contrast according to an embodiment of the present invention.

In order to obtain the comparison result as shown in FIG. 12, data verification was performed under the following conditions. The equipment used for data acquisition is portable wireless ultrasonic equipment. Equipment used to verify the effects of the present invention (e.g., Sonon 300c, etc.) can acquire ultrasound images at a rate of 15 frames / sec. The acquired ultrasound image can be transmitted in real time to a user device capable of wireless communication. A user device according to an exemplary embodiment of the present invention may be a PC, a smart phone, a tablet PC, a laptop, or a mobile display device capable of wireless or wired communication with external devices such as various servers, medical equipment (e.g., Sonon 300c and the like) A wearable device such as a watch, and the like, but the present invention is not limited thereto. The study data for the verification were 1 ~ 15th frames obtained using ultrasound phantom including liver region. 15 ^th frame was used as reference image as ultrasound original image.

Referring to FIGS. 11 and 12, the contrast-to-noise ratio (CNR) is improved by 51.89% as compared with the conventional ultrasound original image. The results of the various index items of this assurance are shown in the following table.

13 shows a block diagram of an apparatus for improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention.

An apparatus 1000 for improving contrast in an ultrasound image using a probability edge map according to an embodiment of the present invention includes an image obtaining unit 1100 for obtaining an ultrasound original image for a target object in a plurality of frames, A similarity determination unit 1200 for determining a similarity between frames, an image matching unit 1300 for matching a plurality of frames of an ultrasound image determined to be similar, an image matching unit 1300 for matching the plurality of ultrasound- A probability edge map generation unit 1500 for generating a probability edge map for the extracted part, and an image value learning unit 1600 for applying the generated probability edge map to the ultrasound original image ).

The contents of the above-described method can be applied in connection with the apparatus according to an embodiment of the present invention. Therefore, the description of the same contents as those of the above-described method with respect to the apparatus is omitted.

One embodiment of the present invention may also be embodied in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer readable medium may include both computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

1, 2, ..., 15: Ultrasonic original image (each frame)
R1, R2, ..., R14: respective ultrasonic matching images
110, 120, 130: probability edge map
e10, e20: Contrast improvement video
1000: Contrast improvement device
1100:
1200:
1300:
1400:
1500: Probability edge map generating unit
1600; Image study

Claims (8)

A method for improving contrast in an ultrasound image using a probability edge map,
Obtaining an ultrasound original image for a target object as a plurality of frames;
Determining a degree of similarity between the obtained plurality of frames;
The method comprising: registering a plurality of frames of an ultrasound image determined to be similar;
Extracting a portion estimated as an edge from the plurality of ultrasound-matched images generated by the matching;
Generating a probability edge map for each extracted portion; And
And applying the generated probability edge map to the ultrasound original image. ≪ Desc / Clms Page number 13 >
The method according to claim 1,
The determination of similarity between the obtained plurality of frames is performed according to a mean structural similarity measure (MSSIM), and a plurality of frames of the ultrasound image determined to be similar, the measured structural similarity value being equal to or greater than a first reference value Wherein the contrast is improved by using a probability edge map.
The method according to claim 1,
Wherein the ultrasound original image is obtainable with N frames, N is a positive integer,
In the step of matching a plurality of frames of the ultrasound image determined to be similar, a first ultrasound-matched image is generated by matching a first frame and a second frame, and the first ultrasound- And generating a second ultrasound matching image, wherein the matching between the frames is sequentially performed up to the Nth frame, and the contrast improving method in the ultrasound image using the probability edge map.
The method according to claim 1,
The generating of the probability edge map for the extracted portion generates the probability edge map by weighting and summation of the portion extracted from each of the ultrasound matching images,
Wherein the step of generating a probability edge map for the extracted part comprises the steps of: re-extracting a portion estimated as an edge based on at least one of a brightness value of a portion estimated as an edge included in the probability edge map and a signal applied from a user; Wherein the edge enhancement map is used to enhance contrast in an ultrasound image.
5. The method of claim 4,
The step of generating a probability edge map for the extracted portion further includes correcting the probability edge map based on the size of the re-extracted portion,
Wherein the calibration is performed by removing the re-extracted portion of the magnitude less than the reference magnitude from the probability edge map.
6. The method of claim 5,
Wherein the step of applying the generated probability edge map to the ultrasound original image comprises generating a first composite image by combining the corrected probabilistic edge map with the ultrasound original image, A second synthesized image is generated by synthesizing the ultrasound original image,
Wherein the second composite image is an image having an improved contrast with respect to the ultrasound original image. A method for improving contrast in an ultrasound image using a probabilistic edge map.
An apparatus for enhancing contrast in an ultrasound image using a probability edge map,
An image acquisition unit for acquiring an ultrasound original image for a target object in a plurality of frames;
A similarity determination unit for determining a similarity between the obtained plurality of frames;
An image matching unit for matching a plurality of frames of the ultrasound image determined to be similar;
An edge estimator for extracting a portion estimated as an edge from the plurality of ultrasound-matched images generated by the matching;
A probability edge map generator for generating a probability edge map for each of the extracted portions; And
And generating an edge map for applying the generated probability edge map to the ultrasound original image.
A computer program stored on a medium for executing the method of any one of claims 1 to 6 in combination with hardware.

Images