KR102907156B1 - Image recognition system and method using baseline - Google Patents

Abstract

An image recognition system using a baseline is disclosed, and the image recognition system using a baseline according to one embodiment of the present invention may include an image acquisition unit that acquires an image of a genetic test result of a subject, an RGB conversion unit that converts each pixel constituting the image into an RGB value, a graph conversion unit that converts the RGB value of each converted pixel into a graph, a calculation unit that calculates a slope between the RGB value of a first pixel and the RGB value of a second pixel that serve as a reference, a baseline generation unit that generates a baseline by connecting the first pixel and the second pixel, and a determination unit that determines whether a probe exists based on the baseline.

Description

Image Recognition System and Method Using Baseline

The present invention relates to an image recognition system and method using a baseline.

Advances in medicine have significantly illuminated how genes function and their association with disease. This has made it possible to identify mutant genes and genetic mutations associated with specific diseases. Diagnostic testing for genetic mutations responsible for specific diseases is already being performed, and some genes can even predict the likelihood of developing future diseases. Predictive genetic testing can save countless lives through early detection and prevention, and the results have far-reaching implications not only for individuals but also for their relatives who share their genetic traits and society as a whole.

Genetic testing refers to the analysis of DNA, RNA, chromosomes, and metabolites for the purpose of identifying an individual or identifying the cause of a specific disease. Specifically, patients with symptoms of a genetic disease are primarily candidates for diagnostic testing. If a patient is diagnosed with a specific genetic disease through genetic testing, their parents, siblings, children, or fetuses may be selected for testing. Testing methods vary depending on the type and target, including carrier testing, diagnostic testing, newborn screening, predictive and prenatal testing, and prenatal testing.

Currently, genetic testing methods have been developed for many traditional genetic diseases, enabling prenatal, pre-symptomatic, and carrier diagnosis, and with the advancement of genetic technology, innovative treatments are also being developed.

However, the number of people seeking genetic testing is rapidly increasing, and the current limited equipment and personnel are facing many difficulties.

Accordingly, there is a need for an evaluation method that simultaneously evaluates a large amount of expression information from various genetic test images, while maintaining objectivity and reliability and taking a short time to diagnosis.

The technology underlying this application is disclosed in Korean Patent Publication No. 10-1985335.

The present invention aims to solve the problems of the prior art described above, and to provide an image recognition system and method using a baseline that automatically reads genetic test results quickly and accurately and provides results.

The present invention aims to solve the problems of the prior art described above, and to automatically read test results for various diseases and provide results on whether or not a person has genes related to the disease.

However, the technical tasks to be achieved by the embodiments of the present invention are not limited to the technical tasks described above, and other technical tasks may exist.

As a technical means for achieving the above-described technical task, an image recognition system using a baseline according to one embodiment of the present invention may include an image acquisition unit that acquires an image of a genetic test result of a subject, an RGB conversion unit that converts each pixel constituting the image into an RGB value, a graph conversion unit that converts the RGB value of each converted pixel into a graph, a calculation unit that calculates a slope between an RGB value of a first pixel and an RGB value of a second pixel that serve as a reference, a baseline generation unit that generates a baseline by connecting the first pixel and the second pixel, and a judgment unit that determines whether a probe exists based on the baseline.

Additionally, the calculation unit can calculate the absolute value of the slope by moving the second pixel from the first pixel to the right by one pixel.

Additionally, the calculation unit can calculate the slope of the next pixel when the slope of the second pixel is smaller than the threshold slope, and count the number of cases in which the slope of the second pixel is continuously larger than the threshold slope.

In addition, the baseline generation unit can generate a baseline by connecting the RGB value of the first pixel and the RGB value of the second pixel that is smaller than a predetermined threshold slope when the number of the counted second pixels is greater than or equal to the number of horizontal pixels of the probe.

Additionally, the judgment unit may move the baseline vertically upward on the graph by a predetermined number of pixels based on the smallest RGB value among the plurality of sections in which the probe is determined to exist.

Additionally, the judgment unit can determine that the probe exists if there are two points where the baseline moved vertically upwards of the graph and the graph intersect within a predetermined pixel range.

In addition, the image recognition system may further include a conversion unit that converts a portion corresponding to an area in which the judgment unit determines that the probe is present among the genetic test result images of the subject to 1, and the remaining portions to 0.

In addition, the judgment unit can compare the result of converting the genetic test result image of the subject and the genetic image of the specific disease in the conversion unit to determine whether the subject has the specific disease.

Meanwhile, a method for image recognition using a baseline performed by an image recognition system using a baseline may include a step of obtaining a genetic test result image of a subject, a step of converting each pixel constituting the image into an RGB value, a step of converting the RGB value of each converted pixel into a graph, a step of calculating a slope between an RGB value of a first pixel and an RGB value of a second pixel as a reference, a step of generating a baseline by connecting the first pixel and the second pixel, and a step of determining whether a probe exists based on the baseline.

The above-described problem-solving methods are merely exemplary and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, additional embodiments may be included in the drawings and detailed description of the invention.

According to the aforementioned means for solving the problem of this invention, by automatically recognizing and reading the genetic test results, it is more accurate than reading the test results with the human eye and has the effect of saving input time.

According to the aforementioned means for solving the problem of the present invention, it is possible to determine whether a person has a specific disease by comparing the result of a genetic test image with the result of converting a genetic image of a specific disease.

However, the effects that can be obtained from this center are not limited to the effects described above, and other effects may exist.

Figure 1 is a block diagram of an image recognition system using a baseline according to one embodiment of the present invention.
Figure 2 is a diagram exemplarily showing the results of a genetic test of a subject according to one embodiment of the present invention.
Figure 3 is a diagram showing a graph of values converted into RGB values for each pixel constituting an image according to one embodiment of the present invention.
Figure 4 is a schematic diagram illustrating a process of searching for a slope between the RGB values of a first pixel and a second pixel that serve as references.
Figure 5 is a drawing showing an example of a generated baseline according to one embodiment of the present invention.
FIG. 6 is a diagram exemplifying the result of moving the baseline vertically upwards of the graph by a predetermined number of pixels according to one embodiment of the present invention.
Figure 7 is a flowchart of an operation of an image recognition system using a baseline according to one embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention are described in detail to facilitate easy implementation by those skilled in the art. However, the present invention can be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, irrelevant parts have been omitted for clarity, and similar reference numerals have been used throughout the specification to indicate similar elements.

Throughout this specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" or "indirectly connected" with another element in between.

Throughout this specification, when it is said that a member is located “on,” “above,” “upper,” “lower,” “lower” or “lower” another member, this includes not only cases where the member is in contact with the other member, but also cases where another member exists between the two members.

Throughout this specification, whenever a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

The present invention relates to an image recognition system (10) using a baseline. More specifically, the present invention relates to an image recognition system (10) and method using a baseline that can provide accurate and rapid reading results by automatically reading genetic test result images for a specific disease.

The image disclosed in this invention is a genetic test result image that tests for the presence of 26 genes to test for a specific disease, and may be a reverse blot hybridization assay (REBA) image, i.e., a REBA image, but is not limited thereto.

Figure 1 is a block diagram of an image recognition system (10) using a baseline according to one embodiment of the present invention.

Referring to FIG. 1, an image recognition system (10) using a baseline according to one embodiment of the present invention may include an image acquisition unit (110), an RGB conversion unit (120), a graph conversion unit (130), a calculation unit (140), a baseline generation unit (150), and a judgment unit (160).

According to one embodiment of the present invention, the image acquisition unit (110) can acquire an image of the genetic test results of the subject.

Specifically, the image acquisition unit (110) can acquire an image of the result of testing whether a subject has a gene for a specific disease through a reverse blot hybridization assay (REBA).

Reverse hybridization (RHE) is a widely used method in clinical testing. It is a rapid, accurate, and highly sensitive molecular diagnostic method capable of detecting and identifying multiple pathogens and determining antibiotic susceptibility in a single experiment. Unlike DNA chips, RHE does not require expensive testing equipment, allows automated testing, and allows for simultaneous testing of multiple samples.

Additionally, the subject's genetic test result image (rebar image) acquired from the image acquisition unit (110) may include information on RGB values representing one color per pixel. For example, the format of the image data may include, but is not limited to, JPG, PNG, BMP, etc.

Figure 2 is a diagram exemplarily showing the results of a genetic test of a subject according to one embodiment of the present invention.

Referring to Figure 2, the genetic test results of the subject are expressed in bold on the image, i.e., the Leva image, if the subject has the gene corresponding to each gene number, and expressed faintly if the subject does not have the gene.

For example, if the atopic dermatitis genes are present on genes 2, 5, 10, and 16, the parts corresponding to genes 2, 5, 10, and 16 in the subject's genetic test result image will be expressed in bold.

According to one embodiment of the present invention, the RGB conversion unit (120) can convert each pixel constituting the genetic test result image of the target into an RGB value.

Specifically, the RGB conversion unit (120) can convert each pixel constituting the subject's genetic test result image into one of the color component values of R (Red), G (Green), and B (Blue), that is, an RGB value. A pixel is the most basic unit constituting a screen, and an image can be expressed as a collection of pixels. A pixel contains information on the corresponding color (red, green, blue, transparency, etc.) for each point, and representative formats include BMP, GIF, JPEG, and PNG. The subject's genetic test result image may be stored in the form of BMP, GIF, JPEG, and PNG, and the RGB conversion unit (120) may convert based on the RGB values contained in the pixels constituting the genetic test result image. At this time, methods of expressing color as RGB values include the CIE model, the RGB model, the HSV model, the YcrCb model, and the CMY model.

When expressing color using the RGB model, all colors are expressed as a mixing ratio of the three primary colors of light: red, green, and blue. In the RGB model, all colors are expressed with (R, G, B) coordinates, where R, G, and B are each 0 or more and 1 or less. For example, red is (1, 0, 0), green is (0, 1, 0), blue is (0, 0, 1), yellow is (1, 1, 0), cyan is (0, 1, 1), magenta is (1, 0, 1), black is (0, 0, 0), and white is (1, 1, 1). Here, R, G, and B represent the amount of red, green, and blue added, respectively. This RGB model is called an additive model because it creates new colors by adding base colors. The HSV model is the color model that most closely resembles how the human eye perceives color. Based on human intuitive vision, it expresses color using three attributes: hue, brightness (or value), and saturation.

Hue can be expressed as the angle at which the color is located on the color wheel, with red at 0 degrees, yellow at 60 degrees, green at 120 degrees, cyan at 180 degrees, blue at 240 degrees, and magenta at 300 degrees. The longer the wavelength of light, the closer the position on the color wheel is to 0 degrees. Saturation indicates how pure a color is. A color with a maximum hue of 1 is a fully saturated color, and a color with a minimum hue of 0 is a completely desaturated color. Although the RGB model and the HSV model each express colors by three distinct characteristics, any color can be expressed as a point on either the RGB color space or the HSV color space, so colors expressed by the HSV model and colors expressed by the RGB model can be converted to each other.

In addition, the RGB value conversion of the RGB conversion unit (120) according to one embodiment of the present invention can be performed by assigning an index number from 0 to 255 to each pixel constituting the image. Specifically, it can be done by assigning any one of 256 RBG color values corresponding to each pixel constituting the image.

According to one embodiment of the present invention, the graph conversion unit (130) can convert the RGB values of each converted pixel into a graph.

In this regard, FIG. 3 is a diagram showing a graph of values converted into RGB values for each pixel constituting an image according to one embodiment of the present invention.

Referring to FIG. 3, the graph conversion unit (130) can display the RGB values of each pixel converted by the RGB conversion unit (120) as a continuous graph on a two-dimensional coordinate system having an x-axis and a y-axis.

For example, the graph conversion unit (130) can select one of the RGB values of R (Red), G (Green), and B (Blue) from each pixel constituting the image, and convert it into a graph on a two-dimensional coordinate system based on changes in the selected RGB value.

In addition, the graph conversion unit (130) can count the number of sections in which the RGB value increases beyond a preset range, and select the RGB value with the largest number of counts among R (Red), G (Green), and B (Blue) to convert into a graph.

Specifically, the graph transformation unit (130) can more accurately detect the presence of a probe by selecting a color with a large number of pixels whose RGB values change rapidly. A probe is a single-length DNA signal that matches a portion of a disease gene, and here, the probe refers to a portion that is expressed in a strong color in a genetic test result image (rebar image).

According to one embodiment of the present invention, the calculation unit (140) can calculate the gradient between the RGB value of the first pixel as a reference and the RGB value of the second pixel.

In this regard, FIG. 4 is a diagram schematically illustrating a process of searching for a slope between the RGB values of the first pixel and the second pixel, which serve as references.

Referring to FIG. 4, the calculation unit (140) can set the first pixel as a reference, that is, the pixel just before the slope begins to change rapidly, as the first pixel as a reference, and sequentially calculate the slope between the RGB values of the next second pixel.

Additionally, the calculation unit (140) can calculate the absolute value of the slope by moving the second pixel from the first pixel to the right by one pixel.

Specifically, the calculation unit (140) may calculate the absolute value of the slope by moving the second pixel one pixel to the right from the first pixel, which is the reference.

In addition, the calculation unit (140) can calculate the slope of the next pixel when the slope of the second pixel is smaller than the critical slope, and count the number of cases in which the slope of the second pixel is continuously larger than the critical slope.

Specifically, the calculation unit (140) moves one pixel at a time and counts the number of cases in which the slope of the second pixel being calculated is greater than the critical slope, thereby calculating the range of the second pixel greater than the critical slope.

A baseline generation unit (150) according to one embodiment of the present invention can generate a baseline by connecting a first pixel and a second pixel.

In this regard, FIG. 5 is a drawing exemplarily showing a generated baseline according to one embodiment of the present invention.

Referring to FIG. 5, the baseline generation unit (150) can generate a baseline by connecting a first pixel that serves as a reference on the graph and a pixel having the smallest RGB value among a plurality of second pixels.

In addition, the baseline generation unit (150) can generate a baseline by connecting the RGB value of the first pixel and the RGB value of the second pixel that becomes smaller than the predetermined threshold slope when the number of cases in which the slope of the counted second pixel is continuously larger than the threshold slope is greater than or equal to the number of horizontal pixels of the probe.

According to one embodiment of the present invention, the judgment unit (160) can determine whether a probe exists based on a baseline.

Specifically, the judgment unit (160) can determine whether a probe exists based on the location where the graph and the baseline overlap. More specifically, the judgment unit (160) can determine that a probe exists if two points on the baseline overlapping the graph are less than a predetermined distance apart, and can determine that a section does not have a probe if the distance is greater than the predetermined distance apart.

Additionally, the judgment unit (160) can move the baseline vertically upward on the graph by a predetermined number of pixels based on the smallest RGB value among the sections in which the probe is judged to exist.

In this regard, FIG. 6 is a drawing exemplarily showing the result of moving the baseline vertically upwards of the graph by a predetermined number of pixels according to one embodiment of the present invention.

Referring to FIG. 6, the judgment unit (160) can move the generated baseline vertically upward on the graph by a pixel that overlaps two points in the section having the smallest RGB value among the sections where the probe is determined to exist, so as to overlap the section where the probe exists.

Additionally, the judgment unit (160) can determine that a probe exists if there are two points where the graph intersects the baseline moved vertically upwards within a predetermined pixel range.

Specifically, the judgment unit (160) can determine that a probe exists if two points on the baseline overlapping the graph are less than a predetermined distance apart, and can determine that a probe does not exist if the distance is greater than the predetermined distance apart.

According to one embodiment of the present invention, the conversion unit can convert a portion corresponding to an area in which a probe is determined to exist in the judgment unit (160) among the genetic test result images of the subject to 1, and the remaining portions to 0.

Specifically, the conversion unit can convert a portion corresponding to a gene number on the genetic test result image corresponding to a section where the judgment unit (160) determines that a gene exists to 1, and convert the remaining portions excluding the portion converted to 1 to 0.

According to one embodiment of the present invention, the judgment unit (160) can compare the result of converting the genetic test result image of the subject and the genetic image of a specific disease in the conversion unit to determine whether the subject has a specific disease.

Specifically, the judgment unit (160) can compare information about a specific disease stored in advance with the result of converting a genetic image of the specific disease, and determine whether or not the patient has the specific disease based on whether they match. Here, the information about a specific disease stored in advance is information stored by converting the genetic number causing the disease to 1 and storing it, and converting the remaining portion, excluding the converted portion, to 0.

In addition, the judgment unit (160) can determine the probability of developing the disease based on the ratio of the disease genetic information and the possessed genes expressed as a result of the test, that is, the ratio of the number of disease-causing gene numbers converted to 1 and the number of expressed gene numbers converted to 1 as a result of the genetic test.

In addition, the judgment unit (160) can set different weights depending on the genetic number that contributes to the onset of the disease, and can determine whether the disease has occurred based on the gender and age of the subject.

According to one embodiment of the present invention, an image recognition system (10) using a baseline may include a display unit (not shown) that provides a genetic test result image and a judgment result.

For example, the display unit (not shown) can output a table on the screen in which the presence or absence of a disease gene is converted into 0 and 1 for each gene number, which is the result of the judgment of the judgment unit (160).

Additionally, the display unit (not shown) can output an area corresponding to a gene number in which a gene is determined to exist in the image by darkening it so that the user can easily recognize it.

Below, we will briefly review the operating flow of the present invention based on the detailed description above.

Figure 7 is an operation flow diagram for an image recognition system (10) using a baseline according to one embodiment of the present invention.

The image recognition method using the baseline illustrated in FIG. 7 can be performed by the image recognition system (10) using the baseline described above. Therefore, even if the content is omitted below, the content described for the image recognition system (10) using the baseline can be equally applied to the description of the image recognition method using the baseline.

Referring to FIG. 7, in step S701, the image acquisition unit (110) can acquire an image of the genetic test results of the subject.

Next, in step S702, the RGB conversion unit (120) can convert each pixel constituting the image into an RGB value.

Next, in step S703, the graph conversion unit (130) can convert the RGB values of each converted pixel into a graph.

Next, in step S704, the calculation unit (140) can calculate the slope between the RGB value of the first pixel as a reference and the RGB value of the second pixel.

Next, in step S705, the baseline generation unit (150) can generate a baseline by connecting the first pixel and the second pixel.

Next, in step S706, the judgment unit (160) can determine whether a probe exists based on the baseline.

In the above description, steps S701 to S706 may be further divided into additional steps or combined into fewer steps, depending on the implementation example of the present invention. Furthermore, some steps may be omitted as needed, and the order of steps may be changed.

An image recognition system (10) and method using a baseline according to one embodiment of the present invention may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention or may be those known to and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The above hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

Additionally, the image recognition method using the aforementioned baseline can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

The above description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

10: Image recognition system using baselines
110: Image acquisition unit
120: RGB conversion unit
130: Graph transformation section
140: Accounting Department
150: Baseline generation unit
160: Judgment

Claims (10)

In an image recognition system using baseline,
An image acquisition unit that acquires an image of the subject's genetic test results;
An RGB conversion unit that converts each pixel constituting the image into an RGB value;
A graph conversion unit that converts the RGB values of each converted pixel into a graph;
A calculation unit that moves the pixels one by one on the graph and calculates the absolute value of the slope based on the difference in RGB values between the pixels, and sets the pixel just before the absolute value changes to a value greater than the critical slope as a first pixel, and the pixels whose absolute value is greater than the critical slope as a plurality of second pixels;
A baseline generation unit that generates a baseline by connecting the pixel with the smallest absolute value among the first pixel and the plurality of second pixels;
A judgment unit that determines whether a probe exists based on the above baseline;
An image recognition system comprising: delete In the first paragraph,
The above calculation section,
An image recognition system, wherein when the slope of the second pixel is less than the threshold slope, the slope of the next pixel is calculated, and the number of cases in which the slope of the second pixel is continuously greater than the threshold slope is counted. In the third paragraph,
The above baseline generation unit,
An image recognition system, wherein, when the number of the counted second pixels is greater than or equal to the number of horizontal pixels of the probe, a baseline is generated by connecting the RGB value of the first pixel and the RGB value of the second pixel that is smaller than a predetermined threshold slope. In paragraph 4,
The above judgment is,
An image recognition system that moves the baseline vertically upward on the graph by a predetermined number of pixels based on the smallest RGB value among a plurality of sections in which the probe is determined to exist. In paragraph 5,
The above judgment is,
An image recognition system that determines that the probe exists when there are two points where the baseline moved vertically upwards of the graph and the graph intersect within a predetermined pixel range. In paragraph 6,
The above image recognition system,
An image recognition system further comprising a conversion unit that converts a portion corresponding to an area determined by the judgment unit to be present in the genetic test result image of the subject to 1 and the remaining portion to 0. In paragraph 7,
The above judgment is,
An image recognition system that compares the result of converting the genetic test result image of the subject and the genetic image of a specific disease in the above conversion unit to determine whether the subject has the specific disease. In a method for image recognition using a baseline, performed by an image recognition system using a baseline,
A step of obtaining an image of the subject's genetic test results;
A step of converting each pixel constituting the image into an RGB value;
A step of converting the RGB values of each converted pixel into a graph;
A step of moving the pixels one by one on the graph, calculating the absolute value of the slope based on the difference in RGB values between the pixels, and setting the pixel just before the absolute value changes to a value greater than the critical slope as a first pixel, and the pixels whose absolute value is greater than the critical slope as a plurality of second pixels;
A step of generating a baseline by connecting the pixel having the smallest absolute value among the first pixel and the plurality of second pixels;
A step of determining whether a probe exists based on the above baseline;
An image recognition method comprising: A computer-readable recording medium having recorded thereon a program for executing the method of Article 9 on a computer.