JP2019106202A - Health state evaluation support system and capillary vessel data acquisition method - Google Patents

Abstract

To provide a health state evaluation support system and capillary vessel data acquisition method capable of automatically recognizing and numeralizing a shape of a capillary vessel.SOLUTION: A health state evaluation support system 10 includes: image processing means 11 for processing an image obtained by photographing a capillary vessel and recognizing a shape of the capillary vessel in the image; and calculation means 12 for calculating a degree of abnormality of the capillary vessel from the recognized shape of the capillary vessel. The calculation means 12 calculates the degree of abnormality of the capillary vessel based on at least one of a number of capillary vessel bends, a number of intersections between arteries and veins, a number of branches, and a degree of bending.SELECTED DRAWING: Figure 1

Description

The present invention relates to a health condition evaluation support system based on the shape of a capillary and a data acquisition method of the capillary.

It has conventionally been known that the shape of capillary blood vessels such as the nail epithelium and the movement of blood flow are related to health. FIG. 2A schematically shows the capillary 20 of the nail epithelium. In the healthy state, the capillaries 20a are linear (see FIG. 2 (b)), but in the unhealthy state, the capillaries 20b tend to meander (see FIG. 2 (c)). Therefore, by observing the shape or the like of the capillary 20, it can be used for discovery, treatment, etc. of various diseases.

Under these circumstances, as a system for observing the shape of capillaries, etc., the density, thickness, shape (number of twisted or deformed blood vessels) and flow velocity of observed blood vessels are classified, analyzed and evaluated, and the results are There has been proposed a medical diagnosis support system which outputs as a comprehensive evaluation of the health condition (see Patent Document 1). However, in this medical diagnosis support system, the operator performs observation of the shape, thickness, and the like of the blood vessel, inputs this numerical value, and semiautomatically.

Patent No. 4743486

The present invention has been made in view of the above circumstances, and an object thereof is to provide a health evaluation support system and capillary data acquisition method for automatically recognizing the shape of a capillary and evaluating the state.

A health condition evaluation support system according to a first aspect of the invention, which meets the object, processes an image obtained by capturing a capillary, and recognizes an image processing unit that recognizes a shape of the capillary in the image, and the recognized capillary A calculation means for calculating the degree of abnormality of the capillary from the shape of the blood vessel is provided, wherein the calculation means includes the number of bends of the capillary, the number of crossings between arteries and veins, the number of branches, and the degree of curvature calculated by a specific equation. The degree of abnormality is calculated based on at least one of According to the health condition evaluation support system according to the first aspect, by providing the image processing means and the calculation means, the shape of the capillary is automatically recognized from the image in which the capillary is imaged, and the capillary recognized The degree of capillary abnormality can be calculated from the shape of the blood vessel.

In the health condition evaluation support system according to the first aspect of the present invention, the calculation means further includes a length, a thickness, a thickness ratio, a sharpness, a width, a flow velocity, an area, an aspect ratio, and a longitudinal length of the capillary. It is preferable to calculate at least one type of data to be selected. By doing this, multiple data including the degree of abnormality can be used for multilateral and comprehensive evaluations related to the health condition and the like.

In the health condition evaluation support system according to the first aspect of the invention, it is preferable to further include an output unit that outputs the calculated data as a radar chart. By doing this, it becomes easier for the evaluator (doctor etc.), the patient, etc. to visually carry out multilateral, comprehensive evaluation, judgment and the like.

In the health condition evaluation support system according to the first invention, preferably, the calculation means detects the amount of at least one of red blood cells and white blood cells of the capillary blood vessel from the density of the capillary blood vessel in the image. Based on the detected amount of at least one of red blood cells and white blood cells, it is possible to know the influence on human body by the administration, for example, the administration of an anticancer agent.

In the health condition evaluation support system according to the first aspect of the present invention, the capillary is preferably a capillary of a nail epithelium. Since the nail epithelium is thin and the side-by-side capillaries are seen through, image processing and calculation can be made relatively easy, and the calculation accuracy can be enhanced.

A data acquisition method of capillaries according to a second aspect of the invention, which meets the above object, includes an image processing step of processing an image obtained by imaging the capillaries and recognizing the shape of the capillaries in the image; There is a calculation step of calculating the degree of abnormality of the capillary from the shape of the capillary, wherein the degree of abnormality is calculated by the number of bends of the capillary, the number of crossings between arteries and veins, the number of branches, and a specific formula. It is calculated based on at least one of the degrees of bending. According to the capillary blood vessel data acquiring method according to the second aspect of the present invention, the shape of the capillary blood vessel can be automatically recognized, and the degree of abnormality of the capillary blood vessel can be calculated from the shape of the recognized capillary blood vessel.

According to the health condition evaluation support system according to the first invention and the capillary vessel data acquiring method according to the second invention, it is possible to automatically recognize the shape of the capillary and calculate the degree of abnormality of the capillary. . Therefore, in addition to the diagnosis such as grasping of the health condition, it can be used for evaluation of treatment, drinking such as supplement, use of health equipment, and the influence of applying cosmetics or plaster on the skin.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram which shows the health condition evaluation assistance system which concerns on the 1st Embodiment of this invention. (A) is a schematic view showing capillaries of the nail epithelium, (b) is a schematic view showing capillaries in a healthy state, and (c) is a schematic view showing capillaries in an unhealthy state. (A) is explanatory drawing explaining each data of a capillary, (b) is a radar chart as an output of each data. It is explanatory drawing of the method of searching for a blood-vessel area | region. (A), (b), (c) is a schematic diagram which shows the capillary in an unhealthy state, respectively.

Subsequently, an embodiment of the present invention will be described with reference to the attached drawings.
As shown in FIG. 1, the health condition evaluation support system 10 according to the first embodiment of the present invention includes an image processing unit 11, a calculation unit 12 and an output unit 13.

The image processing means 11 and the calculation means 12 can use a known computer 14. Specifically, the computer 14 includes a control unit including a CPU and the like, a ROM, a RAM, a hard disk, a keyboard, and the like. The computer 14 functions as an image processing means 11 by processing an image input based on a computer program stored in a ROM, a hard disk or the like, and functions as a calculation means 12 by calculating based on a computer program. Is configured as.

An image (see FIG. 3A) in which the capillary 20 is captured is input to the image processing means 11. The image processing means 11 processes this image and recognizes the shape of the capillary 20 in the image. The captured image may be a color image or a monochrome image. In addition, although a still image or a moving image may be used, it is preferable that the moving image is used when measuring the flow velocity. The imaging of the capillary 20 can be performed by a known blood flow observation device (for example, Bscan or the like manufactured by TOKU Co., Ltd.). There is no particular limitation on which region of the living body the capillary is to be imaged, but the capillary of the nail epithelium can be suitably imaged. The input of the image to the image processing means 11 may be input in real time by connecting the blood flow observation device or the like and the image processing means 11, or image data stored in a recording medium may be fetched.

Image processing (recognition of the shape of the capillary 20 in the image) by the image processing means 11 can be performed, for example, by the following procedure (algorithm).

(1) Gray scale conversion Gray scale conversion is processing for converting a color image into a monochrome image (gray scale image) of only lightness, when the image is a color.
(2) Binarization Binarization is a process of converting a grayscale image into a completely white or black binary image by eliminating the intermediate value (gray value). A binary image can be obtained, for example, by converting pixel values of a certain threshold or more into white pixels and converting pixel values below the threshold into black pixels. The threshold can be appropriately set by the scale bar.
(3) Noise processing Perform raster scan and labeling to process noise. The raster scan is a scan in which pixels are examined from the left end to the right starting from the upper left of the image, and when the right end is reached, the row is lowered by one and pixels are examined from the left end to the right. The labeling is a process of giving the same number (label) to each pixel having the same connected component. As processing for noise, if the labeled area (white pixel) is smaller than a certain area, it is erased, and if the area of the black pixel is smaller than a certain area, it is complemented (painted).
(4) Edge Detection Edge detection is a process of extracting an outline of an object captured as an image. The edge detection algorithm can use Kenny's edge detection algorithm.
(5) Feature point extraction With feature point extraction, the end points, intersections, and corners of lines (in this embodiment, capillaries 20) in an image are detected. The algorithm for feature point extraction can use Harris corner detection or the like.
(6) Reordering of Feature Points The extracted feature points are sorted, for example, in ascending order with respect to the x coordinate.
(7) Classification of feature points The feature points on the vein side and the artery side are classified. For this classification, it is possible to use a support vector machine which is one of two class classification classifiers.
(8) Rearrangement of Sorted Data The sorted feature points are sorted in ascending order, for example, with respect to the y-coordinate.
(9) Complementation processing A processing is performed to complement the adjacent feature points.

As an image processing method different from the above, a method (algorithm) for searching a blood vessel region can also be used. This method will be described with reference to FIG. The extraction starting point A is arranged at a point which is not less than a predetermined pixel value (for example, 0.8) and is at the image end, and the region of the blood vessel is estimated using the gray value of the image and sequentially searched. That is, a pixel D having the highest gradation value is searched in a fan-shaped range C of a predetermined central angle centered on the tip B (initially the start point) of the target blood vessel region, assuming that the pixel D is a blood vessel region It is a method of searching for a blood vessel region.

In the present embodiment, the image processing unit 11 has a function of specifying the position of the capillary 20 in the captured image based on data (for example, coordinates) manually input by the input device. This is effective when it is difficult to automatically specify the shape of the capillary 20 by image processing because the imaged capillary 20 is unclear or the like.
The computer 14 also stores the shape of the capillary 20 specified by the image processing means 11 in a storage medium. The computer 14 is provided with shape comparison means (not shown) including a computer program, and the shape comparison means acquires a plurality of data of the shape of the designated capillary 20 from the storage medium, and the same image taken on different days The shapes of the capillaries 20 are compared. By checking whether or not the shape of the capillary 20 has been improved after a predetermined period has elapsed, it is possible to know the effect of introducing a drug or a supplement.

The calculation means 12 calculates data on the degree of abnormality, length, thickness, thickness ratio, definition, width, flow velocity, area, aspect ratio, longitudinal length, etc. of the capillary 20 from the recognized shape of the capillary 20 (index Calculate). Hereinafter, description will be made with reference to FIG. 3 (a) as appropriate. Moreover, the arrow in FIG. 3 (a) shows the direction of the blood flow.

The degree of abnormality of the capillary 20 is one of the bending level of the capillary 20, the number of bends of the capillary 20, the number of branches of the capillary 20, and the number of arteries and veins of the capillary 20 crossing each other, or Calculated based on multiple combinations.
In the present embodiment, an integrated value of angle change θ per unit length of the capillary 20 (hereinafter, also referred to as “flexibility”) is adopted as the bending level of the capillary 20. The degree of bending can be calculated, for example, by the following equation from the coordinates of each feature point. The degree of tortuosity is related to the degree of stagnation of blood flow, and if the degree of tortuosity is large, hyperlipidemia, inflammation, abnormal growth of tissue, etc. may occur.

Here, the calculating means 12 may adopt the integrated value of the bending angle of the center line drawn in the middle of the artery and the vein of the capillary 20 as the bending level of the capillary 20 instead of the degree of bending. The centerline is drawn, for example, at a position where the distance between the centerline and the artery of the capillary 20 and the distance between the centerline and the vein of the capillary 20 are equal, and the bending angle of the centerline is It means angle change per unit length.

The number of bends of the capillary blood vessel is the number of times the capillary blood vessel is flexed (for example, the number of times the angle change is made per predetermined length or more per unit length), and the number of S-shaped capillary blood vessels 21 shown in FIG. In this case, the number of bends is two.
The number of branches of the capillary is 3 in the case of the capillary 22 shown in FIG. 5 (b), and the number of capillaries crossed is 1 in the case of the capillary 23 shown in FIG. 5 (c). In the case of a normal capillary, the number of branches is 1, ie, the unbranched state shown in FIG. 5 (a). When capillaries cross each other, as shown in FIG. 5 (c), in addition to the cross between the artery and the vein, if one region of the artery crosses the other region of the artery, the one region of the vein and the vein It includes the case where other regions intersect.
The degree of abnormality of the capillary 20 is, for example, K * (the number of bends of the capillary 20) + L * (the bend of the central line drawn between the artery and the vein of the capillary 20) using K, L, M, and P as coefficients. It can be calculated as an integrated value of the angle) + M * (the number of branches of the capillary 20) + P * (the number of crossings between the artery and the vein of the capillary 20).

The length and the area S of the capillary 20 serve as an index indicating the smoothness of the whole blood flow, but the area S can be expressed more sharply. The length can be obtained as an integrated value of the distance between feature points. Instead of the length, the longitudinal length (height) h may be used as the index. Here, as shown in FIG. 3A, the longitudinal length h means the length of the capillary 20 in the y-axis direction (direction along the finger), and the value of the longitudinal length h increases when the blood flow is improved. Tend.
The area S may be an area surrounded by a capillary and a line segment connecting both ends of the capillary, or may be the product of the width W and the longitudinal length h. The capillary 20 has a length of about 200 to 800 μm.

The thickness of the capillary 20 is related to the degree of arterial and venous stasis and venous stasis. The thickness of the capillary 20 can be measured, for example, in the arterial part, the venous part, and the tip part which is the boundary between them. The thickness ratio of the capillary 20 is the thickness R2 (R2 / R1) of the arterial portion relative to the thickness R1 of the venous portion, and is related to the degree of venous stasis.

The definition of the capillary 20 is related to the degree of accumulation and metabolism of fatigue substances. The sharpness can be determined, for example, as the difference between the brightness of the background area and the brightness of the blood vessel area.

The width W of the capillary 20 is related to the degree of hyperlipidemia. The width W is the maximum distance between the artery side and the vein side, and can be obtained as the maximum difference between x coordinate values in a constant y coordinate.

The flow velocity (velocity of blood flow) in the capillary 20 can be determined from the change in density and the moving object present in the blood vessel.
Here, the state in which the red blood cells, white blood cells, or plasma are flowing in the capillary 20 can be detected by changes in light and shade, so one of red blood cells, white blood cells and blood plasma based on the change in light and shade. Alternatively, a plurality of proportions may be derived so that the amount can be detected. When detecting a change in density, it is preferable that the image input to the image processing unit 11 is a moving image. Detecting the proportion and amount of specific blood components is effective in evaluating the health status, for example, by obtaining decreased levels of red blood cells and white blood cells by administration of an anticancer agent, the health status of the human body. Can be useful for the examination of
Then, depending on the reagent introduced into the body, the distribution of the reagent can be confirmed by the concentration change of the capillary 20, and the concentration of the capillary 20 can be determined by staining a specific cell (for example, cancer cell) with the reagent. From the change, it is also possible to detect the number and concentration of that particular cell.

The data (index) is not limited to the above-described index, and another index may be used, or an index obtained by combining the above-mentioned index by addition, subtraction, multiplication, etc. may be used. As a combined index, for example, an aspect ratio (= width W / longitudinal h), roundness (= area of circle with width W as diameter / inside area), etc. may be mentioned. The aspect ratio and the roundness should preferably be smaller.

The output unit 13 is a known monitor, printer or the like, and is connected to the computer 14 (image processing unit 11 and calculation unit 12). Various data calculated by the image processing unit 11 and the calculation unit 12 are output to the output unit 13. The data to be output can be selected appropriately as needed. The output form of the output means 13 includes a radar chart as well as a table. Specifically, for example, as shown in FIG. 3 (b), it can be displayed as a radar chart according to six items of abnormality degree, thickness ratio, sharpness, width, flow velocity and area. Two types of results are output in FIG. 3 (b). In addition, when making a bending degree into the item of a radar chart, a bending degree may be displayed as it is on a radar chart, and a bending degree may be represented as a straightness etc. as a reciprocal. Also, the degree of abnormality may not be displayed on the radar chart. In the radar chart, each item may be configured to define a normal range, a standard value, etc. from a document value, a sample value, etc., and output a standardized value.

The items (indexes) of the radar chart are not limited to the above six items, and the number of items is not limited to six items. In addition to or in place of the above six items, items such as portrait or the like or other combinations (e.g., aspect ratio) may be used. The radar chart may have six items, for example, and other items (longitudinal length, aspect ratio, etc.) may be output as additional items outside the radar chart. Any item may be used as an element of a radar chart, and may be used as an additional item other than an element of a radar chart. As a method of evaluation using the output data, comprehensive evaluation may be performed from the item of a radar chart, and simple evaluation using some indicators (for example, a combination indicator etc.) may be performed. The number and type of data (items) used for evaluation may be appropriately selected according to the purpose.
The calculation means 12 can also calculate capillary age based on the value of each item displayed as a radar chart. The calculation method may be performed by averaging the values of the items displayed on the radar chart, or calculating the sum after weighting the values of the items.

Next, as a second embodiment of the present invention, a data acquisition method of the capillary 20 using the health condition evaluation support system 10 will be described. In this data acquisition method, an image processing step of processing an image obtained by capturing the capillary 20 and recognizing the shape of the capillary 20 in the image, and the shape of the recognized capillary 20, the degree of abnormality of the capillary, In addition, it has a calculation step of calculating length, thickness, thickness ratio, sharpness, width, flow velocity, area, aspect ratio, longitudinal length and the like. In the health condition evaluation support system 10, the image processing process is performed by the image processing means 11 and the calculation process is performed by the calculation means 12. Each calculated data is output by the output means 13 in the form of a table or a radar chart.

The data on capillaries obtained in this way can be used as a reference for judgment by a doctor, as well as evaluations such as treatment, drinking supplements, use of health equipment, and the effects of applying cosmetics and pills on the skin, etc. It can be useful for In addition, each data can be observed at fixed points and changes over time can be examined.

The present invention is not limited to the above-described embodiment, and the configuration can be changed without departing from the scope of the present invention.

The health condition evaluation support system and capillary tube data acquisition method according to the present invention are, in addition to medical devices, evaluation devices for developing new drugs and supplements, health devices for measuring effects such as training, and the like in these applications It can be used as a data acquisition method.

10: health condition evaluation support system, 11: image processing means, 12: calculation means, 13: output means, 14: computer, 20, 20a, 20b, 21, 22, 23: capillaries, A: starting point, B: tip , C: sector, D: pixel

Claims (2)

Image processing means for processing an image in which a capillary is captured and recognizing the shape of the capillary in the image; and calculating means for calculating the degree of abnormality of the capillary from the shape of the recognized capillary Equipped
The health condition evaluation support system which calculates the degree of abnormality based on at least one of the number of bends of the capillary, the number of intersections between arteries and veins, the number of branches and the degree of curvature calculated by the following equation. .

Where x and y are coordinates of the end point, intersection point and corner of the capillary extracted from the image. An image processing step of processing an image in which a capillary is captured and recognizing the shape of the capillary in the image; and calculating the degree of abnormality of the capillary from the recognized shape of the capillary Have
The abnormality degree is a capillary blood vessel data acquisition method calculated based on at least one of the number of bends of the capillary blood vessel, the number of crossings between arteries and veins, the number of branches, and the degree of curvature calculated by the following equation.

Where x and y are coordinates of the end point, intersection point and corner of the capillary extracted from the image.

Images