JP2016190063A - Diagnostic system, image processing method in diagnostic system, and program therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a diagnostic system capable of facilitating diagnosis by a doctor, by displaying a diagnostic object portion in the emphasized state by using a photographed image of an affected part.SOLUTION: A diagnostic system 100 for diagnosing a lesion by using a photographed image of an affected part includes an image storage part 102 for storing the photographed image, and a processing part 101 for processing the photographed image stored in the image storage part 102. The processing part 101 includes separation means 101a for separating the photographed image into a luminance component and a color information component, and extraction means 101b for extracting a diagnostic object portion by the luminance component or the color information component of the photographed image in order to emphasize a characteristic of the portion.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a diagnostic apparatus, an image processing method in the diagnostic apparatus, and a program thereof.

  In general, visual inspection is always performed as a diagnosis of skin lesions, and a lot of information can be obtained. However, with the naked eye or loupe alone, for example, it is difficult to discriminate between moles and spots, and it is also difficult to distinguish benign tumors from malignant tumors. For this reason, dermoscopy diagnosis is conventionally performed in which a lesion is imaged using a camera with a dermoscope.

  A dermoscope is a non-invasive diagnostic instrument that illuminates a lesion with a halogen lamp or the like, sets it to a state without reflected light using an echo gel or a polarizing filter, and observes the magnified image about 10 times. The observation method using this instrument is called dermoscopy diagnosis. The dermoscopy diagnosis is described in detail in the Internet URL (http://www.twmu.ac.jp/DNH/department/dermatology/dermoscopy.html) <browse September 1, 2014>. According to this dermoscopy diagnosis, the pigment distribution from within the epidermis to the superficial dermis can be clearly seen by eliminating irregular reflection due to the keratin.

  For example, Patent Document 1 discloses a technique of a remote diagnosis system for a pigmentation site that performs diagnosis using skin tone images taken with the above-described dermoscope using values such as color tone, texture, asymmetry, and circularity. ing. According to the technique disclosed in Patent Document 1, a camera-equipped mobile phone with a dermoscope is used to photograph skin with benign pigmented nevus that is a concern for melanoma through the dermoscope. Then, the mobile phone is connected to the Internet using the network connection function, and the photographed skin image is transmitted to the remote diagnosis device to request diagnosis. Then, the remote diagnostic device that has received the skin image based on the request uses the melanoma diagnostic program to determine whether the melanoma is a melanoma from the skin image or what stage of the melanoma is. Diagnose and return the result to the requesting doctor.

JP-A-2005-192944

  By the way, although the diagnosis by dermoscope image mentioned above is spreading about dermatosis, it is often not possible to obtain a clear shape change or pattern, and the observation of the image and the determination of the lesion depend on the skill level of the doctor. is the current situation. Therefore, the emergence of tools that can be easily and accurately diagnosed by image processing, such as emphasizing a lesion part of a dermoscope image, has been expected.

  The present invention has been made to solve the above-described problems, and provides a diagnostic device, an image processing method in the diagnostic device, and a program thereof that facilitate diagnosis by a doctor and improve diagnostic accuracy. Objective.

  In order to solve the above-described problem, the present invention provides a diagnostic apparatus for diagnosing a lesion using a captured image of an affected area, the image storage unit storing the captured image, and the imaging stored in the image storage unit A processing unit for processing an image, wherein the processing unit separates the captured image into a luminance component and a color information component, and a part to be diagnosed is used to emphasize the likelihood of the part , And extracting the luminance component or the color information component of the photographed image.

  Further, the present invention is an image processing method in a diagnostic apparatus for diagnosing a lesion using a captured image of an affected area, the step of separating the captured image into a luminance component and a color information component, Extracting the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.

  Furthermore, the present invention is an image processing program in a diagnostic apparatus for diagnosing a lesion using a photographed image of an affected area, and a function for separating the photographed image stored in a computer into a luminance component and a color information component; And a function of extracting the target part of the target image using the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.

  According to the present invention, it is possible to provide a diagnostic apparatus, an image processing method in the diagnostic apparatus, and a program thereof that facilitate diagnosis of a doctor and improve diagnostic accuracy.

It is a block diagram which shows the structure of the diagnostic apparatus which concerns on embodiment of this invention. It is a flowchart which shows the basic processing operation | movement of the diagnostic apparatus which concerns on embodiment of this invention. It is a flowchart which shows the detail of the blood vessel likelihood extraction process operation | movement of FIG. It is a figure which shows an example of the display screen structure of the diagnostic apparatus which concerns on embodiment of this invention.

  DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as “embodiments”) will be described in detail with reference to the accompanying drawings. Note that the same number is assigned to the same element throughout the description of the embodiment.

(Configuration of the embodiment)
FIG. 1 is a block diagram illustrating a configuration of a diagnostic apparatus 100 according to the present embodiment. As shown in FIG. 1, an imaging device 110 with a dermoscope is connected to the diagnostic device 100 according to the present embodiment. The imaging device 110 with a dermoscope performs imaging of an affected area according to an instruction from the diagnostic device 100 (processing unit 101), stores the captured image (dermoscope image) in the image storage unit 102, and displays the image on the display device 120. Further, the captured image is subjected to enhancement processing by the processing unit 101, stored in the image storage unit 102, and displayed on the display device 120. The input device 130 performs an instruction to start capturing a dermoscope image, a part selection operation in the dermoscope image, which will be described later, and the like.

  The display device 120 is an LCD (Liquid Crystal Display) monitor, for example, and the input device 130 is an input device such as a mouse.

  The processing unit 101 processes a captured image of an affected part such as a dermoscopy image stored in the image storage unit 102. As shown in FIG. 1, the processing unit 101 includes a separating unit 101a, an extracting unit 101b, and a generating unit 101c. Including.

  The separating unit 101a functions as a unit that separates a captured image into a luminance component and a color information component. The extraction unit 101b functions as a unit that extracts a region to be diagnosed, such as a blood vessel-corresponding region, using a luminance component or a color information component of the captured image in order to emphasize the likelihood of the region.

  The generation unit 101c functions as a unit that re-synthesizes the extracted result of the above-described part with a background image. At this time, the background image is selected by the doctor operating the input device 130. The captured image, the gray-converted image of the captured image, the contrast-enhanced image of the captured image, and the luminance component of the captured image are converted into a global variation component and a local component. It is at least one of a group of luminance component enhanced images that are separated into variable components and subjected to different enhancements.

  The separation unit 101a, the extraction unit 101b, and the generation unit 101c described above each realize the above-described functions when the processing unit 101 sequentially reads and executes the program according to the present embodiment included in the processing unit 101. To do.

(Operation of the embodiment)
Hereinafter, the operation of the diagnostic apparatus 100 according to the present embodiment shown in FIG. 1 will be described in detail with reference to FIG.

  FIG. 2 shows a flow of basic processing operations of the diagnostic apparatus 100 according to the present embodiment. According to FIG. 2, the processing unit 101 first acquires a captured image of an affected part (skin lesion site) captured by the imaging device 110 with a dermoscope (step S <b> 11). The acquired captured image is stored in a predetermined area of the image storage unit 102 and displayed on the display device 120 (step S12).

  FIG. 4 shows an example of a display screen image displayed on the display device 120. A captured image display area 121 is assigned to the left and a blood vessel emphasized image display area 122 is assigned to the right, for example, and a captured image and an emphasized image are displayed in each area. When the doctor clicks the “start imaging” button 123 assigned to the lower right of the drawing using the input device 130, imaging of the affected area is started by the imaging device 110 with a dermoscope, and the processing unit 101 performs imaging. An image can be acquired and displayed in the captured image display area 121 of the display device 120.

  In the lower left of the screen, check boxes 124, 125, and 126 prepared for designating the display method (display form) of the blood vessel region are allocated, and when displayed highlighted in red on the captured image, When displaying a highlighted black image on a black and white photographed image, or displaying a blood vessel image, the doctor performs a selection operation (clicks) using the input device 130, so that the corresponding check boxes 124, 125, 126 are displayed. A check mark is added.

  The description returns to the flowchart of FIG. The processing unit 101 displays the acquired captured image in the captured image display region 121 of the display device 120, and then extracts a blood vessel region as the likelihood A from the captured image (step S13). Here, the blood vessel region has a value of “0” or “1” in the case of binary, and has a value in the range of 0 to 1 in the case of multiple values. Here, “0” represents a non-blood vessel region, “1” represents a blood vessel region, and processing for extracting this blood vessel region as the likelihood A will be described later.

  Next, the processing unit 101 acquires information regarding the display method (display form) designated by the doctor from the states of the check boxes 124, 125, and 126 on the display screen of the display device 120. When the doctor selects one of the desired check boxes 124, 125, and 126, the processing unit 101 emphasizes the blood vessel equivalent portion by the selected method (form) and displays the highlighted image on the display device 120. Display in area 122.

  Specifically, when the check box 124 is selected (step S14 “composite with captured image”), the processing unit 101 causes the generation unit 101c to display a blood vessel emphasized image in which a blood vessel region is drawn in red on the captured image IMG. E is generated (step S15). Here, the blood vessel emphasized image E is E = IMG. * (1-A) + Red * A. Here, IMG. Represents a captured image, Red represents red, * represents multiplication, and “. *” Represents multiplication for each element. Subsequently, the processing unit 101 displays the generated blood vessel emphasized image E side by side in the emphasized image display area 122 together with the captured image displayed in the captured image display area 121 of the display device 120 (step S16).

  On the other hand, when the check box 125 is selected (step S14 “composite with a gray image”), the processing unit 101 converts the captured image into a gray image by the generation unit 101c and then draws the blood vessel region in red. An enhanced image E is generated (step S17). Here, the blood vessel emphasized image E is E = Grey (IMG). * (1-A) + Red * A. Grey () represents conversion to a gray image. Subsequently, the processing unit 101 displays the generated blood vessel emphasized image E side by side in the emphasized image display area 122 together with the captured image displayed in the captured image display area 121 of the display device 120 (step S16).

  When the check box 126 is selected (step S14 “display blood image”), the processing unit 101 causes the generation unit 101c to draw a blood vessel portion in red and draw a non-blood vessel portion in black. An image is generated (step S18). Here, the blood vessel enhanced image E can be generated by E = Red * A. Although the blood vessel region is shown in red, it is arbitrary and is not limited to red. Subsequently, the processing unit 101 displays the generated blood vessel emphasized image E side by side in the emphasized image display area 122 together with the captured image displayed in the captured image display area 121 of the display device 120 (step S16).

  Here, the process of extracting the blood vessel region in step S13 as the likelihood A will be described in detail with reference to the flowchart of FIG. According to FIG. 3, in the processing unit 101, first, the separation unit 101 a converts a captured image in the RGB color space into a Lab color space (more precisely, CIE 1976 L * a * b color space). For the Lab color space, for example, an Internet URL (http://Ja.wikipedia.org/wiki/Lab%E8%89%B2%E7%A9%BA%E9%96%93)<September 2014 The details are described in <Browsing Date>.

Subsequently, in the processing unit 101, the extraction unit 101b uses the L image (luminance image) in the Lab color space acquired by the separation unit 101a, and acquires a Hessian matrix H for each pixel from the luminance image L ( Step S132). The Hessian matrix H has three elements for each pixel: a second-order derivative in the x direction, a second-order derivative in the y direction, and a second-order part in the xy direction. If each element is Hxx, Hxy, Hyy,
Hxx = s ^ 2 * (Dxx * L)
Hyy = s ^ 2 * (Dyy * L)
Hxy = s ^ 2 * (Dxy * L)
Indicated by

Here, * indicates convolution, and Dxx is a second derivative of the Gaussian kernel in the x direction.
Dxx = 1 / (2 * pi * σ ^ * 4) * ((X. ^ 2) / s ^ 2-1). * Exp (-(X. ^ 2 + Y. ^ 2) / (2 * s ^ 2) )).

  Here, s is a scale value corresponding to the thickness of the blood vessel to be detected. When blood vessels having a plurality of thicknesses are extracted, a blood vessel likelihood A described later is obtained for each blood vessel thickness, and the maximum value A may be selected for each pixel. pi represents the circumference, X and Y represent the positions in the kernel, “. *” represents the multiplication for each element of the matrix, and “. ^” represents the power for each element.

Dyy is a second-order derivative of the Gaussian kernel in the Y direction, and is given by transposing Dxx.
Dyy = Dxx '
Here, 'represents transposition.

Dxy is the first derivative of the Gaussian kernel in the x direction and the first derivative in the y direction.
Dxy = 1 / (2 * pi * σ ^ * 6) * (Y. * Y). * Exp (− (X. ^ 2 + Y. ^ 2) / (2 * s ^ 2)).

Hessian matrix H is
H = [Hxx Hxy; Hxy Hyy].

Next, the extraction unit 101b acquires eigenvalues λ1 and λ2 of the Hessian matrix H for each pixel (step S133). Since the Hessian matrix H is a real target matrix, the eigenvalues λ1 and λ2 are always real numbers and can be obtained as follows.
λ1 = 0.5 * (Dxx + Dyy + tmp)
λ2 = 0.5 * (Dxx; Dyy-tmp)
Here, tmp = sqrt ((Dxx-Dyy). * (Dxx-Dyy) + 4 * Dxy. * Dxy).

  Then, the extraction unit 101b extracts the blood vessel region A from the eigenvalues λ1 and λ2 obtained at step S133 according to the following formula (step S135). The blood vessel region A is represented by A = 1−exp ((K. ^ 2) / 2 * σ ^ 2)). However, K is a value posted as K = sqrt (λ1. * Λ1 + λ2. * Λ2) as shown in step S134. Here, σ is an adjustment coefficient, and sqrt () represents the square root for each element.

Note that when the blood vessel region is represented by binary values, the processing unit 101 may binarize using th1 as a threshold.
That is,
A = 0 if A <th1
A = 1 else

(Effect of embodiment)
As described above, according to the diagnostic apparatus 100 according to the present embodiment, the processing unit 101 includes the separation unit 101a that separates a captured image into a luminance component and a color information component, and the extraction unit 101b includes a blood vessel equivalent site, etc. The region to be diagnosed is extracted by the luminance component or the color information component of the captured image in order to emphasize the likelihood of the region, and the extracted result is displayed on the display device 120. For this reason, the doctor can easily and accurately make a diagnosis by visually recognizing the screen highlighted for the site to be diagnosed, and as a result, the diagnostic accuracy is improved.

  Further, according to the diagnostic apparatus 100 according to the present embodiment, the processing unit 101 causes the generation unit 101c to re-synthesize the result of the extracted part with the background image and display the result on the display device 120. At this time, as a background image, (1) a photographed image, (2) a gray converted image of the photographed image, (3) a contrast-enhanced image of the photographed image, and (4) a luminance component of the photographed image as a global variation component. By providing a UI (User Interface) that can be selected from a group of luminance component emphasized images that have been subjected to different emphasis after being separated into local variation components, it is possible to dynamically select a display form according to the diagnostic purpose. As a result, the doctor can perform diagnosis more easily and accurately, and the diagnosis accuracy is further improved.

  When a luminance component enhanced image obtained by separating the luminance component of the photographed image into a global variation component and a local variation component and performing different enhancement is selected, the separation unit 101a selects an L image corresponding to the luminance in the Lab color space. In order to separate the global variation component and the local variation component, edge preserving filter processing is performed. Here, for example, a bilateral filter is used as the edge preserving filter. Details of the bilateral filter are described in, for example, the Internet URL (http://en.wikipedia.org/wiki/Bilateralfilter) <browse September 1, 2014>.

  As mentioned above, although this invention was demonstrated using embodiment, it cannot be overemphasized that the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above-described embodiments and examples. Further, it is apparent from the description of the scope of claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

  The invention described in the scope of claims attached to the application of this application will be added below. The item numbers of the claims described in the appendix are as set forth in the claims attached to the application of this application.

[Appendix]
[Claim 1]
A diagnostic device for diagnosing a lesion using a photographed image of an affected area,
An image storage unit for storing the captured image;
A processing unit that processes the captured image stored in the image storage unit,
The processing unit is
Separating means for separating the captured image into a luminance component and a color information component;
A diagnostic apparatus, wherein a part to be diagnosed is extracted by the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.
[Claim 2]
The diagnostic apparatus according to claim 1, wherein the part is a blood vessel equivalent part.
[Claim 3]
The diagnostic apparatus according to claim 1, further comprising a generation unit configured to re-synthesize and generate the extracted result of the part with a background image.
[Claim 4]
The background image is subjected to different emphasis by separating the luminance component of the captured image, the gray-converted image of the captured image, the contrast-enhanced image of the captured image, and the luminance component of the captured image into a global variation component and a local variation component. The diagnostic apparatus according to claim 3, wherein the diagnostic apparatus is at least one selected from the group consisting of luminance component enhanced images.
[Claim 5]
An image processing method in a diagnostic apparatus for diagnosing a lesion using a photographed image of an affected area,
Separating the captured image into a luminance component and a color information component;
Extracting a region to be diagnosed from the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the region.
[Claim 6]
An image processing program in a diagnostic apparatus for diagnosing a lesion using a photographed image of an affected area,
On the computer,
A function of separating the stored photographed image into a luminance component and a color information component;
A program for executing a function of extracting a part to be diagnosed by the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.

  DESCRIPTION OF SYMBOLS 100 ... Diagnostic apparatus 101 ... Processing part 101a ... Separation means 101b ... Extraction means 101c ... Generation means 110 ... Imaging device with a dermoscope 120 ... Display device 121 ... Captured image 122 ... Enhanced image 123 ... Photography Start button, 124, 125, 126 ... check box, 130 ... input device

One aspect of the present invention is a diagnostic apparatus for diagnosing a lesion using a captured image of an affected area, and an image storage unit that stores the captured image, and a process that processes the captured image stored in the image storage unit A separation means for separating the photographed image into a luminance component and a color information component, and a region to be diagnosed to emphasize the likelihood of the portion of the photographed image. And an extraction unit that extracts the luminance component or the color information component.

Claims (6)

A diagnostic device for diagnosing a lesion using a photographed image of an affected area,
An image storage unit for storing the captured image;
A processing unit that processes the captured image stored in the image storage unit,
The processing unit is
Separating means for separating the captured image into a luminance component and a color information component;
A diagnostic apparatus, wherein a part to be diagnosed is extracted by the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.   The diagnostic apparatus according to claim 1, wherein the part is a blood vessel equivalent part.   The diagnostic apparatus according to claim 1, further comprising a generation unit configured to re-synthesize and generate the extracted result of the part with a background image.   The background image is subjected to different emphasis by separating the luminance component of the captured image, the gray-converted image of the captured image, the contrast-enhanced image of the captured image, and the luminance component of the captured image into a global variation component and a local variation component. The diagnostic apparatus according to claim 3, wherein the diagnostic apparatus is at least one selected from the group consisting of luminance component enhanced images. An image processing method in a diagnostic apparatus for diagnosing a lesion using a photographed image of an affected area,
Separating the captured image into a luminance component and a color information component;
Extracting a region to be diagnosed from the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the region. An image processing program in a diagnostic apparatus for diagnosing a lesion using a photographed image of an affected area,
On the computer,
A function of separating the stored photographed image into a luminance component and a color information component;
A program for executing a function of extracting a part to be diagnosed by the luminance component or the color information component of the photographed image in order to emphasize the likelihood of the part.

Images