JP7610342B2 - Endoscope System - Google Patents

Description

The present invention relates to an endoscope system.

In the medical field, endoscope systems that capture images of objects inside a living body are widely used. An endoscope system includes an endoscope that is inserted into a living body, captures images of the object, and outputs image signals, and an endoscope processor (hereinafter referred to as the processor) that generates an observation image of the object based on the image signal and outputs the image to a monitor.

In diagnosis using observation images, the severity or progression of a disease (stage or disease phase, etc.) may be determined. The severity of a disease is an index showing the extent of the disease, and the progression of a disease is an index showing the progression of the disease. Standards for these indices are set for each disease or perspective, etc.

As an example of the severity of a disease related to diagnosis using an observation image, there is the Mayo Score, which is one of the endoscopic indices for ulcerative colitis. In the Mayo Score, the disease is judged as mild (grade 0 or 1), moderate (grade 2), or severe (grade 3) based on the presence or absence and the degree of disease characteristics, etc., based on the findings of the affected area in the large intestine using an endoscope. In addition, as an example of the progression of a disease related to diagnosis using an observation image, there is the stage of gastric cancer. The stage of gastric cancer is classified into stages I to IV by comprehensively determining the depth of the tumor and the state of metastasis through observation of the lesion and biopsy, etc. The severity or progression of a disease is an important factor in determining a treatment plan, etc. In particular, for ulcerative colitis, etc., where medical treatment according to the severity is the main focus, accurate diagnosis at the early stage of onset is important, so it is beneficial to determine the severity with high accuracy by endoscopic examination.

Some endoscope systems have a normal mode in which an observation site inside a living body is irradiated with normal white light to observe the overall characteristics of the surface of biological tissue, and a special mode in which special light is irradiated onto the observation site. In the special mode, special light, for example light with a narrow band of limited wavelengths, is irradiated onto the affected area, making it possible to capture disease characteristics such as unique blood vessel shapes or mucosal irregularities that cannot be seen with normal white light.

Depending on the circumstances, this special mode allows detailed observation of the condition of the affected area or the characteristics of the disease that are the basis for determining the severity or progression of the disease. Therefore, the special mode can provide a more accurate determination of the severity or progression than the normal mode in which observation is performed under normal light. High accuracy specifically means that there is a high rate of agreement between the actual severity or progression of the affected area and the severity or progression determined by endoscopic examination.

As an example of using a special mode, an image processing device is disclosed that uses a normal mode and a special mode to obtain fluorescent images with less blurring, thereby analyzing the progression of a disease (Patent Document 1). Also, an endoscope system is disclosed that, in a special mode, displays information based on a disease condition score related to oxygen saturation on the display unit, thereby enabling more accurate and detailed diagnosis (Patent Document 2).

International Publication No. 2017/175452 JP 2015-085152 A

In endoscopic examinations, the normal mode, which allows images to be viewed in natural colors, is usually used, and the special mode described above is often used for areas where the doctor wants to pay particular attention. However, in this case, the special mode is not switched to unless the doctor intends it to. As a result, even if an observation area is one in which disease characteristics can be captured when observed in special mode, the disease characteristics cannot be captured when observed in normal mode, and a problem occurs in which there are areas where the accuracy of determining the severity or progression is low when a diagnosis is made only in normal mode.

The present invention aims to provide an endoscopy system that can determine the severity or progression of a disease with high accuracy during endoscopic examination.

The endoscope system of the present invention includes a light source unit that emits first illumination light and second illumination light having different emission spectra, an image signal acquisition unit that images an object to be observed illuminated with the first illumination light to acquire a first image signal, and an image of the object to be observed illuminated with the second illumination light to acquire a second image signal, a feature calculation unit that calculates a first feature based on the first image signal and calculates a second feature based on the second image signal, a disease condition score calculation unit that calculates a first disease condition score representing a disease condition of the object to be observed based on the first image signal and calculates a second disease condition score representing a disease condition of the object to be observed based on the second image signal, and a disease condition ratio calculation unit that compares the first feature amount with the second feature amount or compares the first disease condition score with the second disease condition score. The display control unit includes a comparison unit, a display processing unit that generates a high score display image using the second image signal when the second feature is greater than the first feature or when the second condition score is greater than the first condition score, a display control unit that controls the display of a first image based on the first image signal on the monitor, and when a high score display image is generated, controls the display of the high score display image on the monitor in place of the first image, or controls the display of both the first image and the high score display image on the monitor, and a comparison target selection unit that specifies whether the first feature and the second feature, or the first condition score and the second condition score, are to be used as targets for comparison by the condition comparison unit.
The endoscope system of the present invention further includes a light source unit that emits first illumination light and second illumination light having different emission spectra, an image signal acquisition unit that images an object being observed illuminated with the first illumination light to acquire a first image signal, and an image of the object being observed illuminated with the second illumination light to acquire a second image signal, a feature calculation unit that calculates a first feature based on the first image signal and a second feature based on the second image signal, a disease condition score calculation unit that calculates a first disease condition score representing a disease condition of the object being observed from the first feature calculated based on the first image signal and a second disease condition score representing a disease condition of the object being observed from the second feature calculated based on the second image signal, a disease condition comparison unit that compares the first feature value with the second feature value or compares the first disease condition score with the second disease condition score, and a disease condition comparison unit that compares the second feature value with the first feature value. the display control unit controls the monitor to display a first image based on the first image signal on the monitor and to hide a second image based on the second image signal on the monitor when the high score display image has been generated , switching from the first image to display the high score display image on the monitor, or controls the monitor to display both the first image and the high score display image, wherein the high score display image is a second image based on the second image signal, a first emphasized image generated by processing the first image signal with the second image signal, or a second emphasized image generated by processing the second image signal with the second image signal .

It is preferable that the first illumination light is white light and the second illumination light is special light.

It is preferable that the disease condition comparison unit includes a comparison object selection unit that specifies whether to use the first feature amount and the second feature amount, or the first disease condition score and the second disease condition score, as the object to be compared.

The first and second condition scores preferably include a disease severity or disease progression.

It is preferable that the first feature and the second feature include values based on blood vessels, ducts, or mucosa.

It is preferable that the display control unit notifies the user of the presence of a high score display image prior to displaying the high score display image.

The notification should preferably be a warning display.

It is preferable that the device is provided with a notification unit that generates sound, light or vibration, and the notification is generated by the notification unit in the form of sound, light or vibration.

It is preferable that the device includes an instruction unit that receives an instruction to display the high score display image, and that the display control unit, after receiving the notification, displays the high score display image in accordance with the instruction from the instruction unit.

When the display control unit controls so that both the first image and the high score display image are displayed on the monitor, it is preferable that the first image based on the first image signal is displayed in a display area larger than the high score display image.

When the display control unit controls so that both the first image and the high score display image are displayed on the monitor, it is preferable that the first image based on the first image signal is displayed in a display area smaller than the high score display image.

When the display control unit controls the display of a second image based on the second image signal on the monitor , it is preferable that when a high score display image is generated , the display control unit controls the display of the second image based on the second signal to continue.

The endoscope system of the present invention can accurately determine the severity or progression of a disease during endoscopic examination.

FIG. 1 is an external view of an endoscope system. 2 is a block diagram showing the functions of the endoscope system. FIG. 1 is a graph showing the spectrum of normal light. 1 is a graph showing the spectrum of normal light. 1 is a graph showing the spectrum of special light. FIG. 2 is a block diagram showing the functions of an image processing unit. 4 is a block diagram showing functions of a determination mode processing unit; FIG. FIG. 2 is a block diagram showing functions of a feature amount calculation unit. FIG. 2 is a block diagram showing the functions of a disease condition score calculation unit. 3 is a block diagram showing functions of a display processing unit. FIG. FIG. 13 is an explanatory diagram showing the relationship between an image, a feature amount, and a disease condition score. FIG. 13 is an explanatory diagram showing the relationship between an image, a feature amount, and a disease condition score. FIG. 11 is an explanatory diagram showing the relationship between an acquired image and a display image. FIG. 11 is an explanatory diagram showing the relationship between an acquired image and a display image. FIG. 11 is an explanatory diagram showing the relationship between an acquired image and a display image. FIG. 2 is an explanatory diagram of an image displayed on a monitor. FIG. 2 is an explanatory diagram of an image displayed on a monitor. FIG. 2 is an explanatory diagram of an image displayed on a monitor. FIG. 2 is an explanatory diagram of an image displayed on a monitor. FIG. 2 is an explanatory diagram of an image displayed on a monitor. FIG. 11 is a flowchart showing a processing procedure in a determination mode.

As shown in FIG. 1, the endoscope system 10 includes an endoscope 12, a light source device 14, a processor device 16, a monitor 18, and a user interface 19. The endoscope 12 irradiates an observation target inside a living body with illumination light, captures an image of the observation target illuminated with the illumination light, and outputs an image signal. The light source device 14 supplies the endoscope 12 with illumination light to be irradiated onto the observation target. The processor device 16 generates an observation image of the observation target based on the image signal, and performs system control and image processing of the endoscope system 10. The monitor 18 is a display unit that displays the image output from the processor device 16. The user interface 19 is an input device for inputting settings to the processor device 16, etc., and is composed of a keyboard KB, a mouse MS, etc. The processor device 16 is electrically connected to the monitor 18 and the user interface 19.

The endoscope 12 has an insertion section 12a to be inserted into the subject, an operating section 12b provided at the base end of the insertion section 12a, a bending section 12c provided at the tip side of the insertion section 12a, and a tip section 12d. The bending section 12c is bent by operating the angle knob 13a of the operating section 12b. The bending section 12c is bent so that the tip section 12d faces the desired direction. The tip section 12d is provided with an injection port (not shown) for injecting air, water, etc. toward the object of observation.

In addition to the angle knob 13a, the operation unit 12b also includes a mode switching unit 13b used to switch between observation modes, a display instruction unit 13c that is an instruction unit that accepts instructions for the image to be displayed on the monitor 18, a scope switch 13e that performs various other selections or instructions, and a zoom operation unit 13d.

By pressing the mode switching unit 13b, the endoscope system 10 switches between the normal mode, the special mode, and the judgment mode in sequence. When the observation mode is the normal mode, normal light is emitted by combining multiple colors of light at a light intensity ratio Lc for the normal mode, and a normal image obtained by capturing an image of an observation target illuminated with this normal light is displayed on the monitor 18. When the observation mode is the special mode, special light is emitted by combining multiple colors of light at a light intensity ratio Ls for the special mode, and a special image obtained by capturing an image of an observation target illuminated with this special light is displayed on the monitor 18. Since the light intensity ratio Lc and the light intensity ratio Ls are different, the normal light and the special light have different emission spectra. The image displayed on the monitor 18 can be set as appropriate.

When the observation mode is the judgment mode, normal light and special light are alternately emitted. Then, a normal image is obtained by capturing an image of the observation target illuminated with normal light, and a special image is obtained by capturing an image of the observation target illuminated with special light. In the judgment mode, the normal image is displayed on the monitor 18 first. The endoscope system 10 also controls the image displayed on the monitor 18 based on the respective feature amounts or disease condition scores calculated based on the normal image and the special image. The feature amounts are quantified or classified so that specific image features of the image signal can be compared. The disease condition score is an index indicating the disease condition of the observation target, and includes the severity or progression of the disease.

By operating the display instruction unit 13c, it is possible to give instructions such as switching the image displayed on the monitor 18. By operating the zoom operation unit 13d, it is possible to enlarge or reduce the observation target and capture an image. In addition, a forceps channel (not shown) for inserting treatment tools and the like is provided from the insertion section 12a to the tip section 12d. Treatment tools are inserted into the forceps channel from the forceps inlet 12e. The endoscope 12 is optically connected to the light source device 14 and electrically connected to the processor device 16.

As shown in FIG. 2, the light source device 14 includes a light source unit 20 that emits illumination light used to illuminate the object of observation, and a light source control unit 22 that controls the light source unit 20. The light source unit 20 is a semiconductor light source of LEDs (Light Emitting Diodes) of multiple colors. The light source control unit 22 controls the amount of illumination light emitted by turning the LEDs on and off and adjusting the drive current and drive voltage of the LEDs.

The light source unit 20 has four color LEDs: a V-LED (Violet Light Emitting Diode) 20a, a B-LED (Blue Light Emitting Diode) 20b, a G-LED (Green Light Emitting Diode) 20c, and an R-LED (Red Light Emitting Diode) 20d, and a wavelength cut filter 23.

As shown in FIG. 3, the V-LED 20a emits violet light V in the wavelength band of 380 nm to 420 nm. The B-LED 20b emits blue light B in the wavelength band of 420 nm to 500 nm. At least the wavelength longer than the peak wavelength of 450 nm of the blue light B emitted from the B-LED 23b is cut by the wavelength cut filter 23. As a result, the blue light Bx after passing through the wavelength cut filter 23 has a wavelength range of 420 to 460 nm. The reason why light in the wavelength range longer than 460 nm is cut in this way is because light in this wavelength range longer than 460 nm reduces the vascular contrast of the blood vessels being observed. Note that instead of cutting light in the wavelength range longer than 460 nm, the wavelength cut filter 23 may attenuate light in the wavelength range longer than 460 nm.

The G-LED 20c emits green light G with a wavelength band ranging from 480 nm to 600 nm. The R-LED 20d emits red light R with a wavelength band ranging from 600 nm to 650 nm. The light emitted from each of the LEDs 20a to 20d may have the same center wavelength and peak wavelength, or they may be different.

The light source control unit 22 independently controls the on/off and light emission amount of each LED 20a-20d, thereby adjusting the timing of light emission, light emission period, light amount, and spectrum of the illumination light. The control of on/off by the light source control unit 22 differs for each observation mode. The reference brightness can be set by the user interface 19, etc.

In the normal mode, the light source control unit 22 lights up all of the V-LED 20a, B-LED 20b, G-LED 20c, and R-LED 20d. At that time, as shown in FIG. 4, the light amount ratio Lc between the purple light V, the blue light Bx, the green light G, and the red light R is set so that the peak of the light intensity of the blue light Bx is greater than the peak of the light intensity of any of the purple light V, the green light G, and the red light R. As a result, in the normal mode, the light source device 14 emits multi-color light for the normal mode, including the purple light V, the blue light Bx, the green light G, and the red light R, as normal light. The normal light has a certain level of intensity from the blue band to the red band, so it is a white light that is almost white. Note that the white light includes not only broadband light that includes all of the wavelength bands of the blue component, the green component, and the red component, such as the white light emitted by a xenon lamp, but also illumination light that is a mixture of light of at least three wavelength bands of the blue component, the green component, and the red component.

In the special mode, the light source control unit 22 turns on all of the V-LED 20a, B-LED 20b, G-LED 20c, and R-LED 20d. At that time, as shown in FIG. 5, the light amount ratio Ls between the purple light V, the blue light Bx, the green light G, and the red light R is set so that the peak of the light intensity of the purple light V is greater than the peak of the light intensity of any of the blue light Bx, the green light G, and the red light R. As a result, in the special mode, the light source device 14 emits multi-color light for the special mode, including the purple light V, the blue light Bx, the green light G, and the red light R, as special light. The special light is bluish light because the proportion of the purple light V is large. Note that the special light does not need to include all four colors of light, and it is sufficient that the special light includes light from at least one of the four LEDs 20a to 20d. Note that light intensity is the density of the light flux within a unit solid angle, and light quantity is a value that evaluates the radiant energy of light based on human sensation (visibility).

In the judgment mode, the light source control unit 22 controls the V-LED 20a, B-LED 20b, G-LED 20c, and R-LED 20d so that normal light and special light are alternately emitted every frame. That is, the light source control unit 22 turns on all of the V-LED 20a, B-LED 20b, G-LED 20c, and R-LED 20d, and controls the light amount ratio Lc and light amount ratio Ls between the purple light V, blue light Bx, green light G, and red light R to be alternately switched every frame. The number of frames per second (number of still images) is, for example, 60 fps (Frame per second). Therefore, in the judgment mode, the light source control unit 22 controls so that normal light and special light are alternately switched every 1/60 seconds. As described above, the light source unit 20 emits normal light (white light (first illumination light)) and special light (second illumination light) that have different emission spectra.

As shown in FIG. 2, the illumination light emitted by the light source unit 20 enters the light guide 41. The light guide 41 is built into the endoscope 12 and the universal cord (not shown), and transmits the illumination light to the tip 12d of the endoscope 12. The universal cord is a cord that connects the endoscope 12 to the light source device 14 and the processor device 16. Note that a multimode fiber can be used as the light guide 41. As an example, a thin-diameter fiber cable with a core diameter of 105 μm, a cladding diameter of 125 μm, and a diameter of φ0.3 to 0.5 mm including the protective layer that serves as the outer shell can be used.

The tip 12d of the endoscope 12 is provided with an illumination optical system 30a and an imaging optical system 30b. The illumination optical system 30a has an illumination lens 45, through which illumination light is emitted toward the observation object. The imaging optical system 30b has an objective lens 46, a zoom lens 47, and an image sensor 48. The image sensor 48 captures an image of the observation object using reflected light of the illumination light returning from the observation object via the objective lens 46 and the zoom lens 47 (including reflected light, scattered light, fluorescence emitted by the observation object, or fluorescence caused by a drug administered to the observation object, etc.).

The zoom lens 47 moves by operating the zoom operation unit 13d, and enlarges or reduces the observation object imaged using the image sensor 48.

The image sensor 48 is, for example, a color sensor having a primary color filter, and includes three types of pixels: B pixels (blue pixels) having a blue color filter, G pixels (green pixels) having a green color filter, and R pixels (red pixels) having a red color filter. The blue color filter transmits mainly purple to blue light. The green color filter transmits mainly green light. The red color filter transmits mainly red light. When an object to be observed is captured using the primary color image sensor 48 as described above, up to three types of images can be simultaneously obtained: a B image (blue image) obtained from the B pixels, a G image (green image) obtained from the G pixels, and an R image (red image) obtained from the R pixels.

As the image sensor 48, a CCD (Charge Coupled Device) sensor or a CMOS (Complementary Metal Oxide Semiconductor) sensor can be used. Although the image sensor 48 in this embodiment is a primary color sensor, a complementary color sensor can also be used. A complementary color sensor has, for example, a cyan pixel with a cyan color filter, a magenta pixel with a magenta color filter, a yellow pixel with a yellow color filter, and a green pixel with a green color filter. When a complementary color sensor is used, the images obtained from the pixels of each color can be converted into B, G, and R images by performing complementary color-primary color conversion. Also, instead of a color sensor, a monochrome sensor without a color filter can be used as the image sensor 48. In this case, the image of each color can be obtained by sequentially capturing an image of the observation target using illumination light of each color such as BGR.

The processor device 16 has a central control unit 52, an image signal acquisition unit 54, an image processing unit 61, and a display control unit 62. The central control unit 52 performs overall control of the endoscope system 10, such as controlling the synchronization of the illumination light irradiation timing and the imaging timing by controlling the light source control unit 22 and the image sensor 48. In the normal mode, normal light is emitted as the illumination light and a normal image signal is input to the image signal acquisition unit 54. In the special mode, special light is emitted as the illumination light and a special image signal is input to the image signal acquisition unit 54. In the judgment mode, a normal image signal that captures an object illuminated with normal light as the illumination light is input to the image signal acquisition unit 54, and an image of an object illuminated with special light as the illumination light is input to the image signal acquisition unit 54, switching between these for each frame. In addition, when various settings are input using the endoscope 12 or the user interface 19, the central control unit 52 inputs the various settings to each part of the endoscope system 10, such as the light source control unit 22, the image sensor 48, or the image processing unit 61.

The image signal acquisition unit 54 acquires an image signal of an object to be observed from the image sensor 48. Specifically, under the control of the central control unit 52, a normal image signal is acquired by imaging an object to be observed under normal light illumination, and a special image signal is acquired by imaging an object to be observed under special light illumination. Acquisition of the normal image signal and the special image signal is switched every frame. The image signal acquisition unit 54 has a DSP (Digital Signal Processor) 56, a noise reduction unit 58, and a conversion unit 59, and uses these to perform various processes on the acquired image signal as necessary. The DSP 56 performs various processes on the acquired image signal as necessary, such as defect correction, offset processing, gain correction, linear matrix processing, gamma conversion, demosaic processing, and YC conversion processing.

The defect correction process corrects the pixel values of pixels that correspond to defective pixels of the image sensor 48. The offset process reduces dark current components from the image signal that has been subjected to the defect correction process and sets an accurate zero level. The gain correction process adjusts the signal level of each image by multiplying the offset-processed image signal by a gain. The linear matrix process improves the color reproducibility of the offset-processed image signal, and the gamma conversion process adjusts the brightness and saturation of the image signal after linear matrix processing.

When the image sensor 48 is a color sensor, demosaic processing is performed. Demosaic processing (also called isotropic processing or simultaneous processing) is a process for interpolating pixel values of missing pixels, and is performed on the image signal after gamma conversion processing. Missing pixels are pixels that have no pixel value due to the arrangement of color filters (because pixels of other colors are arranged in the image sensor 48). For example, since the B image is an image obtained by capturing an observation target at the B pixel, the pixels at the positions corresponding to the G pixel and R pixel have no pixel value. The demosaic processing interpolates the B image to generate pixel values of the pixels at the positions of the G pixel and R pixel of the image sensor 48. The YC conversion processing is a process for converting the image after demosaic processing into the luminance channel Y and the color difference channel Cb and color difference channel Cr.

The noise reduction unit 58 performs noise reduction processing on the luminance channel Y, the chrominance channel Cb, and the chrominance channel Cr using, for example, a moving average method or a median filter method. The conversion unit 59 reconverts the luminance channel Y, the chrominance channel Cb, and the chrominance channel Cr after noise reduction processing back into image signals for each color of BGR.

As shown in FIG. 6, the image processing unit 61 includes a normal mode processing unit 63, a special mode processing unit 64, and a judgment mode processing unit 65. The normal mode processing unit 63 operates when the normal mode is set, and performs color conversion processing, color enhancement processing, and structure enhancement processing on the received normal image signal. In the color conversion processing, color conversion processing is performed on the RGB image using 3x3 matrix processing, tone conversion processing, and three-dimensional LUT (Look Up Table) processing, etc.

Color emphasis processing is performed on RGB image signals that have already been color converted. Structure emphasis processing is processing that emphasizes the structure of the object being observed, and is performed on the RGB image signals after color emphasis processing. By performing various image processing such as those described above, a normal image is obtained. The normal image is an image with natural coloring because it is an image obtained based on normal light that is emitted in a well-balanced manner, consisting of purple light V, blue light Bx, green light G, and red light R. The normal image is input to the display control unit 62.

The special mode processing unit 64 operates when the special mode is set. The special mode processing unit 64 performs color conversion processing, color enhancement processing, and structure enhancement processing on the received special image signal. The color conversion processing, color enhancement processing, and structure enhancement processing are the same as those of the normal mode processing unit 63. A special image is obtained by performing various image processing as described above. The special image is an image obtained based on special light in which the purple light V, which has a high absorption coefficient of hemoglobin in blood vessels, emits a greater amount of light than the other colors of blue light Bx, green light G, and red light R, so that the resolution of the vascular structure and glandular duct structure is higher than other structures. The special image is input to the display control unit 62.

As shown in FIG. 7, the judgment mode processing unit 65 includes a feature amount calculation unit 70, a disease condition score calculation unit 71, a comparison target selection unit 72, a disease condition comparison unit 73, and a display processing unit 74. The judgment mode processing unit 65 operates when the judgment mode is set.

The feature calculation unit 70 performs a feature calculation function of calculating feature amounts (first feature amount and second feature amount) based on a normal image signal (first image signal) and a special image signal (second image signal). The disease condition score calculation unit 71 calculates a disease condition score (first disease condition score and second disease condition score) representing the disease condition of the observation subject from the feature amounts calculated based on the normal image signal and the special image signal, respectively. The comparison subject selection unit 72 selects and specifies whether the feature amount or the disease condition score is to be used as the subject for comparison by the disease condition comparison unit 73.

The disease condition comparison unit 73 compares the feature amount of the normal image signal with the feature amount of the special image signal, or the disease condition score of the normal image signal with the disease condition score of the special image signal, according to instructions from the comparison target selection unit 72. If the result of the comparison by the disease condition comparison unit 73 shows that the feature amount of the special image signal is greater than the feature amount of the normal image signal, or if the disease condition score of the special image signal is greater than the disease condition score of the normal image signal, the display processing unit 74 uses the image from the special image signal to perform image processing, such as emphasis processing, in some cases, to generate a high score display image. Note that if the feature amount or disease condition score of the normal image signal is greater than the feature amount or disease condition score of the special image signal, the image from the normal image signal is used to generate a high score display image. Furthermore, these processes in the judgment mode processing unit 65 are performed automatically.

As shown in FIG. 8, the feature amount calculation unit 70 has a normal image feature amount calculation unit 75 and a special image feature amount calculation unit 76. The normal image feature amount calculation unit 75 calculates the feature amount of the normal image signal (hereinafter referred to as the normal feature amount). The special image feature amount calculation unit 76 calculates the feature amount of the special image signal (hereinafter referred to as the special feature amount). The feature amount is used to calculate the disease condition score and to create a high score display image by comparing the normal feature amount with the special feature amount.

Regarding the feature amount, specifically, for example, in this embodiment, a lower endoscope is used as the endoscope 12, and the observation target is ulcerative colitis, which is an inflammatory bowel disease of the large intestine. In this embodiment, the feature amount includes a predetermined image feature of the image signal based on blood vessels, gland ducts, or mucosa. The feature amount based on blood vessels, gland ducts, or mucosa uses a value that quantifies or classifies the state of blood vessels, the state of gland ducts, or the state of mucosa. The state of blood vessels includes the degree of visibility of blood vessels, the thickness of blood vessels, the density of blood vessels, the shape of blood vessels, the degree of branching of blood vessels, the color of blood vessels, or the distribution of these. The state of gland ducts includes the degree of visibility of gland ducts, the thickness of gland ducts, the density of gland ducts, the shape of gland ducts, the degree of branching of gland ducts, the color of gland ducts, or the distribution of these. The state of mucosa includes the color of the mucosa, the roughness of the surface of the mucosa, the unevenness of the surface of the mucosa, or the distribution of these.

In this embodiment, three types of feature values are calculated: the degree of blood vessel transparency, the color of the mucosa, and the roughness or unevenness of the mucosa. The feature values are obtained by image processing of the normal image signal (first image signal) or the special image signal (second image signal). The feature value of the degree of blood vessel transparency is obtained by detecting blood vessels in the normal image signal or the special image signal. The feature value of the color of the mucosa is obtained from the color itself and the area occupied by the color in the normal image signal or the special image signal. Furthermore, the feature value of the roughness or unevenness of the mucosa is obtained by matching the normal image signal or the special image signal with a previously prepared pattern.

These features are calculated by quantifying the features, or by storing a template of specific features as the image features of the object of observation in advance and determining whether the extracted image features match the features of the template. Here, "matching" includes not only that the features being compared match each other, but also that the difference between the features being compared falls within a certain range. The degree of matching can be quantified to obtain a feature. In this embodiment, in order to make it easier to grasp the above-mentioned features in the special image signal, illumination light is selected that provides higher resolution for vascular and ductal structures than other structures.

The number of types of feature amounts may be any number that can calculate a pathology score, and may be determined appropriately depending on the type of observation target or disease, and may be one type or two or more types. The emission spectrum of the illumination light may be changed depending on the type of feature amount so that the feature amount can be clearly understood. After calculating multiple types of feature amounts, these may be summed up to determine the feature amount of each image, or each feature amount may be weighted and then summed up to determine the feature amount of each image. The same type of feature amount may be calculated for each image, or different types of feature amounts may be calculated. The feature amount may be calculated by image recognition processing using machine learning, in addition to image processing.

As shown in FIG. 9, the disease condition score calculation unit 71 includes a normal image score calculation unit 77, a normal score table 78, a special image score calculation unit 79, and a special score table 80. The normal image score calculation unit 77 calculates a disease condition score of a normal image (first disease condition score) based on the features of the normal image obtained by the normal image feature calculation unit 75 and the normal score table 78. Similarly, the special image score calculation unit 79 calculates a disease condition score of a special image (second disease condition score) based on the special features obtained by the special image feature calculation unit 76 and the special score table 80.

The pathology score for a normal image (hereinafter referred to as the normal score) may be calculated directly using the pixel values of the normal image signal, etc., in addition to being calculated from the normal feature amount. Similarly, the pathology score for a special image (hereinafter referred to as the special score) may be calculated directly using the pixel values of the special image signal, etc., in addition to being calculated from the special feature amount.

As described above, the disease condition score is, for example, the Mayo score, which is one of the endoscopic indices of the severity of ulcerative colitis. The normal image score calculation unit 77 determines the Mayo score of the normal image, which is the normal score, as either mild (0 or 1), moderate (grade 2), or severe (grade 3) based on the normal feature amount and the normal score table 78. Similarly, the special image score calculation unit 79 determines and classifies the Mayo score of the special image, which is the special score, as either mild (0 or 1), moderate (grade 2), or severe (grade 3) based on the special feature amount and the special score table 80.

The comparison target selection unit 72 specifies whether the feature amount or the disease condition score will be used as the target for comparison by the disease condition comparison unit 73. The specification is made by the scope switch 13e (see FIG. 1) or the user interface 19. Note that this specification can be set appropriately, such as specifying one or the other when the endoscope system is started up, or setting it so that once specified, it will not be changed until the next time it is changed. It is also possible to specify both the feature amount and the disease condition score as targets for comparison. In this case, the disease condition comparison unit 73 compares both the normal feature amount and the special feature amount, and the normal disease condition score and the special disease condition score, and sends the results to the disease condition comparison unit 73.

The disease condition comparison unit 73 compares the normal feature amount with the special feature amount, or compares the normal score with the special score, according to the selection made by the comparison target selection unit 72. Alternatively, if both the feature amount comparison and the disease condition score comparison are selected, it compares both the normal feature amount with the special feature amount and the normal disease condition score with the special disease condition score. The comparison results are used to generate a high score display image in the display processing unit 74.

The display processing unit 74 creates a high score display image when a difference occurs between the normal feature amount and the special feature amount, or the normal score and the special score, as a result of the comparison by the condition comparison unit 73 between the normal feature amount and the special feature amount, or when the difference is equal to or exceeds a predetermined range, or when the normal score and the special score are different. The high score display image is an image for encouraging the observer to recognize the image with the higher feature amount or condition score when the feature amount or condition score calculated for the normal image and the special image are different. Therefore, the high score display image can be the image itself with the higher feature amount or condition score between the normal image and the special image.

The comparison target selection unit 72 specifies both the feature amount and the disease condition score as targets for comparison, and if a difference occurs in either or both of the feature amount and the disease condition score as a result of the comparison by the disease condition comparison unit 73, a high score display image is generated based on the normal image or the special image, whichever has the higher feature amount or disease condition score. If the image with the high feature amount differs from the image with the high disease condition score, for example, if the normal feature amount is higher than the special feature amount and the special disease condition score is higher than the normal score, it can be specified whether the high score display image is to be created based on the normal image or the special image.

As shown in FIG. 10, the display processing unit 74 includes a normal image generating unit 81, a special image generating unit 82, a first emphasized image generating unit 83, and a second emphasized image generating unit 84. As a result of the comparison by the pathology comparing unit 73, for example, when the special pathology score based on the special image signal (second image signal) is greater than the normal pathology score based on the normal image signal (first image signal), a high score display image is generated in the special image generating unit 82, the first emphasized image generating unit 83, and the second emphasized image generating unit 84. The special image generating unit 82 has a function similar to that of the special mode processing unit 64, and generates a special image as a high score display image. The first emphasized image generating unit 83 generates an image (first emphasized image) in which a normal image is emphasized by a special image signal as a high score display image. The second emphasized image generating unit 84 generates an image (second emphasized image) in which a special image is emphasized by a normal image signal as a high score display image. Note that if the normal score is equal to or greater than the special score, the high score display image is not generated. The high score display image will be explained later.

The generation of a high score display image will be specifically described with reference to FIG. 11. FIG. 11 is an explanatory diagram for explaining the case where a feature amount and a disease condition score are calculated for each of a normal image and a special image, and where it is determined that a high score image exists and the case where it is determined that a high score image does not exist. A normal image 85 and a special image 86 are images of the same observation site. This observation site is a site where the actual MayoScore (hereinafter referred to as Mayo) is mild. The feature amount of the normal image 85 is calculated to be 30, and the disease condition score is calculated to be Mayo 0, as indicated by "Mayo 0" in FIG. 11. For the same observation site, the feature amount of the special image 86 is calculated to be 30, and the disease condition score is calculated to be Mayo 0. The comparison target is set to the disease condition score by the comparison target selection unit 72, and in this case, the disease condition score does not differ between the normal image 85 and the special image 86, so a high score display image is not created. Therefore, the normal image is displayed unchanged on the monitor 18.

Next, for another observation site that is actually mild and has a Mayo of 1, the feature amount of the normal image 85 is calculated to be 30, and the disease condition score is calculated to be Mayo 0. For the same observation site, the feature amount of the special image 86 is calculated to be 40, and the disease condition score is calculated to be Mayo 1. The comparison object selection unit 72 sets the comparison object to the disease condition score, and in this case, the disease condition scores of the normal image 85 and the special image 86 are different, so a high-score display image is created. In this way, the surface irregularities that are not displayed in the normal image and cannot be grasped are displayed as an image in the special image, so the calculation results of the feature amount are different, and the disease condition score based on the feature amount is also calculated to be a different value from that of the normal image. By creating a high-score display image, the observer can accurately determine the severity of the disease.

Next, for another observation site that is actually moderately ill and has a Mayo score of 2, the feature amount of the normal image 85 is calculated to be 60, and the condition score is calculated to be Mayo 2. For the same site, the feature amount of the special image 86 is calculated to be 65, and the condition score is calculated to be Mayo 2. Similarly, for another observation site that is severely ill and has a Mayo score of 3, the feature amount of the normal image 85 is calculated to be 90, and the condition score is calculated to be Mayo 3. For the same site, the feature amount of the special image 86 is calculated to be 95, and the condition score is calculated to be Mayo 3. The comparison target is set to the condition score by the comparison target selection unit 72, and in this case, since the condition score does not differ between the normal image and the special image, a high score display image is not created. Therefore, the normal image is displayed unchanged on the monitor 18.

A case will now be described in which the comparison target is set to a feature by the comparison target selection unit 72. As shown in FIG. 12, for another observation site with moderate disease and Mayo 2, the feature amount of the normal image 85 is calculated to be 60, and for the same site, the feature amount of the special image 86 is calculated to be 65, so a high score display image based on the special image is created. Similarly, for another observation site with severe disease and Mayo 3, the feature amount of the normal image 85 is calculated to be 90, and for the same site, the feature amount of the special image 86 is calculated to be 95, so a high score display image based on the special image is created.

The high score display image will now be described in detail. As shown in FIG. 13, when the special score is higher between the normal image 85 and the special image 86, the special image 86 (second image) generated by the special image generating unit 82 is set as the high score display image. The high score display image is displayed on the monitor 18.

The high score display image can be generated by processing the image with a lower pathology score (hereinafter referred to as the low score image) using the image with a higher pathology score (hereinafter referred to as the high score image) out of the normal image and the special image.

The first emphasized image generating unit 83 (see FIG. 10) creates an image that emphasizes and displays the feature amount that was the basis for calculating the pathology score of the high score image, and generates a high score display image (first emphasized image) superimposed on the low score image to create the high score display image. As shown in FIG. 14, when the special score is high between the normal image 85 and the special image 86, first, an image is created that emphasizes and displays the feature amount that was the basis for calculating the special score. Then, by superimposing this image on the normal image 85, a first emphasized image 87 having a feature portion 87a that emphasizes and displays the feature amount in the normal image 85 is created. This image is the high score display image. The high score display image is displayed on the monitor 18.

Similarly, the high score display image can be generated by processing the high score image from among the normal image and the special image. The second emphasis image generation unit 84 (see FIG. 10) creates an image that highlights and displays the feature amount that was the basis for calculating the pathology score of the high score image, and generates a high score display image (second emphasis image) superimposed on the low score image to create the high score display image. As shown in FIG. 15, when the special score is high between the normal image 85 and the special image 86, first, an image is created that highlights and displays the feature amount that was the basis for calculating the special score. Then, by superimposing this image on the special image 86, a second emphasis image 88 having a feature portion 88a that further highlights and displays the feature amount in the special image 86 is created. This image is the high score display image. The high score display image is displayed on the monitor 18.

The display control unit 62 controls the display of the high score display image generated by the display processing unit 74. The display is performed by displaying it on the monitor 18. Controlling the display means determining whether or not to display the high score display image, or the display mode of the high score display image, and issuing an instruction to display it on the monitor 18.

As for whether or not to display the high score display image, the display control unit 62 can determine whether or not to display the high score display image based on both the high score image and the image displayed on the monitor 18 when the high score display image is created. Specifically, for example, if the special image is a high score image and the normal image is displayed on the monitor 18 when the high score display image is created from the special image, the display control unit 62 displays the high score display image on the monitor 18. On the other hand, if the special image is displayed on the monitor 18, the display control unit 62 does not change the display on the monitor 18. Also, for example, if the normal image is a high score image and the special image is displayed on the monitor 18 when the high score display image is created from the normal image, the display control unit 62 displays the high score display image on the monitor 18. On the other hand, if the normal image is displayed on the monitor 18, the display control unit 62 does not change the display on the monitor 18. That is, in this case, when the normal image (first image) is displayed, the display control unit 62 continues to display the normal image (first image).

The display mode of the high score display image may be any mode in which the high score display image is displayed on the monitor 18. For example, when the high score display image is created, the image displayed on the monitor 18 (hereinafter referred to as the original image) can be switched to the high score display image. In addition, both the original image and the high score display image can be displayed. In this case, the original image and the high score display image may be displayed side by side on the monitor 18 with the display area on the monitor 18 being the same, or the original image and the high score display image may be displayed on two screens with different display areas. In other words, the original image and the high score display image may be displayed separately as a so-called main image and sub-image.

Specifically, as shown in FIG. 16, when a normal image 85 (first image) is displayed on the monitor 18, if the disease condition score of the special image 86 is higher than that of the normal image 85 and the special image 86, the display control unit 62 switches the screen displayed on the monitor 18 to the special image 86. Also, as shown in FIG. 17, in a similar case, the screen displayed on the monitor 18 is displayed so that the display area on the monitor 18 is the same for the normal image 85 (first image) and the special image 86, and two screens are displayed side by side on the monitor 18. Also, as shown in FIG. 18, in a similar case, the screen displayed on the monitor 18 is displayed so that the normal image 85 (first image) is displayed as a main image with a large display area, and the special image 86 is displayed as a sub-image with a small display area, and two screens are displayed side by side on the monitor 18. Also, as shown in FIG. 19, in a similar case, the screen displayed on the monitor 18 is displayed so that the special image 86 is displayed as a main image with a large display area, and the normal image 85 (first image) is displayed as a sub-image with a small display area, and two screens are displayed side by side on the monitor 18.

The display control unit 62 notifies the observer of the presence of a high score display image before the display control unit 62 controls the display of the high score image. The notification of the presence of a high score display image is a notification for making the observer aware that a high score display image has been generated. The notification is made in a manner that allows the observer to recognize that a high score display image has been generated.

The notification is made by displaying a warning on the monitor 18. The warning can be displayed, for example, by displaying a warning text or image in the display area of the monitor 18, or by changing the color tone of the image on the monitor 18, etc.

The notification can also be made by having the notification unit 17 (see FIG. 2) generate sound, light, or vibration. The notification unit 17 notifies the observer of the presence of a high score display image by generating sound, light, or vibration. Specifically, the notification unit 17 can be a speaker included in the monitor 18. It can also be a small wireless device that generates light or vibration.

The notification will be described in detail. As shown in FIG. 20, a warning display is displayed on the monitor 18 to notify the observer that a high score display image is present. When a high score display image is generated while a normal image 85 is being displayed, a text warning display 89 is displayed on the monitor 18. The warning display 89 is in the form of text such as "High score image present - observation mode will be changed."

The display control unit 62 automatically displays the high score display image after notifying the user of the presence of the high score display image for a predetermined time. After automatically displaying the high score display image, the display control unit 62 may automatically switch to the image that was displayed before the high score display image was displayed after a predetermined time has elapsed, or may switch after an instruction is given. After the notification, the high score display image can be displayed according to an instruction from the instruction unit. The instruction unit accepts an instruction from the observer to display the high score display image on the monitor 18. Therefore, for example, the instruction unit is the display instruction unit 13c of the endoscope 12. Specifically, after the above notification, the display control unit 62 does not display the high score display image on the monitor 18 until an instruction is given by the display instruction unit 13c. On the other hand, after the above notification, when an instruction is given by the display instruction unit 13c, the display control unit 62 displays the high score display image on the monitor 18.

As shown in FIG. 21, the flow of the processing procedure in the judgment mode will be described in a flow diagram. As shown in steps S100 and S140, the image signal acquisition unit 54 acquires a normal image signal and a special image signal in sequence. First, in step S110, a normal image is displayed on the monitor 18. In the normal image feature amount calculation unit 75, a normal feature amount is calculated from the normal image signal (step S120). In the normal image score calculation unit 77, a normal score is calculated from the normal feature amount (step S130). Similarly, in the special image feature amount extraction unit 76, a special feature amount is calculated from the special image signal (step S150). In the special image score calculation unit 79, a special score is calculated from the special feature amount (step S160). When the normal score and the special score are calculated, in this embodiment, since the pathology score is selected by the comparison target selection unit 72, the pathology scores of both are compared by the pathology comparison unit 73 (step S170). As a result of the comparison, it is determined whether or not a high-score image exists (step S180). If a high score image exists (YES in step S180), proceed to step S190 to create a high score display image. If a high score image does not exist (NO in step S180), return to step S100 to obtain an image.

In step S190, the display processing unit 74 creates a high score display image. Then, in step S200, the display control unit 62 determines whether or not to display and the display mode. When the normal score is higher than the special score, in step S200, whether or not to display is determined. Since the normal image is displayed on the monitor 18, if the normal image is a high score image, the high score image is not displayed and the process returns to image acquisition in step S100. If the special image is a high score image (NO in step S200), the process proceeds to display mode determination in step S210. In step S220, the notification unit 74 notifies the observer that a high score image has been generated. After the notification, in step S230, it is determined whether a display instruction has been issued. If a display instruction has been issued, the high score display image in step S240 is displayed on the monitor 18. If no display instruction has been issued, the process returns to normal image acquisition in step S100. When the observer ends the display of the high score display image (YES in step S240), the display of the high score display image ends.

Note that the notification in step S220 and the determination of whether or not a display instruction has been issued in step S230 may be omitted. In that case, after the display mode determination in step S210, the process proceeds to displaying the high score image in step S240.

As described above, by configuring the endoscope system 10, even when observing by displaying a normal image, a special image, which is an image with a different emission spectrum from the normal image, is always obtained, and the feature amount and the disease condition score are calculated for each of the normal image and the special image, so that images with high feature amounts of the observed part or images with high disease severity or disease progression can be observed without missing, and it is possible to prevent a decrease in the accuracy of diagnosis of disease severity, etc. Furthermore, since the disease condition score, which is the disease severity or disease progression, is calculated, variation in diagnosis depending on the observer is prevented, and an objective diagnosis is possible. Furthermore, when a high score display image is generated and automatically displayed on the monitor 18, no instruction from the observer is required. On the other hand, when the display on the monitor 18 is not to be switched, the display of the high score display image can be controlled by the observer's instruction.

In this embodiment, the disease condition score is calculated from the calculated feature amounts for the normal image and the special image, but the disease condition score may be calculated by image processing without using the feature amounts. For example, the disease condition score may be calculated directly from each of the normal image and the special image using image recognition technology based on machine learning. Furthermore, the feature amounts themselves may be calculated using image recognition technology based on machine learning.

The operation method of the above-mentioned endoscope system 10 includes an emission step in which the light source unit 20 emits a first illumination light and a second illumination light having different emission spectra; an image signal acquisition step in which the image signal acquisition unit 54 images an object being observed illuminated with the first illumination light to acquire a first image signal, and also images an object being observed illuminated with the second illumination light to acquire a second image signal; a feature calculation step in which the feature calculation unit 70 calculates a first feature based on the first image signal and calculates a second feature based on the second image signal; a disease condition score calculation step in which the disease condition score calculation unit 71 calculates a first disease condition score representing the disease condition of the object being observed based on the first image signal, and calculates a second disease condition score representing the disease condition of the object being observed based on the second image signal; The method includes a condition comparison step of comparing the first disease score with a second disease score, a high score display image generation step in which the display processing unit 74 generates a high score display image using the second image signal when the second disease score is greater than the first disease score, a display step in which, when the display control unit 62 controls the first image based on the first image signal to be displayed on the monitor, and when a high score display image has been generated, the display control unit 62 controls the first image based on the first image signal to be displayed on the monitor, or controls the first image to be switched to the high score display image to be displayed on the monitor, or controls the first image and both the high score display image to be displayed on the monitor, and a comparison target selection step in which the condition comparison unit specifies whether to use the first feature amount and the second feature amount, or the first disease score and the second disease score, as targets for comparison.
The operation method of the endoscope system 10 described above includes a light emission step in which the light source unit 20 emits first illumination light and second illumination light having different emission spectra, an image signal acquisition step in which the image signal acquisition unit 54 images an object being observed illuminated with the first illumination light to acquire a first image signal, and an image signal acquisition step in which the image signal acquisition unit 54 images an object being observed illuminated with the second illumination light to acquire a second image signal, and a feature amount calculation step in which the feature amount calculation unit 70 calculates a first feature amount based on the first image signal and calculates a second feature amount based on the second image signal. a disease condition score calculation step in which the disease condition score calculation unit 71 calculates a first disease condition score representing the disease condition of the observation subject from a first feature amount calculated based on the first image signal, and calculates a second disease condition score representing the disease condition of the observation subject from a second feature amount calculated based on the second image signal; a disease condition comparison step in which the disease condition comparison unit 73 compares the first feature amount with the second feature amount or compares the first disease condition score with the second disease condition score; and a display processing unit 74, if the second feature amount is greater than the first feature amount, Alternatively, the method includes a high score display image generating step of generating a high score display image using the second image signal when the second disease condition score is greater than the first disease condition score, and generating a high score display image using the first image signal when the first feature amount is greater than the second feature amount or when the first disease condition score is greater than the second disease condition score, and a display step of controlling the display control unit 62 to display a first image based on the first image signal on the monitor and to hide a second image based on the second image signal on the monitor, when the high score display image has been generated, controlling the display control unit 62 to switch from the first image to the high score display image on the monitor, or controlling the display control unit 62 to display both the first image and the high score display image on the monitor, and the high score display image is a second image based on the second image signal, a first emphasized image generated by processing the first image signal with the second image signal, or a second emphasized image generated by processing the second image signal with the second image signal.

In the above, the hardware structure of the processing units that execute various processes, such as the image signal acquisition unit 54, the central control unit 52, the image processing unit 61, the display control unit 62, etc., is the various processors shown below. The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and functions as various processing units, a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and a dedicated electrical circuit (Graphical Processing Unit: GPU), which is a processor with a circuit configuration designed specifically to execute various processes.

A processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, multiple FPGAs, a combination of a CPU and an FPGA, or a combination of a GPU and a CPU). Multiple processing units may also be configured with one processor. As an example of configuring multiple processing units with one processor, first, as represented by computers such as clients and servers, there is a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units. Second, as represented by system on chip (SoC), there is a form in which a processor is used that realizes the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip. In this way, the various processing units are configured using one or more of the above various processors as a hardware structure.

More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

10 Endoscope system 12 Endoscope 12a Insertion section 12b Operation section 12c Bending section 12d Tip section 13a Angle knob 13b Mode switching section 13c Display instruction section 13d Zoom operation section 12e Forceps inlet 14 Light source device 16 Processor device 17 Notification section 18 Monitor 19 User interface 20 Light source section 20a V-LED
20b B-LED
20c G-LED
20d R-LED
22 Light source control unit 23 Wavelength cut filter 30a Illumination optical system 30b Imaging optical system 41 Light guide 45 Illumination lens 46 Objective lens 47 Zoom lens 48 Image sensor 52 Central control unit 54 Image signal acquisition unit 61 Image processing unit 62 Display control unit 63 Normal mode processing unit 64 Special mode processing unit 65 Determination mode processing unit 70 Feature amount calculation unit 71 Disease condition score calculation unit 72 Comparison target selection unit 73 Disease condition comparison unit 74 Display processing unit 75 Normal image feature amount calculation unit 76 Special image feature amount calculation unit 77 Normal image score calculation unit 78 Normal score table 79 Special image score calculation unit 80 Special score table 81 Normal image generation unit 82 Special image generation unit 83 First emphasized image generation unit 84 Second emphasized image generation unit 85 Normal image 86 Special image 87 Enhanced image of normal image (first emphasized image)
87a: Feature portion 88: Enhanced image of special image (second enhanced image)
88a Feature section 89 Warning display S100 to S250 Steps

Claims (12)

a light source unit that emits a first illumination light and a second illumination light having different emission spectra;
an image signal acquisition unit that acquires a first image signal by capturing an image of an observation target illuminated with the first illumination light, and acquires a second image signal by capturing an image of the observation target illuminated with the second illumination light;
a feature amount calculation unit that calculates a first feature amount based on the first image signal and calculates a second feature amount based on the second image signal;
a disease condition score calculation unit that calculates a first disease condition score representing a disease condition of the observation target based on the first image signal, and calculates a second disease condition score representing a disease condition of the observation target based on the second image signal;
a disease condition comparison unit that compares the first feature amount with the second feature amount, or compares the first disease condition score with the second disease condition score;
a display processing unit that generates a high score display image using the second image signal when the second feature amount is greater than the first feature amount or when the second disease condition score is greater than the first disease condition score;
a display control unit that controls to display a first image based on the first image signal on a monitor, and when the high score display image is generated, controls to switch from the first image to display the high score display image on the monitor, or controls to display both the first image and the high score display image on the monitor;
An endoscopic system comprising a comparison object selection unit that specifies whether the first feature amount and the second feature amount, or the first disease condition score and the second disease condition score, should be used as the objects to be compared by the disease condition comparison unit. a light source unit that emits a first illumination light and a second illumination light having different emission spectra;
an image signal acquisition unit that acquires a first image signal by capturing an image of an observation target illuminated with the first illumination light, and acquires a second image signal by capturing an image of the observation target illuminated with the second illumination light;
a feature amount calculation unit that calculates a first feature amount based on the first image signal and calculates a second feature amount based on the second image signal;
a disease condition score calculation unit that calculates a first disease condition score representing a disease condition of the observation target based on the first feature amount, and calculates a second disease condition score representing a disease condition of the observation target based on the second feature amount;
a disease condition comparison unit that compares the first feature amount with the second feature amount or compares the first disease condition score with the second disease condition score ;
a display processing unit that generates a high score display image using the second image signal when the second feature amount is greater than the first feature amount or when the second disease condition score is greater than the first disease condition score;
a display control unit that controls to display a first image based on the first image signal on a monitor and to hide the second image based on the second image signal on the monitor, and when the high score display image is generated, controls to switch from the first image to display the high score display image on the monitor, or controls to display both the first image and the high score display image on the monitor;
Equipped with
an endoscope system in which the high score display image is a second image based on the second image signal, a first emphasized image generated by processing the first image signal using the second image signal, or a second emphasized image generated by processing the second image signal using the second image signal . The endoscope system according to claim 1 , wherein the first illumination light is white light, and the second illumination light is special light. The endoscope system according to claim 1 , wherein the first disease condition score and the second disease condition score include a disease severity or a disease progression. The endoscope system according to claim 1 , wherein the first feature amount and the second feature amount include values based on a blood vessel, a gland duct, or a mucosa. The endoscope system according to claim 1 , wherein the display control unit performs a notification relating to the presence of the high score display image before displaying the high score display image. The endoscope system according to claim 6 , wherein the notification is a display of a warning. A notification unit that generates sound, light, or vibration is provided,
The endoscope system according to claim 6 or 7 , wherein the notification is generated by the notification unit through generation of sound, light, or vibration. an instruction unit that receives an instruction to display the high score display image,
The endoscope system according to claim 6 , wherein the display control unit displays the high score display image in accordance with the instruction by the instruction unit after the notification. An endoscopic system according to any one of claims 1 to 9, wherein when the display control unit controls to display both the first image and the high score display image on the monitor, the display control unit displays the first image based on the first image signal in a display area larger than that of the high score display image. An endoscopic system according to any one of claims 1 to 9, wherein when the display control unit controls to display both the first image and the high score display image on the monitor, the display control unit displays the first image based on the first image signal in a display area smaller than that of the high score display image. The endoscopic system according to any one of claims 1 to 9, wherein the display control unit controls the display of a second image based on the second image signal on a monitor, and when the high score display image is generated, the display control unit controls the display of the second image based on the second signal to continue.

Images