Endoscope device, control device, and information storage medium

Abstract

The embodiment of the invention provides an endoscope device, a control device and an information storage medium. An endoscope device includes a light source unit (100), an imaging unit (200), and a processing unit (310). The light source unit (100) generates, as illumination light, narrow-band light having a peak wavelength between a wavelength band including a maximum wavelength and a wavelength band including a minimum wavelength in the light absorption characteristics of hemoglobin. The imaging unit (200) captures an image of return light from the living body irradiated with the illumination light and outputs an imaging signal. The processing unit (310) recognizes the state of the living body using a captured image generated from the imaging signal, outputs state recognition information indicating the state of the living body, and controls the wavelength characteristics of the illumination light on the basis of the state recognition information.

Description

[0001] This application is a divisional application of the invention patent application with application number 201980095266.X (application date: April 11, 2019, invention name: Endoscopic device, control device, working method and program of endoscope device). Technical Field

[0002] The present invention relates to an endoscope device, a control device, an operating method of an endoscope device, an information storage medium, etc. Background Art

[0003] It is known that a method of facilitating the discovery or diagnosis of a specific part by irradiating special light composed of narrow-band light or the like in an endoscope device. For example, a prior art using such special light is disclosed in Patent Document 1. The endoscope system of Patent Document 1 analyzes image data of an observed image, discriminates the type of the observed part based on the density of blood vessels in each layer of the mucosa, and selects the best illumination light according to the discriminated type of the observed part.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2012-152333 Summary of the invention

[0007] Problems to be solved by the invention

[0008] In tissues such as mucous membranes, the depth reached is determined by the wavelength of the illumination light. However, if a histological change occurs in a living body, the degree of illumination light scattering may be different before and after the change. That is, even for the same type of part, the amount of light reaching a specified depth in the tissue may change before and after the histological change occurs. Therefore, there is a problem that the appearance of the image changes before and after the histological change occurs.

[0009] For example, sterilization of the gastric mucosa causes histological changes in the surface layer of the gastric mucosa. In this case, light that originally reaches a predetermined depth becomes difficult to reach due to increased scattering, so that blood vessels in the mucosa at a predetermined depth are blurred and difficult to see.

[0010] Means for solving problems

[0011] One embodiment of the present invention relates to an endoscope device, comprising: a light source unit that generates narrow-band light as illumination light, the narrow-band light having a peak wavelength between a band including a maximum wavelength and a band including a minimum wavelength in the light absorption characteristics of hemoglobin; an imaging unit that captures return light from a living body irradiated with the illumination light and outputs an imaging signal; and a processing unit that uses an imaging image generated based on the imaging signal to identify the state of the living body, outputs state identification information indicating the state of the living body, and controls the wavelength characteristics of the illumination light based on the state identification information.

[0012] In addition, another embodiment of the present invention relates to a control device, which includes: a processing unit, which causes a light source unit to generate narrow-band light as illumination light, and the narrow-band light has a peak wavelength between a band including a maximum value and a band including a minimum value in the light absorption characteristics of hemoglobin; and a camera signal receiving unit, which receives a camera signal from a camera unit, and the camera unit captures return light from a living body irradiated with the illumination light, the processing unit uses a camera image generated based on the camera signal to identify the state of the living body, outputs state recognition information indicating the state of the living body, and controls the wavelength characteristics of the illumination light based on the state recognition information.

[0013] In addition, another embodiment of the present invention relates to an operating method of an endoscope device, which generates narrow-band light as illumination light, and the narrow-band light has a peak wavelength between a band including a maximum value and a band including a minimum value in the light absorption characteristics of hemoglobin; captures return light from a living body irradiated with the illumination light and outputs an imaging signal; uses a camera image generated based on the imaging signal to identify the state of the living body, and outputs state recognition information indicating the state of the living body; and controls the wavelength characteristics of the illumination light based on the state recognition information.

[0014] In addition, another embodiment of the present invention relates to a program that causes a computer to execute the following steps: causing a light source unit to generate narrow-band light as illumination light, the narrow-band light having a peak wavelength between a band containing a maximum value and a band containing a minimum value in the light absorption characteristics of hemoglobin; outputting an imaging signal by causing an imaging unit to image return light from a living body irradiated with the illumination light; identifying a state of the living body using an imaging image generated based on the imaging signal, and outputting state recognition information indicating the state of the living body; and controlling the wavelength characteristics of the illumination light based on the state recognition information. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a structural example of an endoscope device.

[0016] Figure 2 This is a detailed structural example of the light source unit.

[0017] Figure 3 This is an example of the wavelength characteristics of the narrow-band light generated by the light source unit.

[0018] Figure 4 This is an example of the wavelength characteristics of the narrow-band light generated by the light source unit.

[0019] Figure 5 This is an example of the wavelength characteristics of the narrow-band light generated by the light source unit.

[0020] Figure 6 This is a detailed configuration example of the processing unit.

[0021] Figure 7 This is a flowchart illustrating the procedure of processing performed by the processing unit.

[0022] Figure 8 This is a flowchart illustrating the procedure of processing performed by the processing unit.

[0023] Fig. 9 This is a flowchart illustrating the procedure of processing performed by the processing unit. DETAILED DESCRIPTION

[0024] The present embodiment will be described below. In addition, the present embodiment described below does not unduly limit the contents of the present invention described in the claims. In addition, all the structures described in the present embodiment are not necessarily essential structural elements of the present invention.

[0025] 1. Endoscopic device

[0026] Figure 1 The endoscope device is a structural example. The endoscope device includes an imaging unit 200, a control device 300, a display unit 400, an external I / F unit 500, and a light source unit 100. As the endoscope device, for example, a flexible endoscope used in the digestive tract, etc., and a rigid endoscope used in a laparoscope, etc. can be envisioned, but it is not limited to these.

[0027] The light source unit 100 is a device that generates illumination light. The light source unit 100 is also referred to as a light source device. The light source unit 100 generates white light and special light as illumination light. Specifically, the light source unit 100 generates white light in the WLI (White Light Imaging) mode, and generates special light in the special light mode. The special light mode is, for example, an NBI (Narrow Band Imaging) mode that uses blue narrow-band light and green narrow-band light as illumination light. The timing of emitting illumination light may be either a simultaneous mode in which a plurality of light sources emit light simultaneously, or a sequential mode in which a plurality of light sources emit light in sequence.

[0028] The imaging unit 200 is a part that is inserted into the body and captures the subject. The imaging unit 200 is also called a scope. The imaging unit 200 includes a light guide 210, an illumination lens 220, an objective lens 230, and an imaging element 240. The imaging element 240 is also called an image sensor. The imaging unit 200 has a connector (not shown) and is attached and detached to the control device 300 through the connector.

[0029] The light guide 210 guides the illumination light from the light source unit 100 to the front end of the imaging unit 200. The illumination lens 220 irradiates the illumination light guided by the light guide 210 to the subject. In the present embodiment, the subject is a living body. For example, in an endoscope device for the upper digestive tract, the subject is a mucous membrane of the stomach or esophagus. The reflected light from the subject is incident on the objective lens 230. The objective lens 230 forms a subject image, and the imaging element 240 captures the subject image.

[0030] The imaging element 240 captures the return light from the subject irradiated with the illumination light and outputs an imaging signal. The imaging element 240 may be any one of a color image sensor and a monochrome image sensor in which a color filter is provided in each pixel. The color image sensor is, for example, a Bayer-type image sensor having a Bayer-arranged color filter or a complementary color image sensor having a complementary color filter.

[0031] The imaging unit 200 includes an A / D conversion circuit. The A / D conversion circuit A / D converts an analog imaging signal from the imaging element 240 into a digital imaging signal. The A / D conversion circuit is built into the imaging element 240, for example.

[0032] The control device 300 performs signal processing including image processing. In addition, the control device 300 controls each part of the endoscope device. The control device 300 is also called a processing device or a processor unit. The control device 300 includes a processing unit 310 and an imaging signal receiving unit 330. The processing unit 310 is also called a processing circuit or a processor.

[0033] The imaging signal receiving unit 330 receives the imaging signal from the imaging element 240. The imaging signal receiving unit 330 is, for example, a connector connecting the imaging unit 200 and the control device 300, or an interface circuit for receiving the imaging signal, or a pre-processing circuit for generating image data based on the imaging signal, etc. In addition, the imaging signal receiving unit 330 and the processing unit 310 may be implemented by separate hardware or by integrated hardware.

[0034] The processing unit 310 generates a display image by performing image processing based on the camera signal received by the camera signal receiving unit 330, and outputs the display image to the display unit 400. In addition, the processing unit 310 controls each unit of the endoscope device. Specifically, the processing unit 310 controls the wavelength characteristics of the illumination light, the light emission timing of the light source, and the camera timing of the camera element 240. For example, the user operates the external I / F unit 500 to switch between the WLI mode and the special light mode. For example, when the special light mode is set, the processing unit 310 instructs the light source unit 100 to emit special light, generates a special light image based on the camera signal, and outputs the special light image to the display unit 400. When the WLI mode is set, the processing unit 310 instructs the light source unit 100 to emit white light, generates a white light image based on the camera signal, and outputs the white light image to the display unit 400.

[0035] The display unit 400 is a device that displays a display image from the processing unit 310. The display unit 400 is, for example, a liquid crystal display device. The external I / F unit 500 is a device that receives user operations on the endoscope device. For example, the external I / F unit 500 is a button, a dial, a pointing device, a touch panel, or a foot switch.

[0036] 2. Light source

[0037] The following description will be made using the case where special light observation is NBI as an example, but the method of this embodiment can also be applied to special light observation other than NBI. That is, when the scattering state of the illumination light at a predetermined part changes due to histological changes at the predetermined part, the same method as that of this embodiment can be applied.

[0038] Figure 2 1 is a detailed configuration example of the light source unit 100 . The light source unit 100 includes a driving unit 110 , light sources LDV1 , LDV2 , LDG, and LDW, and a combining unit 120 .

[0039] The light source control unit 312 inputs a control signal for instructing the light emission timing and light amount of each light source to the driving unit 110. Figure 5 As described later, the light source control unit 312 is included in the processing unit 310. The driving unit 110 drives the light sources LDV1, LDV2, LDG, and LDW based on a control signal from the light source control unit 312. For example, the driving unit 110 supplies a driving current to the light source to cause the light source to emit light.

[0040] The light sources LDV1, LDV2, LDG, and LDW generate light having a specified wavelength characteristic, respectively. The light sources LDV1, LDV2, and LDG generate a first narrowband light, a second narrowband light, and a third narrowband light, respectively. The half-peak width of the narrowband light is, for example, a few nm to tens of nm. The light source LDW generates white light. White light has a continuous spectrum in the visible light band. Alternatively, white light may also be composed of light of multiple bands. Each light source is, for example, an LED or a laser. Alternatively, LDW as a white light source may also be a xenon lamp, etc. In addition, the light sources LDV1, LDV2, and LDG may also be realized by a white light source and an optical filter that allows each narrowband light to pass.

[0041] The combiner 120 combines the lights emitted from the light sources LDV1, LDV2, LDG, and LDW, and allows the combined lights to enter the light guide 210. The combiner 120 is composed of, for example, a dichroic mirror and a lens. Alternatively, the combiner 120 may be an optical fiber that emits lights incident from multiple incident ends to one emission end.

[0042] Figure 3 , Figure 4 2 is an example of wavelength characteristics of the narrow-band light generated by the light source unit 100 . Figure 3 This is an example of wavelength characteristics when light sources LDV1 and LDG emit light. Figure 4 This is an example of wavelength characteristics when the light sources LDV2 and LDG emit light.

[0043] The light source unit 100 generates narrowband light having a peak wavelength between a band including a maximum and a band including a minimum on the absorption coefficient HBC of hemoglobin. The maximum in the absorption coefficient HBC is near a wavelength of 415nm, and the minimum is near a wavelength of 500nm. The band including the maximum is a prescribed wavelength range including the maximum, and the band including the minimum is a prescribed wavelength range including the minimum. For example, the band including the maximum to the band including the minimum is 400nm to 520nm.

[0044] Specifically, light sources LDV1 and LDV2 generate first narrowband light NV1 and second narrowband light NV2, respectively. When the visible light band is divided into a blue region, a green region, and a red region, the first narrowband light NV1 has a peak wavelength in the blue region. The second narrowband light NV2 has a peak wavelength in the blue region at a position closer to the longer wavelength side than the first narrowband light. Figure 3 , Figure 4In the example, NV1 has a peak wavelength of 415nm, and NV2 has a peak wavelength of 430nm. The peak wavelength of NV1, 415nm, is the peak wavelength of blue narrowband light used in conventional NBI. The peak wavelength of NV2, 430nm, is a wavelength obtained by shifting the peak wavelength of NV1, 415nm, toward the long wavelength side. In addition, the peak wavelength of NV1 only needs to be within the range of 400nm to 420nm, and the peak wavelength of NV2 only needs to be within the range of 420nm to 450nm.

[0045] The light source LDG generates third narrowband light NG. The third narrowband light NG has a peak wavelength in the green region. Figure 4 In the example, the third narrowband light NG has a peak wavelength of 540 nm. The peak wavelength of NG, 540 nm, is the peak wavelength of the green narrowband light used in conventional NBI. In addition, the peak wavelength of NG only needs to be in the range of 530 to 550 nm. In addition, the light quantity ratio between NV1 and NG, and the light quantity ratio between NV2 and NG can be arbitrary.

[0046] Figure 5 This is an example of wavelength characteristics when light sources LDV1, LDV2, and LDG emit light. The weight coefficient of the light amount of the second narrowband light NV2 relative to the light amount of the first narrowband light NV1 is set to α. The light amount ratio of NV1 and NV2 is expressed as (1-α): α, where α is a real number of 0≤α≤1. The light source control unit 312 controls the light amount ratio of NV1 and NV2 by controlling the weight coefficient α. In addition, Figure 3 Corresponding to the case of α=0, Figure 4 This corresponds to the case where α = 1. That is, even when NV1 or NV2 is turned off, it is also included in the light emission control based on weighting.

[0047] According to the present embodiment described above, a first narrowband light NV1 and a second narrowband light NV2 having a peak wavelength on the long wavelength side thereof are used. Since NV2 has a longer wavelength than NV1, the degree of scattering in the tissue is less than that of NV1, and it penetrates deeper from the tissue surface than NV1. By using two narrowband lights with different degrees of scattering, even when the forward and backward scattering states of histological changes are different, appropriate illumination can be performed. This point will be described below together with the description of the operation of the processing unit 310.

[0048] 3. Processing Department

[0049] Figure 6 2 is a detailed configuration example of the processing unit 310 . The processing unit 310 includes a state recognition unit 311 , a light source control unit 312 , and an image output unit 313 .

[0050] The state recognition unit 311 uses the camera image generated based on the camera signal to recognize the state of the living body, and outputs the state recognition information as a result. The state recognition unit 311 may generate the camera image for the recognition process, or may use the camera image generated by the image output unit 313. The light source control unit 312 controls the wavelength characteristics of the illumination light based on the state recognition information. Specifically, the light source control unit 312 controls the wavelength characteristics of the illumination light as follows. Figure 3 , Figure 4 Alternatively, the light source control unit 312 switches between the first narrowband light NV1 and the second narrowband light NV2. Figure 5 In this way, the weighting of the first narrowband light NV1 and the second narrowband light NV2 is changed.

[0051] In this way, even when the front and rear scattering states of the histological change are different, the state recognition unit 311 can recognize whether it is the state before the change or the state after the change. Moreover, the light source control unit 312 can control the wavelength characteristics of the illumination light based on the recognition result. Thus, appropriate illumination corresponding to the state of the living body can be performed. Specifically, in the case where the subject of interest is difficult to visually recognize due to the change in the scattering state, the degree of scattering can be changed by changing the wavelength of the narrow-band light. Thus, the visual recognition of the subject of interest can be restored.

[0052] If using Figure 3 As described in , etc., narrow-band light has a peak wavelength from a band containing a maximum to a band containing a minimum in the light absorption characteristics of hemoglobin. That is, the peak wavelength of the narrow-band light is controlled in a wavelength region where the light absorption of hemoglobin is relatively large. The subject of interest is a subject containing hemoglobin, typically a blood vessel. Narrow-band light can capture a blood vessel image at a depth corresponding to the peak wavelength, but when the state of light scattering changes, the visual recognition of the blood vessel image decreases. At this time, by changing the peak wavelength, the light can reach the blood vessel, and the visual recognition of the blood vessel image can be improved.

[0053] Here, the state of the living body is the state of the same type of part, and is a state in which at least the scattering intensity of light changes before and after the state changes. More specifically, the state of the living body is a state accompanied by histological changes before and after the state changes. As histological changes, for example, changes in tissue thickness or changes in intercellular bonding of tissues can be envisioned.

[0054] The state identification information is information indicating the state of the recognized living body. For example, the state identification unit 311 identifies which state is one of a plurality of states and outputs a flag, index, or identification data indicating the recognized state as the state identification information.

[0055] In addition, in the present embodiment, the first narrowband light NV1 has a peak wavelength in the blue region, and the second narrowband light NV2 has a peak wavelength at a position closer to the longer wavelength side than the first narrowband light NV1. That is, the light source control unit 312 controls the wavelength characteristics of the illumination light by shifting the peak wavelength in the blue region toward the longer wavelength side.

[0056] Since the first narrowband light NV1 has a peak wavelength in the blue region, it is possible to capture blood vessel images of the surface layer of tissues such as the mucosal surface. However, when scattering becomes stronger due to histological changes, the contrast of the blood vessel image is reduced due to scattering, or the scattered light appears similar to other types of lesions.

[0057] According to this embodiment, in a state where scattering is relatively strong, the second narrowband light NV2 having a lower scattering degree than the first narrowband light NV1 can be shifted. Thus, the illumination light reaches the depth of the blood vessel that it should reach, thereby easily improving the contrast of the blood vessel image or easily distinguishing the type of lesions.

[0058] In the present embodiment, the peak wavelength of the first narrowband light NV1 is within a range of 400 nm to 420 nm. The state recognition unit 311 recognizes whether the gastric mucosa is sterilized using at least the captured images captured by the first narrowband light NV1 and the third narrowband light NG.

[0059] Since the wavelength of 400nm to 420nm is near the maximum in the absorption coefficient of hemoglobin HBC, the first narrowband light NV1 can image superficial blood vessels such as mucous membranes with high contrast. By using the first narrowband light NV1 and the third narrowband light NG, special light observation called NBI can be performed.

[0060] NBI is used to diagnose gastric cancer, but the visual recognizability of gastric cancer is different before and after the sterilization of Helicobacter pylori. Specifically, histological changes occur in the gastric mucosa due to sterilization, and as a result, the degree of scattering of the first narrow-band light NV1 in the gastric mucosa becomes larger, and it is difficult for the first narrow-band light NV1 to reach the surface blood vessels. In addition, in NBI, inflammation of the gastric mucosa appears as a white area, but sometimes gastric cancer after sterilization appears as a suspected white area. The white area is an area that looks whiter than the surrounding area. When the white area is visible, the doctor suspects inflammation of the gastric mucosa, so it is difficult to distinguish between gastric cancer after sterilization and inflammation.

[0061] According to this embodiment, when the state recognition unit 311 recognizes that the gastric mucosa is sterilized, the light source control unit 312 can generate the second narrowband light NV2 having a longer wavelength than the first narrowband light NV1. Thus, the second narrowband light NV2 reaches the surface blood vessels, thereby improving the visibility of sterilized gastric cancer.

[0062] In addition, in this embodiment, if using Figure 8 As described later, the light source unit 100 may generate a first illumination light including narrowband light and a second illumination light as white light. The state recognition unit 311 may also use a video image captured by the second illumination light to recognize the state of the living body, and the light source control unit 312 controls the wavelength characteristics of the first illumination light based on the state recognition information.

[0063] In this way, when the living state is easily recognized by the one using the white light image, the living state can be recognized accurately. Furthermore, by controlling the wavelength of the special light according to the recognition result, the wavelength selection suitable for the living state can be realized with higher accuracy.

[0064] In addition, in this embodiment, if using Figure 8 As will be described later, the state recognition unit 311 may also recognize inflamed mucous membranes. That is, the state recognition unit 311 may also recognize whether or not there is inflammation in the mucous membrane captured in the image.

[0065] The inflamed mucosa scatters light more strongly than the normal mucosa, so it appears as a white area in NBI observation. Therefore, the visual recognition of blood vessels or lesions under the inflamed mucosa is reduced. In the white light image, the inflamed mucosa is photographed as an area with strong red, so it can be identified based on the color of the image. Moreover, when the inflamed mucosa is detected, the light source control unit 312 emits the second narrow-band light NV2, thereby enabling the second narrow-band light NV2 to reach under the inflamed mucosa. As a result, in NBI observation, the visual recognition of blood vessels or lesions under the inflamed mucosa can be improved.

[0066] In addition, in this embodiment, when the state recognition unit 311 detects that the state of the living body is the first state, the light source control unit 312 sets the weight coefficient α to the first weight coefficient. Figure 5 As described above, α is a weight coefficient of the light amount of the second narrow-band light NV2 relative to the light amount of the first narrow-band light NV1. When the state recognition unit 311 detects that the state of the living body is a second state different from the first state, the light source control unit 312 sets the weight coefficient α to a second weight coefficient greater than the first weight coefficient. The second state is a state in which the scattering of the illumination light in the mucous membrane of the living body is stronger than the first state.

[0067] In this way, when the second state in which the scattering of the illumination light in the mucosa is relatively strong is detected, the weight of the second narrow-band light NV2 on the long wavelength side can be increased. As a result, the scattering degree of the narrow-band light in the mucosa is reduced, so that the visual recognition of the surface blood vessels and the like can be ensured in the second state as in the first state.

[0068] In addition, in this embodiment, if using Fig. 9As described later, the state recognition unit 311 can also estimate the proximity between the camera unit 200 and the living body. The light source control unit 312 can also control the wavelength characteristics of the illumination light based on the state recognition information and the proximity. The proximity is the distance between the front end of the lens body and the surface of the object. For example, the proximity is estimated based on the focus position of the objective lens 230 or the zoom ratio of the objective lens 230.

[0069] The doctor performs screening while moving the scope in the living body. When an area suspected of being a lesion is found during screening, the doctor moves the scope close to the area for detailed observation. According to this embodiment, the wavelength characteristics of the illumination light are controlled by using the proximity, so that the wavelength control linked to the observation state can be performed. For example, in screening, normal NBI illumination can be performed regardless of the state of the living body, and when a specified state such as a sterilized mucosa is detected during detailed observation, the weight coefficient α of the second narrow-band light NV2 is increased.

[0070] As a method for the state recognition unit 311 to recognize the living body state, a recognition method using an image recognition algorithm or a recognition method using machine learning such as AI (Artificial Intelligence) can be adopted.

[0071] In the image recognition algorithm, the state of a living body is detected based on, for example, the feature quantity of an image or the shape of an object. The feature quantity is, for example, the color or brightness of an image. The shape of an object is, for example, the structure of blood vessels or the structure of a mucosal surface. The structure of a mucosal surface is, for example, the shape of a lesion such as atrophy or polyps of the gastric mucosa.

[0072] In machine learning, learning images obtained by photographing a living body and the correct answer labels attached to the learning images are used as teaching data to learn a learning model. The correct labels are made by doctors, etc. For example, the correct label is a label indicating whether the gastric mucosa is sterilized, or a label indicating whether the mucosa is inflamed, etc. The learning model includes an inference algorithm and parameters. As an inference algorithm, various machine learning algorithms such as neural networks or support vector machines can be used. Parameters are parameters used in the inference algorithm, such as weight coefficients between nodes in a neural network, etc. The learning model after learning is called a learned model.

[0073] The state recognition unit 311 recognizes the state of a living body from a captured image using a learned model. The learned model can be installed as a program or as hardware. When the learned model is described in a program, the processor executes the program to implement the function of the state recognition unit 311.

[0074] The image output unit 313 generates a display image based on the camera signal and outputs the display image to the display unit 400. In the WLI mode, the R channel, G channel, and B channel of the camera signal are input to the R channel, G channel, and B channel of the display image, respectively. In the NBI mode, the B channel of the camera signal is input to the B channel and G channel of the display image, and the G channel of the camera signal is input to the R channel of the display image. In the case where the camera element 240 is a color image sensor, the image output unit 313 further performs interpolation processing, etc. The WLI mode and the NBI mode can be set by the user via the external I / F unit 500, for example, or can be set by using Fig. 9 As described above, the mode settings are set according to the proximity between the scope and the subject. The image output unit 313 generates a display image based on these mode settings.

[0075] In addition, the control device 300 including the processing unit 310 may also be configured as follows. That is, the control device 300 includes a memory storing information and a processor that operates based on the information stored in the memory. The information is, for example, a program and various data. The processor includes hardware. The processor uses a camera image generated based on a camera signal to identify the state of the living body, outputs state recognition information indicating the state of the living body, and controls the wavelength characteristics of the illumination light based on the state recognition information.

[0076] The processor can realize the functions of each part through separate hardware, or can realize the functions of each part through integrated hardware. For example, the processor includes hardware, and the hardware can include at least one of a circuit for processing digital signals and a circuit for processing analog signals. For example, the processor can be composed of one or more circuit devices and one or more circuit elements mounted on a circuit substrate. One or more circuit devices are, for example, ICs, etc. One or more circuit elements are, for example, resistors, capacitors, etc. The processor can also be, for example, a CPU (Central Processing Unit). However, the processor is not limited to the CPU, and various processors such as GPU (Graphics Processing Unit) or DSP (Digital Signal Processor) can be used. In addition, the processor can also be an integrated circuit device such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). In addition, the processor can also include an amplifier circuit, a filter circuit, etc. for processing analog signals.

[0077] The memory may be a semiconductor memory such as SRAM or DRAM, or a register, or a magnetic storage device such as a hard disk device, or an optical storage device such as an optical disk device. For example, the memory stores computer-readable commands, which are executed by the processor, so that the function of the processing unit 310 is realized as a process. The command here may be a command set constituting a program, or a command instructing a hardware circuit of the processor to perform an action.

[0078] In addition, the program for implementing the processing performed by the processing unit 310 can be stored in, for example, an information storage medium that is a medium readable by a computer. The information storage medium can be implemented, for example, by an optical disk, a memory card, an HDD, or a semiconductor memory (ROM). The semiconductor memory is, for example, a ROM. The processing unit 310 performs various processes of this embodiment based on the program and data stored in the information storage medium. That is, a program for causing a computer to function as the processing unit 310 is stored in the information storage medium. A computer is a device having an input device, a processing unit, a storage unit, and an output unit.

[0079] Below, use Figure 7 to Figure 9 The flowchart of the present invention describes the order of processing performed by the processing unit 310. In addition, the following description takes the case where the switching between the first narrowband light NV1 and the second narrowband light NV2 is performed according to the state of the living body as an example, but the light intensity ratio of the first narrowband light NV1 and the second narrowband light NV2 may also be switched according to the state of the living body.

[0080] Figure 7 This is a flowchart showing the processing procedure when identifying the living state during NBI observation.

[0081] In step S1, the light source control unit 312 causes the light source unit 100 to emit the first narrowband light NV1 and the third narrowband light NG. In step S2, the imaging element 240 captures an image, and the imaging signal receiving unit 330 receives an imaging signal.

[0082] In step S3, the state recognition unit 311 determines the color tone of the mucosa based on the camera image. Specifically, the state recognition unit 311 determines whether there is white in the white area in the NBI image. In step S4, the state recognition unit 311 identifies whether it is a sterilized mucosa based on the result of the color tone judgment. Since gastric cancer appears as a suspected white area in the sterilized mucosa, the sterilized mucosa can be identified by detecting the white area. In addition, state recognition using machine learning can also be performed in steps S3 and S4.

[0083] In step S4, if it is determined that the mucous membrane is not sterilized, steps S1 to S4 are performed again. In step S4, if it is determined that the mucous membrane is sterilized, in step S5, the light source control unit 312 switches the setting of the wavelength characteristic to the second narrowband light NV2 and the third narrowband light NG. In step S6, the light source control unit 312 causes the light source unit 100 to emit the second narrowband light NV2 and the third narrowband light NG. In step S7, the imaging element 240 performs imaging, the imaging signal receiving unit 330 receives the imaging signal, and the process returns to step S6.

[0084] Figure 8 This is a flowchart showing a processing procedure when a living body state is identified during WLI observation.

[0085] In step S21, the light source control unit 312 causes the light source unit 100 to emit white light. In step S22, the imaging element 240 captures an image, and the imaging signal receiving unit 330 receives an imaging signal.

[0086] In step S23, the state recognition unit 311 determines the color tone of the mucosa based on the camera image. Specifically, the state recognition unit 311 determines whether there is red color of the inflamed mucosa in the white light image. In step S24, the state recognition unit 311 identifies whether it is an inflamed mucosa based on the result of the color tone judgment. In addition, state recognition using machine learning can also be performed in steps S23 and S24.

[0087] If it is determined in step S24 that the mucosa is inflamed, in step S25, the light source control unit 312 sets the wavelength characteristics in the NBI mode to the second narrowband light NV2 and the third narrowband light NG. If it is determined in step S24 that the mucosa is not inflamed, in step S26, the light source control unit 312 sets the wavelength characteristics in the NBI mode to the first narrowband light NV1 and the third narrowband light NG.

[0088] In step S27 , the light source control unit 312 determines whether the WLI mode is switched to the NBI mode. Specifically, it determines whether an operation to switch to the NBI mode is performed via the external I / F unit 500 .

[0089] If it is determined in step S27 that the mode is WLI, the process returns to step S21. If it is determined in step S27 that the mode is switched to NBI, the light source control unit 312 causes the light source unit 100 to emit narrowband light according to the wavelength characteristics set in step S25 or S26 in step S28. In step S29, the imaging element 240 performs imaging, the imaging signal receiving unit 330 receives the imaging signal, and the process returns to step S28.

[0090] Fig. 9This is a flowchart showing a processing procedure when wavelength characteristics are switched using state identification information and proximity.

[0091] In step S41, the light source control unit 312 causes the light source unit 100 to emit the first narrowband light NV1 and the third narrowband light NG. In step S42, the imaging element 240 captures an image, and the imaging signal receiving unit 330 receives an imaging signal.

[0092] In step S43, the state recognition unit 311 determines the color tone of the mucous membrane based on the captured image. In step S44, the state recognition unit 311 determines whether the mucous membrane is sterilized based on the result of the color tone determination.

[0093] In step S44, if it is determined that the mucous membrane is not sterilized, steps S41 to S44 are performed again. In step S44, if it is determined that the mucous membrane is sterilized, in step S45, the light source control unit 312 determines whether the front end of the scope is close to the subject. For example, the focus position or zoom factor of the objective lens 230 is operated via the external I / F unit 500. Based on the focus position or zoom factor set by the operation, the light source control unit 312 determines the degree of proximity.

[0094] If it is determined in step S45 that the front end of the scope and the subject are not close, steps S41 to S44 are executed again. If it is determined in step S45 that the front end of the scope and the subject are close, in step S46, the light source control unit 312 switches the setting of the wavelength characteristics in the NBI mode to the second narrowband light NV2 and the third narrowband light NG. In step S47, the light source control unit 312 causes the light source unit 100 to emit the second narrowband light NV2 and the third narrowband light NG. In step S48, the imaging element 240 performs imaging, the imaging signal receiving unit 330 receives the imaging signal, and the process returns to step S47.

[0095] Above, the embodiments and variations thereof to which the present invention is applied are described, but the present invention is not directly limited to the embodiments or variations thereof. In the implementation stage, the structural elements can be deformed and concretized within the scope of the main purpose of the invention. In addition, various inventions can be formed by appropriately combining the multiple structural elements disclosed in the above-mentioned embodiments and variations. For example, several structural elements can also be deleted from all the structural elements recorded in the embodiments and variations. Furthermore, the structural elements described in different embodiments and variations can also be appropriately combined. In this way, various deformations and applications can be performed within the scope of the main purpose of the invention. In addition, in the specification or the drawings, the term recorded at least once with a different term in a broader sense or synonymous can be replaced with the different term anywhere in the specification or the drawings.

[0096] Explanation of symbols

[0097] 100 light source unit, 110 driving unit, 120 combining unit, 200 imaging unit, 210 light guide, 220 illumination lens, 230 objective lens, 240 imaging element, 300 control device, 310 processing unit, 311 state recognition unit, 312 light source control unit, 313 image output unit, 330 imaging signal receiving unit, 400 display unit, 500 external I / F unit, HBC absorption coefficient, LDG, LDV1, LDV2, LDW light source, NG third narrowband light, NV1 first narrowband light, NV2 second narrowband light

Claims

1. An endoscope device, characterized in that: Include: a light source section that generates narrow-band light as illumination light, the narrow-band light having a peak wavelength between a wavelength band including a maximum wavelength and a wavelength band including a minimum wavelength in the light absorption characteristics of hemoglobin; an imaging unit that outputs an imaging signal based on return light from a living body irradiated with the illumination light; and a processing unit that uses a camera image generated based on the camera signal to identify whether the gastric mucosa is in an unsterilized state or a sterilized state as the state of the living body, outputs state identification information indicating the state of the living body, and controls the wavelength characteristics of the illumination light based on the state identification information, The illumination light includes a first narrowband light and a second narrowband light, the second narrowband light having a peak wavelength at a position closer to a longer wavelength side than the first narrowband light, The processing unit sets a weight coefficient of the light amount of the second narrow-band light relative to the light amount of the first narrow-band light to a first weight coefficient when detecting that the state of the living body is the first state; The processing unit sets the weight coefficient to a second weight coefficient greater than the first weight coefficient when detecting that the state of the living body is a second state different from the first state.

2. The endoscope device according to claim 1, characterized in that The light source unit generates the illumination light including at least first narrowband light having a peak wavelength in a blue region and second narrowband light having a peak wavelength on the longer wavelength side than the first narrowband light.

3. The endoscope device according to claim 2, characterized in that: The light source unit generates the illumination light further including a third narrow-band light having a peak wavelength in a green region, A peak wavelength of the second narrowband light is between a peak wavelength of the first narrowband light and a peak wavelength of the third narrowband light.

4. The endoscope device according to claim 2, characterized in that: The peak wavelength of the first narrowband light is in the range of 400 nm to 420 nm.

5. The endoscope device according to claim 3, characterized in that: The processing unit recognizes whether the gastric mucosa is in an unsterilized state or a sterilized state as the state of the living body, using the captured image captured by at least the first narrowband light and the third narrowband light.

6. The endoscope device according to claim 1, characterized in that: The light source unit generates first illumination light including the narrow-band light and second illumination light which is white light. The processing unit recognizes the state of the living body using the captured image captured by the second illumination light, and controls the wavelength characteristics of the first illumination light based on the state recognition information.

7. The endoscope device according to claim 1, characterized in that: The processing section recognizes an inflamed mucosa as a state of the living body.

8. The endoscope device according to claim 1, characterized in that: The second state is a state in which scattering of the illumination light in the mucous membrane of the living body is stronger than that in the first state.

9. The endoscope device according to claim 1, characterized in that: The processing unit estimates a proximity between the imaging unit and the living body, and controls the wavelength characteristic of the illumination light based on the state recognition information and the proximity.

10. A control device, characterized in that: Include: a processing unit that causes the light source unit to generate narrow-band light as illumination light, the narrow-band light having a peak wavelength between a band including a maximum and a band including a minimum in the light absorption characteristics of hemoglobin; and an imaging signal receiving unit that receives an imaging signal from an imaging unit that outputs the imaging signal based on return light from a living body irradiated with the illumination light, The processing unit uses a camera image generated based on the camera signal to identify whether the gastric mucosa is in an unsterilized state or a sterilized state as the state of the living body, outputs state identification information indicating the state of the living body, and controls the wavelength characteristics of the illumination light based on the state identification information. The illumination light includes a first narrowband light and a second narrowband light, the second narrowband light having a peak wavelength at a position closer to a longer wavelength side than the first narrowband light, The processing unit sets a weight coefficient of the light amount of the second narrow-band light relative to the light amount of the first narrow-band light to a first weight coefficient when detecting that the state of the living body is the first state; The processing unit sets the weight coefficient to a second weight coefficient greater than the first weight coefficient when detecting that the state of the living body is a second state different from the first state.

11. An information storage medium storing a program, wherein the program causes a computer to execute the following steps: causing the light source unit to generate narrow-band light as illumination light, the narrow-band light having a peak wavelength between a band including a maximum and a band including a minimum in the light absorption characteristics of hemoglobin; causing the imaging unit to output an imaging signal based on the return light from the living body irradiated with the illumination light; using a captured image generated based on the captured image signal to identify whether the gastric mucosa is in an unsterilized state or in a sterilized state as the state of the living body, and outputting state identification information indicating the state of the living body; as well as controlling the wavelength characteristics of the illumination light based on the state identification information, in, The illumination light includes a first narrowband light and a second narrowband light, the second narrowband light having a peak wavelength at a position closer to a longer wavelength side than the first narrowband light, When the state of the living body is detected to be the first state, a weight coefficient of the light amount of the second narrow-band light relative to the light amount of the first narrow-band light is set to a first weight coefficient; When the state of the living body is detected to be a second state different from the first state, the weight coefficient is set to a second weight coefficient greater than the first weight coefficient.

Images