JP6669539B2 - Image processing apparatus, operation method of image processing apparatus, and image processing program - Google Patents

Description

  The present invention relates to an image processing apparatus that processes images used for diagnosing atrophic gastritis, an operation method of the image processing apparatus, and an image processing program.

  In the medical field, diagnosis using an endoscope system including a light source device, an electronic endoscope, and a processor device has been widely performed. In particular, hospitals that perform gastrointestinal endoscopy require a definitive diagnosis before performing endoscopic treatment such as endoscopic mucosal resection or endoscopic submucosal dissection, and observe the state of mucosal changes Therefore, there is an increasing need to observe an endoscope image in which changes are emphasized.

  Optical methods, digital methods, optical digital methods, and dye scattering methods are examples of observation methods that emphasize changes. The digital method FICE (Flexible Spectral Imaging Color) is used for observing and picking up fine blood vessels in the surface structure. Enhancement (registered trademark), NBI (Narrow Band imaging, registered trademark), which is an optical digital method, or indigocamine spraying or Lugol spraying, which is a dye spraying method, are used. An endoscope generally uses white light to capture an image, while FICE extracts a spectral image by performing signal processing to make it easier to see the properties of a tissue or blood vessels. On the other hand, the NBI narrows down and irradiates white light using an optical filter, thereby acquiring and highlighting the reflected spectrum information of the living body.

  Originally, an endoscope image tends to be concentrated in a red part and a hue in a narrow range, and there is little difference between a lesioned part and a normal part, and processing for emphasizing the difference is desired. Therefore, a hue / color enhancement type that emphasizes hue and saturation or a hue enhancement type that emphasizes a difference in hue has been proposed (for example, Patent Document 1). According to Patent Document 1, in the hue emphasis type, a color vector of an average color is obtained in a two-dimensional (RY and BY) color space in which an influence of luminance is removed from an image, and the color vector is radially formed around the position of the color vector. The hue range is expanded to the position where it was moved. On the other hand, in the hue cooperation type, the hue is expanded around the position of the color vector. In addition, it is disclosed that, in the case where the pigment dispersion is performed and the case where the pigment dispersion is not performed, since the hue is different, a table for converting is changed between the case where the pigment dispersion is performed and the case where the pigment dispersion is not performed. I have.

  In addition, an endoscope using narrow-band light irradiates light with a wavelength that is easily absorbed by hemoglobin in the blood for observation. It becomes an image. When the gastric mucosa in the endoscopic image is normal, the surface mucosal layer is thick, so most of the light is absorbed by this mucosal layer and then reflected, Blood vessels can hardly be observed on an endoscopic image. On the other hand, in the case of gastric mucosa in which atrophic gastritis has progressed, the change in the internal structure of the gastric mucosa due to the progression of atrophic gastritis is due to the thinning of the mucosal layer due to the decrease in gastric gland cells. On the image, the mucosal muscularis of a color close to white is seen through, and the color of the atrophic mucosal part is a color faded from the normal part. Further, in the atrophic mucosa, blood vessels in the submucosal layer can be seen through as the mucosal layer becomes thinner with atrophy. Therefore, in the diagnosis of gastric lesions based on atrophic gastritis, the degree of atrophy progression is determined and the boundary between a normal part and a gastritis part is determined using the above characteristics.

JP-A 1-113018

  However, even with an endoscope using narrow-band light, when atrophy has advanced to a high degree (for example, in the case of atrophy included in group C or group D in an ABC examination), an endoscopic image is obtained. Although the above characteristics can be clearly observed above, when atrophy has not progressed much (for example, in the case of atrophy included in Group B or Group C in an ABC examination), it can be observed on an endoscopic image. The difference between the atrophied part and the normal part is slight, and it may be difficult to determine the degree of atrophy progression and the boundary between the normal part and the gastritis part. Therefore, it is required to clarify the difference between the above features on an endoscopic image so that the boundary between the normal part and the gastritis part can be observed.

  An object of the present invention is to provide an image processing apparatus, an operation method of the image processing apparatus, and an image processing program that can emphasize a change in color of a mucous membrane or the like that can occur when the stomach atrophy due to atrophic gastritis.

An image processing apparatus according to the present invention includes an image acquisition unit configured to acquire an endoscope image formed by an image signal including a narrow-band image signal, and a three-dimensional color including a coordinate axis of at least one component of luminance and brightness. A color difference vector for obtaining a color difference vector, which is a three-dimensional vector in a three-dimensional color space, from a reference color representing a color of a normal portion of an endoscope image to a color of each pixel of interest in the endoscope image in space; The acquisition unit and, in this color space, the color of each pixel of interest is added to the reference color in the same direction as the color difference vector of the pixel of interest, and the color difference expansion vector of the vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector. A color difference extension unit that performs a color difference extension process for converting to a color, and an output unit that outputs an endoscope image in which the color difference between a normal portion and an abnormal portion obtained by applying the color difference extension process to all pixels of the endoscope image is extended. equipped, color The vector acquisition unit uses a reference color having a higher luminance value as the representative luminance value increases, corresponding to a representative luminance value representing the endoscope image among a plurality of predetermined reference colors, and using the representative luminance value. The color difference vector is obtained using a reference color having a lower luminance value as the value becomes lower .

An operation method of the image processing apparatus according to the present invention is an operation method of an image processing apparatus including an image acquisition unit, a color difference vector acquisition unit, a color difference expansion unit, and an output unit, wherein the image acquisition unit has a narrow band. An image acquisition step of acquiring an endoscope image generated by an image signal including the image signal, and a color difference vector acquisition unit configured to narrow the color difference vector in a three-dimensional color space including a coordinate axis of at least one component of luminance and brightness. A three-dimensional vector in a three-dimensional color space from a reference color representing a color of a normal part of an endoscope image generated by an image signal including a band image signal to a color of each pixel of interest in the endoscope image. a chrominance vector obtaining step of obtaining certain chrominance vector, the color difference expansion unit in the color space, the color of each pixel of interest is the same direction as the color difference vector of the target pixel and the vector quantity of chrominance vector A color difference extension step of performing a color difference extension process of converting a color difference extension vector of a vector amount to which the adjustment is added to a reference color, and the output unit performs the color difference extension process on all pixels of the endoscope image. An output step of outputting an endoscope image in which the color difference between the normal part and the abnormal part is expanded, and the color difference vector obtaining step includes a step of obtaining a representative luminance value representing the endoscope image among a plurality of predetermined reference colors. Correspondingly, a color difference vector is obtained using a reference color having a higher luminance value as the representative luminance value increases, and using a reference color having a lower luminance value as the representative luminance value decreases .

The image processing program of the present invention includes a computer, an image obtaining section that obtains an endoscopic image generated by the image signal containing the narrowband image signals, the axes of at least one component of the brightness and contrast 3 In a three-dimensional color space, a color difference vector that is a three-dimensional vector in a three-dimensional color space from a reference color representing a color of a normal part of an endoscope image to a color of each pixel of interest in the endoscope image is obtained. A color difference vector obtaining unit, and in this color space, the color of each pixel of interest is set in the same direction as the color difference vector of the pixel of interest, and the color difference extension vector of the vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is used as the reference color. A color difference expansion unit that performs color difference expansion processing that converts the color into a color added to the image, and an endoscope image obtained by expanding the color difference between a normal part and an abnormal part obtained by applying the color difference expansion processing to all pixels of the endoscope image To function as an output unit for outputting color difference vector acquisition unit, in response to the representative luminance value representing the out endoscopic image of a plurality of reference color predetermined higher the luminance value surrogate Table luminance value increases Using a reference color, a color difference vector is obtained using a reference color having a lower luminance value as the representative luminance value decreases .

  “Narrowband image signal” refers to an image signal obtained by imaging a specimen irradiated with narrowband light, and “image signal including narrowband image signal” refers to a specimen irradiated with light including narrowband light. Means an image signal obtained by imaging the image.

  The “color space” refers to a space in which colors can be designated by coordinates, and the “color space including luminance” refers to a three-dimensional color space including luminance components. Luminance refers to a color component representing the degree of brightness. Similar to luminance, lightness is used as a component that represents the degree of brightness, and color spaces include a color space having a coordinate axis of a component represented by luminance and a color space having a coordinate axis of a component represented by lightness. However, in this specification, neither luminance nor brightness is distinguished as a component representing the degree of brightness.

  The “color difference vector” refers to a three-dimensional vector representing a difference between a vector representing a position of a reference color in a three-dimensional color space and a vector representing a position of a color of a pixel of interest.

Also, the color difference expansion unit increases the emphasis amount as the vector amount of the color difference vector becomes larger when the vector amount of the color difference vector is smaller than the first threshold, and when the vector amount of the color difference vector is larger than the first threshold, It is preferable that the emphasis amount is reduced as the vector amount increases.

  In addition, the image processing apparatus may further include a storage unit that stores a plurality of reference colors in advance, and the color difference vector obtaining unit may include a representative color value corresponding to a representative luminance value representing an endoscope image among the plurality of reference colors in the storage unit. A color difference vector may be obtained by using a reference color having a higher luminance value as the luminance value increases, and using a reference color having a lower luminance value as the representative luminance value decreases.

  Further, the representative luminance value of the endoscope image may be an average value of luminance values of all pixels of the endoscope image.

  Further, the reference color may be an average value of all pixels of the endoscope image.

The reference color, which is calculated from at least one or more pixels of the endoscopic image other than the pixels having the color component exceeds a second threshold value of the color components of each picture element of the endoscopic image is desired .

  “A pixel having at least one or more color components exceeding the second threshold” is a color component that exceeds the color of an image that normally appears when an image of a sample is taken, for example, a color at a location where halation or the like occurs. A pixel having a component or a pixel having a color component that appears when an image other than the sample is captured.

  Further, the color space may be any of the Ycc color space, the Lab color space, the Luv color space, the HSB color space, the HSL color space, and the HSV color space.

  Further, it is desirable that the narrow-band image signal is obtained by imaging a sample illuminated with narrow-band light that absorbs more blood than other bands.

  Further, the narrow band image signal is a blue narrow band image signal obtained by imaging a sample illuminated with blue narrow band light whose light absorption for blood is larger than other bands in the blue band, or in the green band. It may be a green narrow-band image signal obtained by imaging a sample illuminated with green narrow-band light that absorbs more blood than other bands.

  Furthermore, when the endoscopic image is an image of the inner wall of the stomach, the normal part is normal mucosa and the abnormal part is abnormal mucous membrane.

Further, another image processing apparatus of the present invention includes an image acquisition unit that acquires an endoscope image constituted by an image signal including a narrow-band image signal, and a plurality of reference colors representing colors of a predetermined normal part. Of the endoscope image, the higher the average value, the higher the reference value, the lower the average value . In a three-dimensional color space including a coordinate axis of at least one of the components , a color difference vector that is a three-dimensional vector in a three-dimensional color space from a reference color to the color of each pixel of interest in an endoscope image is obtained. A color difference vector obtaining unit, and in the color space, the color of each pixel of interest is set in the same direction as the color difference vector of the pixel of interest, and the color difference extension vector of the vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is used as the reference color. Add A color difference extension unit that performs a color difference extension process for converting to a color, and an output unit that outputs an endoscope image in which the color difference between a normal portion and an abnormal portion obtained by applying the color difference extension process to all pixels of the endoscope image is extended. The color difference expansion unit includes a distance between the color of the abnormal portion and the reference color in the color space as a first threshold, and when the vector amount of the color difference vector is smaller than the first threshold, the larger the vector amount of the color difference vector, When the enhancement amount is increased and the vector amount of the color difference vector is larger than the first threshold, the enhancement amount is reduced as the vector amount increases.

Also, operating method of another image processing apparatus of the present invention, an image acquisition unit, and a color difference vector acquisition unit, and the color difference extension, a method of operating an image processing apparatus having an output unit, the image acquisition unit An image acquisition step of acquiring an endoscope image generated by an image signal including a narrow-band image signal, and a color difference vector acquisition unit configured to perform endoscopic viewing of a plurality of reference colors representing colors of a predetermined normal part. Corresponding to the average value of the brightness values of the mirror image, at least one of the brightness and the brightness is used by using a reference color having a higher brightness value as the average value becomes higher and using a reference color having a lower brightness value as the average value becomes lower. A color difference vector acquisition for acquiring a color difference vector which is a three-dimensional vector in a three-dimensional color space from a reference color to a color of each pixel of interest in an endoscope image in a three-dimensional color space including coordinate axes of two components. Step and color difference The color portion is a color obtained by adding the color of each pixel of interest in the color space in the same direction as the color difference vector of the pixel of interest, and adding a color difference extension vector of a vector amount obtained by adding a vector amount of the color difference vector to the reference color. A color difference extension step of performing a color difference extension process for converting to an output, and an output unit that outputs an endoscope image in which the color difference between a normal part and an abnormal part obtained by applying the color difference extension process to all pixels of the endoscope image is extended. A color difference expanding step, wherein the distance between the color of the abnormal part in the color space and the reference color is set as a first threshold, and when the vector amount of the color difference vector is smaller than the first threshold, the vector amount of the color difference vector Is increased, the enhancement amount is increased. When the vector amount of the color difference vector is larger than the first threshold, the enhancement amount is decreased as the vector amount increases.

Further, another image processing program according to the present invention includes a computer, an image acquisition unit that acquires an endoscope image constituted by an image signal including a narrow-band image signal, and a plurality of images representing a predetermined normal part color. According to the average value of the luminance values of the endoscope image among the reference colors, the higher the average value, the higher the luminance value of the reference color, and the lower the average value, the lower the luminance value, the lower the luminance value, using the reference color. And a color difference that is a three-dimensional vector in the three-dimensional color space from the reference color to the color of each pixel of interest in the endoscope image in the three-dimensional color space including the coordinate axis of at least one component of lightness and brightness. A color difference vector acquisition unit for acquiring a vector, and a color difference extension vector of a vector amount in the color space, in which the color of each pixel of interest is in the same direction as the color difference vector of the pixel of interest and the amount of enhancement is added to the vector amount of the color difference vector. A color difference extension unit that performs color difference extension processing that converts the color to a color that has been added to the reference color, and an endoscope image that has extended the color difference between the normal part and the abnormal part in which the color difference extension processing has been applied to all pixels of the endoscope image An image processing program for functioning as an output unit for outputting a color difference vector, wherein the distance between the color of the abnormal part and the reference color in the color space is set as a first threshold, and the vector amount of the color difference vector is set to the first value. If the vector amount of the chrominance vector is larger than the first threshold, the enhancement amount is increased. If the vector amount of the chrominance vector is larger than the first threshold value, the enhancement amount is decreased as the vector amount is increased.
Further, another image processing apparatus according to the present invention includes an image acquisition unit configured to acquire an endoscope image configured by an image signal including a narrowband image signal, and a coordinate axis of at least one component of luminance and brightness. In a three-dimensional color space, a color difference vector which is a three-dimensional vector in a three-dimensional color space from a reference color representing a color of a normal portion of an endoscope image to a color of each pixel of interest in the endoscope image is represented by A color difference vector obtaining unit to obtain, and a color space of the target pixel in the color space in the same direction as the color difference vector of the target pixel, and a color difference extension vector of a vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector. A color difference expansion unit that performs color difference expansion processing to convert to a color added to the reference color, and an endoscope image in which the color difference between the normal part and the abnormal part obtained by applying the color difference expansion processing to all pixels of the endoscope image is output Output section and It includes reference color is the average value of the pixel of at least one endoscopic image other than the pixels having the color component exceeds a second threshold value of the color component of each pixel of the endoscopic image.

  The “color of the abnormal part” refers to a color that is likely to appear in the abnormal part, and is a color that represents the abnormal part. For example, the color that appears most frequently in the abnormal portion may be used, or the color of the abnormal portion may be averaged.

  The “distance between the color of the abnormal part in the color space and the reference color” refers to the vector amount of the difference vector between the reference color and the color of the abnormal part obtained in the color space.

  According to the present invention, the color of each target pixel of an endoscope image formed by an image signal including a narrow-band image signal is defined as a reference color representing a normal part color and a target color of each target pixel in a color space including luminance. By emphasizing the color difference in the direction of the color difference vector representing the color difference of the color, the difference in color between an abnormal part such as a mucous membrane and a normal part, which may occur when the stomach is atrophied due to atrophic gastritis, and the difference in luminance are taken into account. Can be emphasized.

FIG. 1 is an external view of an endoscope system. FIG. 2 is a block diagram illustrating functions of the endoscope system according to the first embodiment. 5 is a graph showing the spectral intensity of white light. 4 is a graph showing the spectral intensity of special light. FIG. 3 is a block diagram illustrating an internal configuration of an abnormal region emphasis unit. FIG. 9 is a diagram for explaining color difference enhancement in a color space having a luminance component axis. FIG. 7 is a diagram illustrating a relationship between a vector amount of a color difference vector and an enhancement amount. FIG. 7 is a diagram for explaining a difference between color difference enhancement of an abnormal part and color difference enhancement of a bleeding part in a color space. FIG. 7 is a diagram for explaining a difference between color difference enhancement of an abnormal part and color difference enhancement of a color close to a normal part in a color space. The flowchart which shows the flow of a diagnosis of atrophic gastritis. FIG. 9 is a block diagram illustrating functions of the endoscope system according to the second embodiment. 4 is a graph showing a wavelength of a light source.

  As shown in FIG. 1, the endoscope system 10 according to the first embodiment includes an endoscope 12, a universal cord 13, a light source device 14, a processor device 16, a monitor 18, and an input device 20. Have. The endoscope 12 is optically connected to the light source device 14 via the universal cord 13 and is also electrically connected to the processor device 16. The endoscope 12 has an insertion section 21 inserted into a sample, an operation section 22 provided at a base end portion of the insertion section, and a bending section 23 and a distal section 24 provided at a distal end side of the insertion section 21. are doing. By operating the angle knob 22a of the operation section 22, the bending section 23 performs a bending operation. With this bending operation, the distal end portion 24 is directed in a desired direction.

  The operation unit 22 includes a mode changeover switch (mode changeover SW) 22b and a zoom operation unit 22c in addition to the angle knob 22a. The mode switch 22b is used for switching between two types of modes, a normal observation mode and a special observation mode. The normal observation mode is a mode in which white light is used for illumination in the sample. The special observation mode is a mode in which bluish special light is used as illumination in the sample, and is a mode in which a change in the color of the mucous membrane and a see-through of blood vessels that may occur when the stomach atrophy due to atrophic gastritis is emphasized. The zoom operation unit 22c is used for a zoom operation for driving a zoom lens 47 (see FIG. 2) in the endoscope 12 to enlarge the sample.

  The processor device 16 is connected to the monitor 18 and the input device 20. The monitor 18 displays image information and the like. The input device 20 functions as a user interface that receives input operations such as function settings. Note that an external recording unit (not shown) for recording image information and the like may be connected to the processor device 16.

  As shown in FIG. 2, the light source device 14 includes a blue laser light source (445LD) 34 that emits a blue laser light having a center wavelength of 445 nm and a blue-violet laser light source (405LD) 36 that emits a blue-violet laser light having a center wavelength of 405 nm. It is provided as a light source. Light emission from the semiconductor light emitting elements of these light sources 34 and 36 is individually controlled by the light source control unit 40, and the light amount ratio between the light emitted from the blue laser light source 34 and the light emitted from the blue violet laser light source 36 can be changed. It has become. In the normal observation mode, the light source control unit 40 mainly drives the blue laser light source 34 and controls so as to slightly emit blue-violet laser light. In the case of the normal observation mode, the blue-violet laser light source 36 may be driven. However, in this case, it is preferable to keep the emission intensity of the blue-violet laser light source 36 low.

  On the other hand, in the special observation mode, both the blue laser light source 34 and the blue-violet laser light source 36 are driven, and the emission ratio of the blue laser light is set to be larger than the emission ratio of the blue-violet laser light. Controlling. Note that the half width of the blue laser light or the blue-violet laser light is preferably set to about ± 10 nm. As the blue laser light source 34 and the blue-violet laser light source 36, a broad-area InGaN-based laser diode can be used, and an InGaAsN-based laser diode or a GaAsN-based laser diode can also be used. Further, a configuration using a light emitting body such as a light emitting diode may be used as the light source.

  The laser light emitted from each of the light sources 34 and 36 is incident on a light guide (LG) 41 via an optical member (neither is shown) such as a condenser lens, an optical fiber, and a multiplexer. The light guide 41 is incorporated in the light source device 14, the endoscope 12, and the universal cord (cord for connecting the endoscope 12 and the light source device 14) 13. The blue laser light having a center wavelength of 445 nm or the blue-violet laser light having a center wavelength of 405 nm is transmitted to the distal end portion 24 of the endoscope 12 via the light guide 41. Note that a multimode fiber can be used as the light guide 41. As an example, a thin fiber cable having a core diameter of 105 μm, a cladding diameter of 125 μm, and a diameter of 0.3 to 0.5 mm including a protective layer serving as an outer cover can be used.

  Such blue narrow-band light by the blue laser light and the blue-violet laser light has a large absorption for light-absorbing substances in the mucous membrane, specifically, blood (particularly, hemoglobin) contained in a large amount in the digestive tract, and in the special observation mode. When photographed, the difference between the normal mucosal area and the atrophic mucosal area increases.

  The distal end portion 24 of the endoscope 12 has an illumination optical system 24a and an imaging optical system 24b. The illumination optical system 24a is provided with a phosphor 44 to which a blue laser beam having a center wavelength of 445 nm or a blue-violet laser beam having a center wavelength of 405 nm from the light guide 41 is incident, and an illumination lens 45. When the phosphor 44 is irradiated with the blue laser light, the phosphor 44 emits fluorescence. Some blue laser light passes through the phosphor 44 as it is. The blue-violet laser light is transmitted without exciting the phosphor 44. The light emitted from the phosphor 44 is radiated into the sample via the illumination lens 45.

  Here, in the normal observation mode, mainly blue laser light is incident on the phosphor 44, and therefore, as shown in FIG. 3A, blue laser light and fluorescence excited and emitted from the phosphor 44 by the blue laser light are combined. White light is irradiated into the specimen. On the other hand, in the special observation mode, since both the blue-violet laser light and the blue laser light enter the phosphor 44, the blue-violet laser light, the blue laser light, and the blue laser light as shown in FIG. The special light obtained by multiplexing the fluorescent light excited and emitted from 44 is irradiated into the sample. In this special observation mode, the blue component contains a blue-violet laser beam in addition to the blue laser beam having a high emission intensity, so that the special light contains a large amount of the blue component and the wavelength range covers almost the entire visible light range. It is a broadband light.

The phosphor 44 absorbs a part of the blue laser light and excites and emits green to yellow light (for example, YAG (yttrium aluminum garnet) -based phosphor, or BAM (BaMgAl ₁₀ O). ₁₇ ) It is preferable to use a material containing a phosphor). When a semiconductor light emitting element is used as an excitation light source for the phosphor 44 as in the present configuration example, high intensity white light can be obtained with high luminous efficiency, the intensity of the white light can be easily adjusted, and the color of the white light can be easily adjusted. Changes in temperature and chromaticity can be kept small.

  As shown in FIG. 2, the imaging optical system 24b of the endoscope 12 has an imaging lens 46, a zooming lens 47, and an imaging sensor 48. The reflected light from the specimen enters the imaging sensor 48 via the imaging lens 46 and the zooming lens 47. As a result, a reflected image of the sample is formed on the image sensor 48. The zoom lens 47 moves between the telephoto end and the wide end by operating the zoom operation unit 22c. When the zooming lens 47 moves to the wide end side, the reflection image of the specimen is reduced, and when the zooming lens 47 moves to the tele end side, the reflection image of the specimen is enlarged.

  The imaging sensor 48 is a color image sensor, and captures a reflected image of the specimen and outputs an image signal. Note that the image sensor 48 is preferably a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal-Oxide Semiconductor) image sensor. The image sensor used in the present invention is an RGB image sensor having RGB channels in which an RGB color filter is provided on an imaging surface, and performs an R, R, and B color filter by performing photoelectric conversion in each channel. An R image signal is output from the pixel, a G image signal is output from a G pixel provided with a G (green) color filter, and a B image signal is output from a B pixel provided with a B (blue) color filter. .

  The image sensor 48 may be an image sensor having C (cyan), M (magenta), Y (yellow), and G (green) CMYG filters on the imaging surface. In the case of an image sensor provided with a CMYG filter, RGB three-color image signals can be obtained by color conversion from four CMYG color image signals. In this case, it is necessary to provide any one of the endoscope 12, the light source device 14, and the processor device 16 with a color conversion unit for performing color conversion from the four CMYG image signals to the three RGB image signals. is there.

  The image signal output from the image sensor 48 is transmitted to a CDS (correlated double sampling) / AGC (Automatic Gain Control) circuit 50. The CDS / AGC circuit 50 performs correlated double sampling (CDS) and automatic gain control (AGC) on an image signal that is an analog signal. The image signal that has passed through the CDS / AGC circuit 50 is subjected to gamma conversion by a gamma conversion unit 51. As a result, an image signal having a gradation suitable for an output device such as the monitor 18 is obtained. The image signal after the gamma conversion is converted into a digital image signal by an A / D converter (A / D converter) 52. The A / D-converted digital image signal is input to the processor device 16.

  The processor device 16 includes a receiving unit 54, an image processing switching unit 60, a normal light image processing unit 62, a special light image processing unit 64, and an image display signal generating unit 66. The receiving unit 54 receives a digital image signal from the endoscope 12. The receiving section 54 includes a DSP (Digital Signal Processor) 56 and a noise removing section 58. The DSP 56 performs gamma correction and color correction processing on the digital image signal. The noise removing unit 58 removes noise from the digital image signal by performing a noise removal process (for example, a moving average method, a median filter method, or the like) on the digital image signal that has been subjected to gamma correction or the like by the DSP 56. The digital image signal from which the noise has been removed is transmitted to the image processing switching unit 60.

  The image processing switching unit 60 transmits a digital image signal to the normal light image processing unit 62 when the mode is set to the normal observation mode by the mode switching switch 22b, and when the mode is set to the special observation mode, The digital image signal is transmitted to the special light image processing unit 64.

  The normal light image processing unit 62 includes an image acquisition unit 68, a color enhancement unit 70, and a structure enhancement unit 72. The image acquisition unit 68 acquires RGB image data by allocating the inputted RGB three-channel digital image signals to R image data, G image data, and B image data, respectively. Further, the RGB image data may have been subjected to color conversion processing such as 3 × 3 matrix processing, gradation conversion processing, and three-dimensional LUT processing.

  The color emphasizing unit 70 performs various color emphasizing processes on the RGB image data. The structure enhancement unit 72 performs a structure enhancement process such as spatial frequency enhancement on the RGB image data. The RGB image data on which the structure enhancement processing has been performed by the structure enhancement section 72 is input from the normal light image processing section 62 to the image display signal generation section 66 as a normal light image.

  The special light image processing unit 64 includes an image acquisition unit 74, an abnormal region enhancement unit 77, and a structure enhancement unit 78. The image acquisition unit 74 acquires RGB image data in the same manner as the image acquisition unit 68. The abnormal region emphasizing unit 77 performs a color difference expansion process that emphasizes a color difference between a normal mucosal region (normal portion) and an abnormal region (abnormal portion) that may include a lesion such as atrophied mucosa or gastric cancer. Details of the abnormal area emphasizing unit 77 will be described later. The structure enhancement unit 78 performs a structure enhancement process such as a spatial frequency enhancement on the RGB image data on which the color difference expansion process has been performed. The RGB image data subjected to the structure enhancement processing by the structure enhancement unit 78 is input from the special light image processing unit 64 to the image display signal generation unit 66 as a special light image.

  The image display signal generation unit 66 converts the normal light image or the special light image input from the normal light image processing unit 62 or the special light image processing unit 64 into a display image signal for displaying as a displayable image on the monitor 18. I do. The converted display image signal is output to the monitor 18, and the monitor 18 displays the display image signal as a normal light image or a special light image.

  As illustrated in FIG. 4, the abnormal region emphasizing unit 77 includes a color space conversion unit 80, a color difference vector acquisition unit 82, a color difference expansion unit 84, a color space inverse conversion unit 86, and a storage unit 88. When the gastric mucosa on the inner wall of the stomach in the endoscopic image is a normal part, blood vessels in the normal gastric submucosa can hardly be observed on the endoscopic image, but abnormal mucosa such as atrophic mucosa. In the case of (abnormal portion), the mucosal layer becomes thinner due to the decrease in gastric gland cells, and the color of the abnormal portion becomes faded from that of the normal portion because the mucosal muscle plate of a color close to white can be seen through. However, endoscopic images taken of the stomach wall are concentrated in the red part and tend to concentrate in a narrow range in the color space, and the color difference between the normal part and the abnormal part is only for a skilled observer. It is difficult to determine visually. Therefore, a color difference expansion process for expanding the color difference according to the difference between the color of each pixel of the image data and the reference color is performed using the color of the normal mucous membrane as the reference color.

  First, the color space conversion unit 80 converts the R value, the G value, and the B value of each pixel represented in the RGB color space of the RGB image data acquired by the image acquisition unit 74 into a three-dimensional image having a luminance or brightness component. To the value of the color space. A color space having a luminance or brightness component includes a Y-axis representing a luminance component, a Ycc color space having a Cb axis and a Cr axis representing a color difference component, an L-axis representing a brightness component, and an a-axis representing a complementary color component. A Lab color space having a hue and a b-axis, an L-axis representing a lightness component, a Luv color space having a u-axis and a v-axis representing a saturation and a hue component, a hue H / saturation S / lightness B (or lightness V) There is an HSB color space (or an HSV color space) composed of the axes of the components of the above, or an HSL color space composed of the axes of the components of the hue H, the saturation S, and the luminance L. Any color space may be used. Further, the color space may be an RGB color space having no axis representing a component of luminance or brightness. Hereinafter, in the present embodiment, a case will be described in which color difference expansion processing is performed after conversion to a color space having an axis representing a luminance or brightness component. Some color spaces after the conversion have axes representing the components of luminance and lightness. Hereinafter, the luminance will be described as luminance for convenience without distinguishing between luminance and lightness.

  The color difference vector acquisition unit 82 calculates the color difference between the reference color representing the color of the normal mucous membrane, which is the normal part of the endoscope image, and the color of each pixel of interest in the endoscope image in a color space having a luminance axis. Thus, a three-dimensional color difference vector is obtained by subtracting the vector of the reference color position from the vector of the color position of each pixel of interest.

  The color of the normal mucous membrane differs depending on whether the entire endoscopic image is a bright image or a dark image. Therefore, a plurality of reference colors corresponding to the luminance value of the endoscope image are stored in the storage unit 88 in advance as the reference colors, and the reference colors and the respective colors are used by using the reference colors corresponding to the luminance of the endoscope image. Get the color difference vector of the pixel color. These reference colors are to determine colors that are likely to appear statistically on the normal mucous membrane of the endoscopic image from the endoscopic images captured in the past according to various brightness values of the endoscopic image. Can be. Specifically, when the luminance value of the endoscope image is high, the luminance value of the reference color is high, and when the luminance value of the endoscope image is low, the luminance value of the reference color is low. Therefore, a table in which different reference colors are set corresponding to a plurality of brightness values is stored in the storage unit 88, and the reference color corresponding to the brightness value closest to the endoscope image that is the target of the color difference expansion processing is stored. To take out. Alternatively, the reference color when the luminance value is high and the reference color when the luminance value is low are stored, and when the luminance value of the endoscope image that is the target of the color difference expansion process is the luminance value between them. Is obtained by interpolation between the reference color when the luminance value is high and the reference color when the luminance value is low, and when the luminance value of the endoscope image is out of the range, the luminance value is The reference color when the luminance value is high and the reference color when the luminance value is low may be obtained by extrapolation.

  Also, a representative luminance value representing the luminance of all pixels of the endoscope image can be used as the luminance value of the endoscope image. For example, the average value of the luminance values of all the pixels of the endoscope image or the median value of the luminance values of all the pixels of the endoscope image may be used as the representative luminance value.

  The color difference expansion unit 84 uses the color difference vector acquisition unit 82 to determine the color of each pixel of interest in a color space having a luminance axis in order to clarify the difference between a normal portion that is a normal mucosa and an abnormal portion that is an abnormal mucosa. The obtained color difference vector of each pixel of interest is in the same direction as the color difference vector, and the color difference expansion vector of the vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is converted into a color difference enhanced color obtained by adding the reference color to the normal portion. Increase the color difference of the abnormal part.

  The color difference emphasis in the Lab color space having the axis of the luminance (brightness) component will be specifically described with reference to FIG. In FIG. 5, the L axis is a luminance (brightness) component, and the a axis and the b axis are complementary color components. When the position S of the reference color in the Lab color space and the position of the color of the pixel of interest are P, the color difference vector is p. As shown in the following equation (1), the emphasis amount d corresponding to the vector amount | p | of the color difference vector p is changed to the color difference emphasizing color Q extending in the direction of the color difference vector p. In this way, by expanding the color difference between the reference color and each pixel in the same direction as the color difference vector representing the difference between the reference color and the color of each pixel in the Lab color space, the difference between the abnormal part and the normal part is obtained. Can be made natural and clear.

  In addition, pixels having a color close to the reference color, that is, pixels having a color close to the normal mucous membrane are preferably maintained as they are, so the emphasis amount d is reduced. It is preferable to increase the emphasis amount d so that the difference between the two becomes clear. On the other hand, it is more preferable that no emphasis is performed on a portion that largely deviates from the color of the mucous membrane because it is highly likely that the color is not a mucous membrane color, such as a bleeding part or a part where the pigment is applied.

  FIG. 6 shows an example showing the relationship between the enhancement amount d and the vector amount | p |. As shown in FIG. 5, the color difference vector between the typical color and the reference color appearing on the abnormal mucous membrane so that the color changes naturally as a whole and the difference between the color appearing on the abnormal mucous membrane and the reference color becomes clear. When a value close to the vector amount (distance) | p | of p is set as the first threshold value R1 and the vector amount | p | of the color difference vector p is smaller than the first threshold value R1, the vector amount | p | Is larger, the enhancement amount d is increased. When the vector amount | p | of the color difference vector p is larger than the first threshold R1, the enhancement amount d is reduced as the vector amount | p | Specifically, a look-up table that defines the correspondence between the vector amount | p | of the color difference vector and the enhancement amount d is stored in advance in the storage unit 88 for each reference color, and the reference color S and the color difference vector p are stored. Of the emphasis amount d corresponding to the vector amount | p | As described above, by increasing the emphasis amount when the vector amount of the color difference vector is near the first threshold value R1, the color difference between the color of the abnormal mucous membrane and the color of the normal mucous membrane (reference color) is expanded, And do not change colors that are clearly different from the normal mucous membrane color. As a result, the abnormal part can be easily recognized, and the color of the part where a part other than the normal part or the mucous membrane is photographed, such as the normal mucous membrane, can be observed with the original color.

  7A and 7B, the color difference of each pixel after conversion when the amount of enhancement is changed according to the vector amount of the color difference vector between the position S of the reference color in the Lab color space and the position of the color of each pixel. The position of the color space of the emphasized color will be described. P1 in FIG. 7A indicates the position in the color space of the color of the portion considered to be the abnormal mucous membrane, and near the color close to the abnormal mucous membrane, the enhancement amount d1 is increased and the color difference emphasis color is set to Q1. On the other hand, P2 in FIG. 7A indicates the position in the color space of the color of a part considered to be a bleeding part with a large color difference from the normal mucous membrane, and is a color different from the normal mucous membrane color, so that the enhancement amount d2 (<d1 ) Is reduced and the color difference emphasis color is set to Q2.

  Similarly to FIG. 7A, P1 in FIG. 7B indicates the position in the color space of the color of the portion considered to be the abnormal mucous membrane, and near the color close to the abnormal mucosa, the enhancement amount d1 is large and the color difference emphasis color is Q1. To On the other hand, P3 in FIG. 7B indicates a position in the color space of a color close to the normal mucous membrane, and since the color difference from the reference color S is small and close to the color of the normal part, the enhancement amount d3 (<d1) is reduced. The color difference emphasis color is set to Q3.

  The color space inverse conversion unit 86 reconverts the color difference emphasized color obtained by the color difference expansion unit 84 into RGB image data. Further, if necessary, gamma conversion is performed on the RGB image data. As a result, color difference emphasized RGB image data having a gradation suitable for an output device such as the monitor 18 is obtained. The output unit of the present invention includes a color space inverse conversion unit 86 and an image display signal generation unit 66.

  Next, the operation of the endoscope at the time of a series of examinations and the flow of processing in the present embodiment will be described with reference to the flowchart of FIG. First, the normal observation mode is set (S1), and the insertion section 21 of the endoscope 12 is inserted into the sample. While observing the normal light image, the tip 24 is advanced into the sample (S2-N). When the tip 24 of the insertion section 21 reaches the stomach (S2-Y), it is diagnosed whether atrophic gastritis has occurred. (S3). Here, from the normal light image, the mucous membrane has a fading tone, or the boundary between the part where the dendritic deep blood vessels are transparent and the part where it is not transparent (referred to as an endoscopic gland boundary). Can be read (S3-Y), the doctor judges that a pathological finding that a lesion such as gastric cancer has occurred due to atrophic gastritis (S11).

  On the other hand, if the presence of the bleached mucous membrane or the endoscopic gland boundary cannot be read from the normal light image (S3-N), the mode switching is performed in order to more securely diagnose. By operating the switch 22b, the mode is switched to the special observation mode (S4). By switching the special observation mode, special light including both the blue laser light and the blue-violet laser light is emitted. The RGB image data is acquired by the image acquisition unit 74 from the RGB image signals obtained when the special light is emitted.

  First, the color space conversion unit 80 converts the R, G, and B values of each pixel expressed in the RGB color space into, for example, values in the Lab color space (S5). A representative luminance value is determined from the luminance values (L values) of the pixels of all the endoscope images. Next, a reference color corresponding to the representative luminance value is extracted from the storage unit 88, and a color difference vector between each pixel and the reference color is calculated (S6). Further, the look-up table corresponding to the reference color is used to determine the enhancement amount according to the vector amount of the color difference vector. The color of each pixel is converted into a color difference enhanced color obtained by adding the color difference extended vector of the vector amount obtained by adding the enhancement amount in the same direction as the color difference vector to the reference color (S7).

  Based on the image data converted to the color difference emphasizing color, the color space inverse conversion unit 86 returns the color space to the RGB color space, and the special light image is displayed on the monitor 18 (S8).

  On the special light image, when there is no stomach atrophy, the mucous membrane is displayed in a normal color. In this case (S9-N), the doctor judges that there is no occurrence of a lesion such as gastric cancer due to atrophic gastritis (S10). On the other hand, when the atrophy of the stomach is slightly advanced, the color of the atrophy mucosa is displayed in a fading tone (S9-Y). This allows the endoscopic gland boundaries to be clearly displayed. Therefore, even in the actual stomach, even if the color of the atrophic mucosa is not so much displayed in fading color, the doctor judges that the disease is a pathological finding that atrophy such as gastric cancer is caused by atrophic gastritis. (S11).

  Although the case where the reference color is determined according to the luminance value of the endoscope image has been described above, the average value of the colors of all the pixels of the endoscope image may be used. However, the reference color in this case deviates from the color component considered to be different from the mucous membrane color when at least one color component among the color components of all pixels of the endoscope image exceeds a specific value. An average value is calculated for colors having values using a second threshold value, excluding pixels having components of colors exceeding the second threshold value. Areas where a color different from the mucous membrane color appears are, for example, pixels that have color components in areas where halation has occurred, or colors that appear when images other than the specimen are photographed, such as residues, pigment-dispersed areas, or bleeding areas. It is a pixel having a component. The determination of a pixel having a component different from the mucous membrane color among the color components may be made based on RGB values, or may be made after conversion into a color space having a luminance component. Alternatively, a pixel having a color different from the color of the mucous membrane may be determined from a combination of RGB values, and an average value may be calculated excluding pixels having a color different from the color of the mucous membrane. Alternatively, a pixel having a color different from the color of the mucous membrane may be determined from the combination of the color components after the conversion into the color space having the luminance component.

  In the above embodiment, after the RGB color space is converted into a color space having axes representing luminance or lightness components, the color difference expansion process is performed, and the color subjected to the color difference expansion process is converted again into the RGB color space. Although the case has been described, the color difference expansion processing may be performed by the color difference vector acquisition unit 82 and the color difference expansion unit 84 in the RGB color space without converting from the RGB color space to another color space.

  In the above-described embodiment, a case has been described in which special light including blue narrow-band light (blue laser light and blue-violet laser light) having high light absorbency with respect to the mucous membrane absorbing substance is used. On the other hand, light containing green narrow band light (for example, a wavelength component of 540 to 560 nm) having high light absorption may be used.

  In the above embodiment, the case where the light source is a semiconductor light emitting element has been described. In the second embodiment, an endoscope using an LED as the light source will be described with reference to FIGS. 9 and 10. In the second embodiment, the configuration other than the light source device 14 of the endoscope and the illumination optical system 24c of the distal end portion 24 is almost the same as that of the first embodiment, and therefore, the same reference numerals are given and detailed description is omitted. I do. The operation of the endoscope during the examination and the flow of the processing are substantially the same as those in the first embodiment, and thus detailed description is omitted.

  As shown in FIG. 9, the light source device 14 includes a V-LED (Violet Light Emitting Diode) 42a, a B-LED (Blue Light Emitting Diode) 42b, a G-LED (Green Light Emitting Diode) 42c, and an R-LED (Red). The driving of the four-color LEDs 42a to 42d may be controlled by the light source control unit 40. In this configuration, an optical path coupling unit 43 that couples the optical paths of the four colors of light emitted from the four color LEDs 42 a to 42 d is provided, and the light coupled by the optical path coupling unit 43 is a light inserted into the insertion unit 21. The light is radiated into the subject via the guide (LG) 41 and the illumination lens 45. Note that an LD (Laser Diode) may be used instead of the LED.

  As shown in FIG. 10, the V-LED 42a generates violet light Vi having a center wavelength of 405 ± 10 nm and a wavelength range of 380 to 420 nm. The B-LED 42b generates blue light B1 having a center wavelength of 460 ± 10 nm and a wavelength range of 420 to 500 nm. The G-LED 42c generates green light Gr having a wavelength range of 480 to 600 nm. The R-LED 42d generates red light Re having a center wavelength of 620 to 630 nm and a wavelength range of 600 to 650 nm.

The light source control unit 40 turns on the V-LED 42a, the B-LED 42b, the G-LED 42c, and the R-LED 42d in any of the normal observation mode and the special observation mode. Therefore, the observation target is irradiated with light in which the four colors of the purple light Vi, the blue light Bl, the green light Gr, and the red light Re are mixed. The light source control unit 40, in the normal observation mode, violet light Vi, blue light Bl, green light Gr, quantity ratio between red light Re is _{Vi c: Bl c: Gr c} : as a Re _c, each The LEDs 42a to 42d are controlled. On the other hand, the light source control unit 40, the special observation mode, violet light Vi, blue light Bl, green light Ge, the light intensity ratio between red light _{Re Vi s: Bl s: Ge} s: As a Re _s, each The LEDs 42a to 42d are controlled.

  The distal end portion 24 of the endoscope 12 is provided with an illumination optical system 24c and an imaging optical system 24b. The illumination optical system 24c has an illumination lens 45, and the light from the light guide 41 is applied to the observation target via the illumination lens 45. The imaging optical system 24b has substantially the same configuration as in the first embodiment.

  In the first and second embodiments, the case where the processing of the abnormal area emphasizing unit 77 is performed by the processor device 16 has been described. In addition, an image processing program for functioning as the image acquisition unit, the color difference vector acquisition unit, the color difference expansion unit, and the output unit described above is installed, and is recorded on an external recording unit or the like in the processor device 16 by an external computer. The processing of the abnormal region emphasizing unit 77 may be performed on the endoscope image.

Reference Signs List 10 Endoscope system 12 Endoscope 13 Universal cord 14 Light source device 16 Processor device 18 Monitor 20 Input device 21 Insertion unit 22 Operation unit 22a Angle knob 22b Mode switch 22c Zoom operation unit 23 Curved unit 24 Tip unit 24a, 24c Lighting Optical system 24b Imaging optical system 34 Blue laser light source 36 Blue-violet laser light source 40 Light source control unit 41 Light guides 42a to 42d LED
43 optical path coupling unit 44 phosphor 45 illumination lens 46 imaging lens 47 zooming lens 48 imaging sensor 50 CDS / AGC circuit 51 gamma conversion unit 52 A / D converter 54 reception unit 56 DSP
58 Noise removal unit 60 Image processing switching unit 62 Normal light image processing unit 64 Special light image processing unit 66 Image display signal generation unit 68 Image acquisition unit 70 Color enhancement unit 72 Structure enhancement unit 74 Image acquisition unit 77 Abnormal area enhancement unit 78 Structure Emphasis unit 80 color space conversion unit 82 color difference vector acquisition unit 84 color difference expansion unit 86 color space inverse conversion unit 88 storage unit

Claims (13)

An image acquisition unit that acquires an endoscope image constituted by an image signal including a narrowband image signal,
In a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, a reference color representing a color of a normal part of the endoscope image to a color of each pixel of interest in the endoscope image. A color difference vector acquisition unit that acquires a color difference vector that is a three-dimensional vector in the three-dimensional color space ;
In the color space, the color of each pixel of interest is added to the reference color in the same direction as the color difference vector of the pixel of interest, and a color difference extension vector of a vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is added. A color difference expansion unit that performs color difference expansion processing for converting to color,
An output unit that outputs an endoscope image obtained by expanding the color difference between the normal part and the abnormal part, wherein the color difference expansion process is performed on all pixels of the endoscope image,
The color difference vector acquisition unit corresponds to a representative luminance value representing the endoscope image among a plurality of predetermined reference colors, and uses a reference color having a higher luminance value as the representative luminance value increases. An image processing device for acquiring the color difference vector using a reference color having a lower luminance value as the representative luminance value decreases .   When the vector amount of the color difference vector is smaller than a first threshold, the color difference expanding unit increases the enhancement amount as the vector amount of the color difference vector increases, and the vector amount of the color difference vector is smaller than the first threshold. The image processing apparatus according to claim 1, wherein when the vector amount is large, the emphasis amount is reduced as the vector amount increases. Representative luminance value of the endoscope image, the image processing apparatus according to claim 1 or 2, wherein the average value of the luminance values of all the pixels of the endoscopic image. The image processing according to any one of claims 1 to 3 , wherein the color space is one of a Ycc color space, a Lab color space, a Luv color space, an HSB color space, an HSL color space, and an HSV color space. apparatus. The narrow-band image signals, the image processing apparatus of light absorption according to any one of claims 1-4 obtained by imaging the illuminated sample narrowband light more than the other bands for blood. The narrow-band image signal is a blue narrow-band image signal obtained by imaging a sample illuminated with blue narrow-band light, which absorbs more blood than other bands in the blue band, or blood in the green band. 6. The image processing apparatus according to claim 5 , wherein the image processing apparatus is a green narrow-band image signal obtained by imaging a sample illuminated with green narrow-band light having more light absorption than other bands. The endoscopic image, the normal portion is an image obtained by photographing the inner wall of the stomach is normal mucosa, the image processing apparatus according to any one of the abnormal portion is abnormal mucosa claims 1-6. An image acquisition unit, a color difference vector acquisition unit, a color difference expansion unit, an operation method of an image processing apparatus including an output unit,
An image acquisition step in which the image acquisition unit acquires an endoscope image generated by an image signal including a narrowband image signal,
The color difference vector acquisition unit is configured to determine a color of a normal part of an endoscope image generated by an image signal including a narrowband image signal in a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness. A color difference vector obtaining step of obtaining a color difference vector that is a three-dimensional vector in the three-dimensional color space from a reference color to be displayed to a color of each pixel of interest in the endoscope image;
The color difference expansion unit sets a color of the target pixel in the color space in the same direction as the color difference vector of the target pixel, and a color difference expansion vector of a vector amount obtained by adding an enhancement amount to the vector amount of the color difference vector. A color difference expanding step of performing a color difference expanding process of converting the color into a color added to the reference color;
The output unit includes an output step of outputting an endoscope image obtained by expanding the color difference between the normal part and the abnormal part obtained by performing the color difference expansion process on all pixels of the endoscope image,
The color difference vector obtaining step corresponds to a representative luminance value representing the endoscope image among a plurality of predetermined reference colors, and uses a reference color having a higher luminance value as the representative luminance value increases. An operation method of the image processing apparatus for acquiring the color difference vector using a reference color having a lower luminance value as the representative luminance value decreases . Computer
An image acquisition unit that acquires an endoscope image generated by an image signal including a narrowband image signal,
In a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, a reference color representing a color of a normal part of the endoscope image to a color of each pixel of interest in the endoscope image. A color difference vector acquisition unit that acquires a color difference vector that is a three-dimensional vector in the three-dimensional color space ;
In the color space, the color of each pixel of interest is added to the reference color in the same direction as the color difference vector of the pixel of interest, and a color difference extension vector of a vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is added. A color difference expansion unit that performs color difference expansion processing for converting to color,
An image processing program for functioning as an output unit that outputs an endoscope image obtained by expanding the color difference between the normal part and the abnormal part obtained by performing the color difference expansion processing on all pixels of the endoscope image,
The color difference vector acquisition unit corresponds to a representative luminance value representing the endoscope image among a plurality of predetermined reference colors, and uses a reference color having a higher luminance value as the representative luminance value increases. An image processing program for acquiring the color difference vector using a reference color having a lower luminance value as the representative luminance value decreases . An image acquisition unit that acquires an endoscope image constituted by an image signal including a narrowband image signal,
Corresponding to the average value of the luminance values of the endoscope image among a plurality of reference colors representing the color of the predetermined normal part, the higher the average value, the higher the reference value, the higher the reference value, and the higher the average value, In a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, a color of each pixel of interest in the endoscope image is calculated using a reference color having a lower luminance value as the value becomes lower. A color difference vector acquisition unit that acquires a color difference vector that is a three-dimensional vector in the three-dimensional color space up to;
In the color space, the color of each pixel of interest is added to the reference color in the same direction as the color difference vector of the pixel of interest, and a color difference extension vector of a vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is added. A color difference expansion unit that performs color difference expansion processing for converting to color,
An output unit that outputs an endoscope image obtained by expanding the color difference between the normal part and the abnormal part, wherein the color difference expansion process is performed on all pixels of the endoscope image,
The color difference expansion unit sets a distance between the color of the abnormal part and the reference color in the color space as a first threshold, and when a vector amount of the color difference vector is smaller than the first threshold, the color difference vector An image processing apparatus that increases the enhancement amount as the vector amount increases, and decreases the enhancement amount as the vector amount increases when the vector amount of the color difference vector is greater than the first threshold. An image acquisition unit, and a color difference vector acquisition unit, and the color difference extension, a method of operating an image processing apparatus having an output unit,
An image acquisition step in which the image acquisition unit acquires an endoscope image generated by an image signal including a narrowband image signal,
The color difference vector obtaining unit corresponds to an average value of the luminance values of the endoscope image among a plurality of reference colors representing predetermined normal portion colors , and the higher the average value is, the higher the luminance value is. Using a color and a reference color having a lower luminance value as the average value becomes lower, in the three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, from the reference color and the endoscope image. A color difference vector obtaining step of obtaining a color difference vector that is a three-dimensional vector in the three-dimensional color space up to the color of each target pixel in the color space ;
The color difference expansion unit sets a color of the target pixel in the color space in the same direction as the color difference vector of the target pixel, and a color difference expansion vector of a vector amount obtained by adding an enhancement amount to the vector amount of the color difference vector. A color difference expanding step of performing a color difference expanding process of converting the color into a color added to the reference color;
The output unit includes an output step of outputting an endoscope image obtained by expanding the color difference between the normal part and the abnormal part obtained by performing the color difference expansion process on all pixels of the endoscope image,
The color difference expanding step includes, when a distance between the color of the abnormal portion and the reference color in the color space is a first threshold, and when a vector amount of the color difference vector is smaller than the first threshold, the color difference vector An operation method of an image processing apparatus, wherein the enhancement amount is increased as the vector amount increases, and when the vector amount of the color difference vector is larger than the first threshold, the enhancement amount is decreased as the vector amount increases. Computer
An image acquisition unit that acquires an endoscope image constituted by an image signal including a narrowband image signal,
Corresponding to the average value of the luminance values of the endoscope image among a plurality of reference colors representing the color of the predetermined normal part, the higher the average value, the higher the reference value, the higher the reference value, and the higher the average value, In a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, a color of each pixel of interest in the endoscope image is calculated using a reference color having a lower luminance value as the value becomes lower. A color difference vector acquisition unit that acquires a color difference vector that is a three-dimensional vector in the three-dimensional color space up to;
In the color space, the color of each pixel of interest is added to the reference color in the same direction as the color difference vector of the pixel of interest, and a color difference extension vector of a vector amount obtained by adding the enhancement amount to the vector amount of the color difference vector is added. A color difference expansion unit that performs color difference expansion processing for converting to color,
An image processing program for functioning as an output unit that outputs an endoscope image obtained by expanding the color difference between the normal part and the abnormal part obtained by performing the color difference expansion processing on all pixels of the endoscope image,
The color difference expansion unit sets a distance between the color of the abnormal part and the reference color in the color space as a first threshold, and when a vector amount of the color difference vector is smaller than the first threshold, the color difference vector An image processing program for increasing the enhancement amount as the vector amount increases, and reducing the enhancement amount as the vector amount increases when the vector amount of the color difference vector is greater than the first threshold. An image acquisition unit that acquires an endoscope image constituted by an image signal including a narrowband image signal,
In a three-dimensional color space including a coordinate axis of at least one component of luminance and lightness, a reference color representing a color of a normal part of the endoscope image to a color of each pixel of interest in the endoscope image. A color difference vector acquisition unit that acquires a color difference vector that is a three-dimensional vector in the three-dimensional color space;
In the color space, the color of each pixel of interest is added in the same direction as the color difference vector of the pixel of interest, and a color difference extension vector of a vector amount obtained by adding an enhancement amount to the vector amount of the color difference vector is added to the reference color. A color difference expansion unit that performs color difference expansion processing for converting the color
An output unit that outputs an endoscope image obtained by expanding the color difference between the normal part and the abnormal part, wherein the color difference expansion process is performed on all pixels of the endoscope image,
The reference color is an average value of all pixels of the endoscope image other than pixels having at least one color component exceeding a second threshold among color components of each pixel of the endoscope image. Image processing device.