WO2017150071A1 - 補正データ生成方法及び補正データ生成装置 - Google Patents
補正データ生成方法及び補正データ生成装置 Download PDFInfo
- Publication number
- WO2017150071A1 WO2017150071A1 PCT/JP2017/003945 JP2017003945W WO2017150071A1 WO 2017150071 A1 WO2017150071 A1 WO 2017150071A1 JP 2017003945 W JP2017003945 W JP 2017003945W WO 2017150071 A1 WO2017150071 A1 WO 2017150071A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- color
- point
- data
- correction
- predetermined
- Prior art date
Links
- 238000012937 correction Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 40
- 201000010099 disease Diseases 0.000 claims abstract description 37
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 37
- 208000024891 symptom Diseases 0.000 claims description 35
- 230000000875 corresponding effect Effects 0.000 claims description 31
- 239000011159 matrix material Substances 0.000 claims description 21
- 210000001519 tissue Anatomy 0.000 claims description 21
- 102000001554 Hemoglobins Human genes 0.000 claims description 16
- 108010054147 Hemoglobins Proteins 0.000 claims description 16
- 210000004400 mucous membrane Anatomy 0.000 claims description 9
- 230000002596 correlated effect Effects 0.000 claims description 6
- 239000000049 pigment Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 68
- 206010061218 Inflammation Diseases 0.000 description 51
- 230000004054 inflammatory process Effects 0.000 description 51
- 238000011156 evaluation Methods 0.000 description 28
- 238000003384 imaging method Methods 0.000 description 21
- 230000008859 change Effects 0.000 description 19
- 230000003902 lesion Effects 0.000 description 19
- 230000008569 process Effects 0.000 description 19
- 230000002757 inflammatory effect Effects 0.000 description 11
- 230000002159 abnormal effect Effects 0.000 description 7
- 210000004877 mucosa Anatomy 0.000 description 7
- 210000002429 large intestine Anatomy 0.000 description 6
- 239000003086 colorant Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 210000000056 organ Anatomy 0.000 description 5
- 239000004065 semiconductor Substances 0.000 description 5
- 208000007882 Gastritis Diseases 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000000873 masking effect Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 210000004798 organs belonging to the digestive system Anatomy 0.000 description 3
- 230000000241 respiratory effect Effects 0.000 description 3
- 210000002784 stomach Anatomy 0.000 description 3
- 206010009900 Colitis ulcerative Diseases 0.000 description 2
- 208000022559 Inflammatory bowel disease Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 208000037062 Polyps Diseases 0.000 description 2
- 201000006704 Ulcerative Colitis Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000020169 heat generation Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 206010003694 Atrophy Diseases 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 210000001198 duodenum Anatomy 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 208000027866 inflammatory disease Diseases 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 229910001507 metal halide Inorganic materials 0.000 description 1
- 150000005309 metal halides Chemical class 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000000813 small intestine Anatomy 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 210000004291 uterus Anatomy 0.000 description 1
- 229910052724 xenon Inorganic materials 0.000 description 1
- FHNFHKCVQCLJFQ-UHFFFAOYSA-N xenon atom Chemical compound [Xe] FHNFHKCVQCLJFQ-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/00002—Operational features of endoscopes
- A61B1/00004—Operational features of endoscopes characterised by electronic signal processing
- A61B1/00009—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/00002—Operational features of endoscopes
- A61B1/00043—Operational features of endoscopes provided with output arrangements
- A61B1/00055—Operational features of endoscopes provided with output arrangements for alerting the user
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1032—Determining colour for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14546—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring analytes not otherwise provided for, e.g. ions, cytochromes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/1459—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters invasive, e.g. introduced into the body by a catheter
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4842—Monitoring progression or stage of a disease
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4015—Image demosaicing, e.g. colour filter arrays [CFA] or Bayer patterns
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/6002—Corrections within particular colour systems
- H04N1/6005—Corrections within particular colour systems with luminance or chrominance signals, e.g. LC1C2, HSL or YUV
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
- A61B1/05—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances characterised by the image sensor, e.g. camera, being in the distal end portion
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/06—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements
- A61B1/0661—Endoscope light sources
- A61B1/0669—Endoscope light sources at proximal end of an endoscope
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/06—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements
- A61B1/07—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor with illuminating arrangements using light-conductive means, e.g. optical fibres
Definitions
- the present invention relates to a correction data generation method and a correction data generation device.
- the lesion is generally a color different from that of normal mucosal tissue.
- color endoscope apparatuses it is possible for an operator to grasp and diagnose a lesion part slightly different in color from a normal tissue.
- long-term training under the guidance of an expert It is necessary to receive.
- even a skilled operator cannot easily diagnose and diagnose a lesion from a slight color difference, and requires careful work.
- Patent Document 1 Japanese Patent Application Laid-Open No. 2014-18332
- Patent Document 1 describes an apparatus for scoring a lesion part appearing in a photographed image in order to assist an operator in diagnosing the lesion part. ing.
- the apparatus described in Patent Literature 1 performs a tone emphasis process that gives a non-linear gain to a pixel value for each pixel that constitutes a captured image by an electronic endoscope, thereby determining a pixel that is determined as a lesioned part.
- the tone-enhanced pixel data in the RGB space defined by the RGB three primary colors is converted into a predetermined color space such as the HSI color space, HSV color space, etc.
- the degree data is acquired, whether or not the pixel is a lesion is determined based on the acquired hue and saturation data, and an evaluation value (lesion index) is calculated based on the determined number of pixels. .
- the present invention has been made in view of the above circumstances, and an object of the present invention is to provide a correction data generation method for suppressing variations in score values when the same lesioned part is imaged with different electronic endoscope systems. And a correction data generation device.
- a correction data generation method is a method executed by a computer, an acquisition step of acquiring captured image data obtained by capturing an index relating to a predetermined disease, and a response according to the acquired captured image data Based on the arrangement step of arranging the actual shooting data points in a predetermined color space associated with a predetermined disease according to the color component, and the distance between the data point and the predetermined target point in the predetermined color space
- the method includes a calculating step for calculating a correction value for correcting the value of each pixel constituting a captured image by the electronic endoscope, and a storing step for storing the calculated correction value.
- the correction data generation method has a first color that is a color of a living tissue when the symptom level is a predetermined first level for a predetermined disease in the obtaining step.
- First photographed image data obtained by photographing the first index, and a second index having a second color that is the color of the living tissue when the symptom level is the predetermined second level for the disease
- the second captured image data is acquired, and the first and second data points corresponding to the acquired first and second captured image data are arranged in a predetermined color space according to the color component in the arranging step.
- the calculating step based on the distance between the first data point and the predetermined first target point in the predetermined color space and the distance between the second data point and the predetermined second target point.
- the correction value may be calculated.
- the correction data generation method may include a step of accepting a symptom level designation operation by a user and a step of notifying a user of an index corresponding to the accepted symptom level.
- the distance between the first data point and the first target point, and the second data point and the second target point are calculated.
- a matrix coefficient that minimizes the total value with the distance may be calculated as a correction value.
- the predetermined color space is, for example, a two-dimensional color space including an R component axis and a G component axis orthogonal to the R component axis.
- the first color is, for example, the color of the biological tissue when the symptom level is the highest for a disease.
- the first target point is a point located on an axis having a high correlation with the hemoglobin pigment in a predetermined color space.
- the second color is, for example, the color of the living tissue when the disease is healthy.
- the second target point is a point located on an axis having a high correlation with the color of the mucous membrane in the body cavity in a predetermined color space.
- the correction data generation apparatus includes an acquisition unit that acquires captured image data obtained by capturing an index relating to a predetermined disease, and an actual shooting data point corresponding to the acquired captured image data.
- a correction data generation method and a correction data generation device for suppressing variations in score values when the same lesion is imaged with different electronic endoscope systems.
- FIG. 1 It is a block diagram which shows the structure of the electronic endoscope system which concerns on one Embodiment of this invention. It is a figure which shows the flowchart of the special image generation process performed at the time of special mode in one Embodiment of this invention. It is a figure which shows the RG plane on which a pixel corresponding point is plotted in one Embodiment of this invention. It is a figure explaining the reference axis set in an RG plane. It is a figure which shows the example of a display screen displayed on the display screen of a monitor at the time of special mode in one Embodiment of this invention. It is a figure which shows the flowchart of the calibration process performed at the time of calibration mode in one Embodiment of this invention. It is a figure which assists description of the calibration process of FIG.
- FIG. 1 is a block diagram showing a configuration of an electronic endoscope system 1 according to an embodiment of the present invention.
- the electronic endoscope system 1 is a system specialized for medical use, and includes an electronic scope 100, a processor 200, and a monitor 300.
- the processor 200 includes a system controller 202 and a timing controller 204.
- the system controller 202 executes various programs stored in the memory 222 and controls the entire electronic endoscope system 1 in an integrated manner.
- the system controller 202 is connected to the operation panel 218.
- the system controller 202 changes each operation of the electronic endoscope system 1 and parameters for each operation in accordance with an instruction from the operator input from the operation panel 218.
- the input instruction by the operator includes, for example, an instruction to switch the operation mode of the electronic endoscope system 1. In this embodiment, there are a normal mode, a special mode, and a calibration mode as operation modes.
- the timing controller 204 outputs a clock pulse for adjusting the operation timing of each unit to each circuit in the electronic endoscope system 1.
- the lamp 208 emits white light L after being started by the lamp power igniter 206.
- the lamp 208 is a high-intensity lamp such as a xenon lamp, a halogen lamp, a mercury lamp, or a metal halide lamp.
- the white light L emitted from the lamp 208 is limited to an appropriate amount of light through the diaphragm 212 while being collected by the condenser lens 210.
- the lamp 208 may be replaced with a semiconductor light emitting element such as an LD (Laser Diode) or an LED (Light Emitting Diode).
- LD Laser Diode
- LED Light Emitting Diode
- the semiconductor light emitting device has features such as low power consumption and small amount of heat generation compared to other light sources, there is an advantage that a bright image can be acquired while suppressing power consumption and heat generation amount. The ability to obtain a bright image leads to an improvement in the accuracy of the inflammation evaluation value described later.
- the semiconductor light emitting element is not limited to the processor 200 and may be incorporated in the electronic scope 100. As an example, the semiconductor light emitting element may be provided in the distal end portion of the electronic scope 100.
- the motor 214 is mechanically connected to the diaphragm 212 via a transmission mechanism such as an arm or gear not shown.
- the motor 214 is a DC motor, for example, and is driven under the drive control of the driver 216.
- the aperture 212 is operated by the motor 214 to change the opening degree so that the image displayed on the display screen of the monitor 300 has an appropriate brightness.
- the amount of white light L emitted from the lamp 208 is limited according to the opening degree of the diaphragm 212.
- the appropriate reference for the brightness of the image is changed according to the brightness adjustment operation of the operation panel 218 by the operator.
- the dimming circuit that controls the brightness by controlling the driver 216 is a well-known circuit and is omitted in this specification.
- the white light L that has passed through the stop 212 is condensed on the incident end face of an LCB (Light Carrying Bundle) 102 and is incident on the LCB 102.
- White light L incident on the LCB 102 from the incident end face propagates in the LCB 102.
- the white light L propagating through the LCB 102 is emitted from the emission end face of the LCB 102 disposed at the tip of the electronic scope 100 and irradiates the living tissue via the light distribution lens 104.
- the return light from the living tissue irradiated with the white light L forms an optical image on the light receiving surface of the solid-state image sensor 108 via the objective lens 106.
- the solid-state image sensor 108 is a single-plate color CCD (Charge Coupled Device) image sensor equipped with a complementary color checkered filter.
- the solid-state image sensor 108 accumulates an optical image formed by each pixel on the light receiving surface as a charge corresponding to the amount of light, and generates and outputs pixel data of yellow Ye, cyan Cy, green G, and magenta Mg.
- the solid-state imaging element 108 is not limited to a CCD image sensor, and may be replaced with a CMOS (Complementary Metal Oxide Semiconductor) image sensor or other types of imaging devices.
- the solid-state image sensor 108 may also be one equipped with a primary color filter (Bayer array filter).
- a driver signal processing circuit 112 receives pixel data of each pixel obtained by imaging the living tissue irradiated with the white light L from the solid-state imaging device 108 in a frame cycle.
- the driver signal processing circuit 112 outputs pixel data input from the solid-state image sensor 108 to the signal processing circuit 220 of the processor 200.
- “frame” may be replaced with “field”.
- the frame period and the field period are 1/30 seconds and 1/60 seconds, respectively.
- the driver signal processing circuit 112 also accesses the memory 114 and reads the unique information of the electronic scope 100.
- the unique information of the electronic scope 100 recorded in the memory 114 includes, for example, the number and sensitivity of the solid-state image sensor 108, the operable frame rate, the model number, and the like.
- the driver signal processing circuit 112 outputs the unique information read from the memory 114 to the system controller 202.
- the system controller 202 performs various calculations based on the unique information of the electronic scope 100 and generates a control signal.
- the system controller 202 controls the operation and timing of various circuits in the processor 200 using the generated control signal so that processing suitable for the electronic scope connected to the processor 200 is performed.
- the timing controller 204 supplies clock pulses to the driver signal processing circuit 112 according to the timing control by the system controller 202.
- the driver signal processing circuit 112 drives and controls the solid-state imaging device 108 at a timing synchronized with the frame rate of the video processed on the processor 200 side, according to the clock pulse supplied from the timing controller 204.
- the signal processing circuit 220 provided in the processor 200 includes a preprocess circuit 220A, a process circuit 220B, an output circuit 220C, a correction circuit 220D, a scoring circuit 220E, and a mapping circuit 220F.
- the pre-processing circuit 220A performs demosaic processing on the RAW pixel data input at a frame period from the driver signal processing circuit 112 to convert it into RGB pixel data, color matrix processing, white balance adjustment, Hue gain adjustment, and the like. And output to the process circuit 220B.
- the process circuit 220B performs normalization processing, gamma correction, and the like on the pixel data input from the preprocess circuit 220A to generate normal color image data, and outputs the normal color image data to the output circuit 220C.
- the output circuit 220C performs processing such as Y / C separation and color difference correction on the color image data input from the process circuit 220B and converts it into a predetermined video format signal.
- the converted video format signal is output to the monitor 300. As a result, a normal color image of the living tissue is displayed on the display screen of the monitor 300.
- FIG. 2 shows a flowchart of special image generation processing executed in the special mode.
- the special image generation process of FIG. 2 is started when the operation mode of the electronic endoscope system 1 is switched to the special mode.
- FIG. 3 is a diagram for conceptually explaining the operation of the correction circuit 220D, and shows an RG plane (two-dimensional color space) defined by an R axis and a G axis orthogonal to each other.
- the R axis is the axis of the R component (R pixel value)
- the G axis is the axis of the G component (G pixel value).
- pixel data of each pixel in the RGB space defined by the RGB three primary colors is converted into RG pixel data (two-dimensional made up of two types of color components).
- Pixel data (orthographic projection conversion).
- the pixel data of each pixel in the RGB color space is plotted in the RG plane according to the R and G pixel values.
- the pixel data points plotted in the RG plane are referred to as “pixel corresponding points”.
- FIG. 3 for the sake of clarity, only the pixel corresponding points of some pixels are shown instead of the pixel corresponding points of all the pixels.
- the pixel data (three-dimensional data) in the RGB space is orthogonally projected onto the RG plane, and the vertical line drawn on the RG plane from the point in the RGB space corresponding to the pixel data is displayed. It becomes a pixel corresponding point (two-dimensional data).
- FIG. 4 is a diagram for assisting the explanation of the reference axis.
- the R component In the body cavity of a patient to be imaged, the R component is dominant over other components (G component and B component) due to the influence of hemoglobin pigment or the like. Component) becomes strong against other colors (G component and B component).
- the color of the captured image in the body cavity changes according to the imaging condition that affects the brightness (for example, the degree of hitting of the white light L).
- the shaded portion where the white light L does not reach is black (achromatic color, for example, R, G, B is zero or a value close to zero), and the portion where the white light L strikes strongly and is specularly reflected is White (achromatic color, for example, R, G, B is a value close to 255 or 255).
- the pixel value of the abnormal part image increases as the white light L strikes stronger. Therefore, depending on how the white light L hits, the pixel value may take a value that has no correlation with the intensity of inflammation.
- a normal site in a body cavity where inflammation has not occurred is covered with sufficient mucosa.
- an abnormal site in a body cavity where inflammation occurs is not covered with sufficient mucosa.
- the mucous membrane becomes thinner as the inflammation becomes stronger.
- the mucous membrane is basically a white tone, but has a slightly yellowish color, and the color (yellow color) reflected on the image changes depending on the shade (thickness of the mucous membrane). Therefore, the density of the mucous membrane is considered to be one index for evaluating the intensity of inflammation.
- a straight line passing through (50, 0) and (255, 76) is set as one of the reference axes in the RG plane, and (0, 0) and (255, 192) are set as one of the reference axes.
- the former reference axis is referred to as “hemoglobin change axis AX1”, and the latter reference axis is referred to as “mucosal change axis AX2”.
- the plot shown in FIG. 4 is obtained as a result of analysis of a large number of sample images in the body cavity by the inventor.
- Sample images used for analysis include an example of inflammation image with the highest symptom level (example of inflammation image with the most severe level) and an example of inflammation image with the lowest symptom level (image example that is considered to be a substantially normal site) ) And the like are included.
- FIG. 4 only a part of the plot obtained as a result of the analysis is shown for the sake of clarity.
- the number of plots actually obtained as a result of the analysis is much larger than the number of plots shown in FIG.
- the R component becomes stronger with respect to other components (G component and B component) as the abnormal site is more intensely inflamed. Therefore, it is a boundary line between a region where the plot is distributed and a region where the plot is not distributed, and is an axis on the boundary line closer to the R axis than the G axis, in the example of FIG. 4, (50, 0) and (255, 76).
- This axis is the hemoglobin change axis AX1.
- On the hemoglobin change axis AX1, a plot corresponding to an inflammatory site with the highest symptom level photographed under various photographing conditions (for example, the degree of hitting of the white light L) is superimposed.
- On the boundary line passing through) is highly correlated with the lesion with the lowest symptom level (the inflammatory (abnormal) site with the lowest symptom level, which is considered to be a substantially normal (healthy) site) Set as axis.
- This axis is the mucosa changing axis AX2.
- On the mucosal axis AX2, a plot corresponding to an inflammatory site having the lowest symptom level (substantially regarded as a normal site) photographed under various imaging conditions (for example, how white light L hits) is superimposed. .
- the inflammation site with the highest symptom level is accompanied by bleeding.
- the inflammatory site with the lowest symptom level is a substantially normal site and is therefore covered with sufficient mucosa. Therefore, the plot in the RG plane shown in FIG. 4 can be understood as being distributed in a region sandwiched between an axis having the highest correlation with blood (hemoglobin pigment) and an axis having the highest correlation with mucous color. . Therefore, of the boundary lines between the region where the plot is distributed and the region where the plot is not distributed, the boundary line closer to the R axis (the R component is strong) indicates the inflammatory site with the highest symptom level (hemoglobin change axis AX1). The boundary line closer to the G axis (stronger G component) corresponds to the axis indicating the inflammatory site with the lowest symptom level (mucosal change axis AX2).
- the correction circuit 220D selects one target pixel from all the pixels in a predetermined order.
- the correction circuit 220D stores correction matrix coefficients calculated in a calibration mode described later.
- the correction circuit 220D performs processing step S14 (attention) in order to suppress variation in score values (in other words, individual differences of electronic scopes) when the same lesioned part is imaged by different electronic endoscope systems.
- the pixel data (R, G) of the target pixel selected in (Selection of pixel) is corrected using the correction matrix coefficient.
- the correction matrix coefficients will be described in detail in [Operation in calibration mode] described later.
- the angle ⁇ is a parameter that is substantially unaffected by changes in the brightness of the captured image.
- the scoring circuit 220E uses the angle 255 for all the pixels of the current frame so that the value 255 is obtained when the angle ⁇ is zero and the value is zero when the angle ⁇ is ⁇ MAX.
- ⁇ is normalized. Note that ⁇ MAX is equal to the angle formed by the hemoglobin change axis AX1 and the mucosa change axis AX2. As a result, inflammation intensity (8-bit information) falling within the range of 0 to 255 is obtained.
- the scoring circuit 220E calculates an average value (or an integrated value of the inflammation intensity of all the pixels) obtained by averaging the inflammation intensity of all the pixels in the current frame as the inflammation evaluation value of the entire captured image.
- display data display data example: Score: OO
- the mapping circuit 220F displays the display color of each pixel of the current frame on the color map image based on the above table, the value of the inflammation intensity obtained in the processing step S17 (normalization processing). Depending on the color.
- mapping circuit 220F converts the color data of each pixel of the current frame into the display color data determined in the processing step S19 (determining the display color on the color map image). Color map image data composed of pixels displayed in the displayed display color is generated.
- the output circuit 220C causes a normal color image based on the normal color image data input from the process circuit 220B, and the color map image generated in the processing step S20 (color map image data generation).
- the former image data (normal color image data) and the latter image data (color map image data) are added using the ratio of overlaying the color map image based on the data as a coefficient.
- the coefficient setting can be appropriately changed by a user operation. For example, when a normal color image is desired to be displayed darker, the color image data coefficient is set higher. When a color map image is desired to be displayed darker, the color map image data coefficient is set higher.
- the output circuit 220C generates display data of an overlay image of a normal color image and a color map image based on the image data added in processing step S21 (overlay processing) in FIG.
- a masking process for masking the peripheral area is performed, and screen data for monitor display is generated by superimposing an inflammation evaluation value on the mask area generated by the masking process.
- the output circuit 220 ⁇ / b> C converts the generated monitor display screen data into a predetermined video format signal and outputs it to the monitor 300.
- Fig. 5 shows a screen display example in the special mode.
- a captured image in the body cavity an overlay image in which a normal image and a color map image are displayed in an overlay manner
- an image display area A screen with a mask around is displayed.
- an inflammation evaluation value (score) is displayed in the mask area.
- the display form of the captured image in the special mode is not limited to an overlay display of a normal color image and a color map image.
- both the normal color image and the color map image may be displayed with the same size, or one of the normal color image and the color map image is displayed as the main image and the other is smaller than the main image. It may be displayed as an image.
- the inflammation evaluation value (here, the region to be imaged) can be obtained only by performing simple calculation processing without performing nonlinear calculation processing such as tone enhancement processing or complicated color space conversion processing. A value correlated with the increase or decrease of the hemoglobin pigment). That is, the hardware resources necessary for calculating the inflammation evaluation value can be greatly reduced.
- the inflammation evaluation value does not substantially vary depending on the imaging conditions that affect the brightness of the captured image in the body cavity (for example, how the irradiated light hits), the surgeon can make a more objective and accurate determination of inflammation. Can be reduced.
- FIG. 6 shows a flowchart of the calibration process executed in the calibration mode.
- FIG. 7 is a diagram for assisting the description of the calibration process of FIG.
- the calibration process of FIG. 6 is executed at the time of factory shipment, for example, and is started when the operation mode of the electronic endoscope system 1 is switched to the calibration mode.
- preparation work by the worker is performed prior to the execution of the calibration process. Specifically, the operator adjusts the white balance of the electronic endoscope system 1 using a gray card or the like.
- the operator sets the electronic endoscope system 1 on the calibration jig and activates the calibration software on a terminal (PC) connected to the processor 200.
- the worker adjusts the brightness of the captured image by the electronic scope 100.
- the operator manually adjusts the opening of the aperture 212 so that the brightness value of the captured image when the subject for brightness adjustment is captured falls within the target brightness value.
- the luminance value of the captured image can be confirmed on calibration software.
- the operator sets the first index on the calibration jig, thereby fixing and arranging the first index within the angle of view of the electronic scope 100.
- the first index is an index having a first color that is the color of the living tissue when the symptom level is highest for a predetermined disease.
- the first index is a plate-like member to which a color corresponding to a predetermined point (first target point P T1 described later) on the hemoglobin change axis AX1 in the RG plane is applied.
- the second index is an index having a second color that is the color of the living tissue when the predetermined disease is healthy.
- the second index is a plate-like member coated with a color corresponding to a predetermined point (second target point P T2 described later) on the mucous membrane change axis AX2 in the RG plane.
- the second index (surface coated with the second color) is photographed by the electronic scope 100 according to the operation input by the operator, and the photographed image data (RAW format, YUV format, etc.) is stored in the PC. Is input. An operator can photograph the first index and the second index under the same conditions by using a calibration jig.
- processing step S31 imaging of the first index
- present processing step S32 captured image data obtained by imaging the index relating to the predetermined disease is acquired.
- the first actual measurement value of the first index is obtained from the captured image data of the first index captured in the processing step S31 (imaging of the first index) by the calibration software.
- An imaging data point P D1 is calculated.
- an average value of pixels (for example, 200 ⁇ 200 pixels) in the central region in the image of the first index is calculated as the first actual photographing data point P D1 .
- the second actual measurement value of the second index is obtained from the captured image data of the second index captured in the processing step S32 (second index imaging) by the calibration software.
- An imaging data point P D2 is calculated.
- the average value of the pixels (for example, 200 ⁇ 200 pixels) in the central area in the image of the second index is calculated as the second actual imaging data point P D2 , similarly to the first actual imaging data point. Is done.
- a first target point P T1 corresponding to the first actual imaging data point P D1 is set on the hemoglobin change axis AX1, and a second actual imaging is set on the mucosa changing axis AX2.
- a second target point P T2 corresponding to the data point P D2 is set.
- the first target point P T1 corresponds to the first color of the first index
- the second target point P T2 corresponds to the second color of the second index.
- this processing step S36 the distance between the first actual photographing data point P D1 and the first target point P T1 (first distance ⁇ 1 ) and the second actual photographing data point P are obtained by the calibration software.
- a correction matrix coefficient that minimizes the total value of the distance (second distance ⁇ 2 ) between D2 and the second target point P T2 is calculated using a least square method or the like.
- a correction value for correcting the value of each pixel constituting the captured image by the electronic endoscope based on the distance between the actual captured data point and the predetermined target point in the color space is calculated. .
- the correction matrix coefficient may be calculated using the following equation. ⁇ Calculation matrix coefficient calculation example M 11 to M 22 : Correction matrix coefficients REF 11 and REF 21 : First target point P T1 REF 12 , REF 22 : second target point P T2 MEA 11 , MEA 21 : First actual photographing data point P D1 MEA 12 , MEA 22 : second actual photographing data point P D2
- the above formula is derived by modifying the formula for multiplying the measured value (actual imaging data point) by the correction matrix and correcting it to the correction target (target point).
- the first index and the second index related to the target disease are substantially the same when each electronic endoscopic system is photographed. Since a value (a value approximate to the first target point P T1 or the second target point P T2 in any electronic endoscope system) is obtained, the finally calculated inflammation evaluation value is also substantially equal. Become. Therefore, it can be seen that even when the target disease (such as gastritis) is actually photographed by each electronic endoscope system, variation in the inflammation evaluation value can be suppressed.
- the correction target specifically, a specific color related to the target disease is set as the correction target
- it remains in the color data used for the evaluation value calculation of the target disease.
- Errors mainly, variations due to individual differences in the optical parts of the electronic scope 100
- the calculation accuracy of the evaluation value is improved.
- the electronic endoscope system according to the present embodiment brings about the following effects and solutions in the technical field.
- the electronic endoscope system is a diagnostic aid for early detection of inflammatory diseases.
- the degree of inflammation can be displayed on the screen, or the image of the region where the inflammation has occurred can be emphasized so that the surgeon can find mild inflammation that is difficult to visually recognize. .
- mild inflammation is difficult to distinguish from a normal part, the effects brought about by the configuration of the present embodiment regarding the evaluation of mild inflammation become significant.
- an objective evaluation value can be provided to the surgeon as an evaluation of the degree of inflammation, so that the diagnostic difference between the surgeons can be reduced.
- the merit of providing an objective evaluation value according to the configuration of the present embodiment to an inexperienced surgeon is great.
- the configuration of the present embodiment it is possible to display the inflamed part as an image in real time by reducing the load of image processing. Therefore, diagnostic accuracy can be improved.
- the color map image (image showing the degree of inflammation) and the normal image are arranged side by side or synthesized without delay. Can be displayed. Therefore, it is possible to display a color map image without extending the examination time, and as a result, it is possible to avoid an increase in patient burden.
- the observation target part in the present embodiment is, for example, a respiratory organ, a digestive organ, or the like.
- the respiratory organ or the like is, for example, the lung or the ENT.
- Examples of digestive organs include the large intestine, the small intestine, the stomach, the duodenum, and the uterus.
- the electronic endoscope system according to the present embodiment is considered to be more effective when the observation target is the large intestine. Specifically, this is due to the following reasons.
- the inflammation evaluation value according to the present embodiment is effective as an index of inflammatory bowel disease (IBD) represented by ulcerative colitis. Since a treatment method for ulcerative colitis has not been established, the use of the electronic endoscope system having the configuration of the present embodiment has an extremely great effect of early detection and suppression of progression.
- IBD inflammatory bowel disease
- the large intestine is a long and slender organ compared to the stomach and the like, and the obtained image has a depth and becomes darker at the back. According to the configuration of the present embodiment, it is possible to suppress the fluctuation of the evaluation value due to the change in brightness in the image. Therefore, when the electronic endoscope system according to the present embodiment is applied to the observation of the large intestine, the effect of the present embodiment becomes remarkable. That is, the electronic endoscope system according to the present embodiment is preferably an electronic endoscope system for respiratory organs or an electronic endoscope system for digestive organs, and more preferably an electronic endoscope system for large intestine.
- mild inflammation is generally difficult to diagnose
- the configuration of the present embodiment for example, by displaying the result of evaluating the degree of inflammation on the screen, it is possible to prevent the operator from overlooking the mild inflammation. it can.
- the judgment criteria are not clear, and this is a factor that increases individual differences among surgeons.
- an objective evaluation value can be provided to the surgeon, so that variation in diagnosis due to individual differences can be reduced.
- the above-described configuration of the present embodiment can be applied not only to the degree of inflammation but also to the evaluation value of various lesions accompanied by cancer, polyps, and other color changes. In these cases, the same advantages as described above can be applied. Effects can be achieved. That is, the evaluation value of the present embodiment is preferably an evaluation value of a lesion with a color change, and includes at least one of an inflammation level, a cancer, and a polyp.
- Embodiments of the present invention are not limited to those described above, and various modifications are possible within the scope of the technical idea of the present invention.
- the embodiment of the present application also includes an embodiment that is exemplarily specified in the specification or a combination of obvious embodiments and the like as appropriate.
- the operator selects the first index having the first color (the color of the living tissue when the symptom level is the highest for a given disease), and the second index is Those having the second color (the color of living tissue when healthy for a given disease) have been selected.
- the color closer to the first color or the second color (that is, the correction target) in the color space is calibrated with higher accuracy.
- a color that is farther from the correction target for example, a color that cannot be inflamed, such as light blue
- the operator may select an index to be set on the calibration jig corresponding to the symptom level to be scored with high accuracy using the electronic endoscope system 1. For example, when scoring mild inflammation with high accuracy, the surgeon may select, as the first index, one having the color of living tissue when mild inflammation occurs.
- the system controller 202 receives an operation for specifying a symptom level by an operator via a connected peripheral device (such as a keyboard), an index corresponding to the specified symptom level is displayed on the display screen of the monitor 300. And notification by voice reproduction (that is, notification to the user). Thereby, the surgeon can reliably select an appropriate index from a plurality of indices.
- the inflammation evaluation value is calculated using the R component and G component (RG two-dimensional color space) included in each pixel.
- the two-dimensional color of RG is calculated.
- the target disease stomach atrophy
- evaluation values for colorectal tumors and the like can also be calculated.
- the correction matrix coefficient is calculated using an index and a target point different from those in the above embodiment.
- the correction circuit 220D of the processor 200 may store a plurality of types of correction matrix coefficients corresponding to various target diseases. By changing the correction matrix coefficient according to the disease to be diagnosed, evaluation value calculation that is stable (small variation due to individual differences) is performed for each target disease.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Optics & Photonics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Endoscopes (AREA)
- Instruments For Viewing The Inside Of Hollow Bodies (AREA)
- Closed-Circuit Television Systems (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
Description
図1は、本発明の一実施形態に係る電子内視鏡システム1の構成を示すブロック図である。図1に示されるように、電子内視鏡システム1は、医療用に特化されたシステムであり、電子スコープ100、プロセッサ200及びモニタ300を備えている。
通常モード時のプロセッサ200での信号処理動作を説明する。
次に、特殊モード時のプロセッサ200での信号処理動作を説明する。図2に、特殊モード時に実行される特殊画像生成処理のフローチャートを示す。図2の特殊画像生成処理は、電子内視鏡システム1の動作モードが特殊モードに切り替えられた時点で開始される。
本処理ステップS11では、現フレームの各画素の画素データがプリプロセス回路220Aに入力される。各画素の画素データは、プリプロセス回路220Aによる信号処理後、プロセス回路220B及び補正回路220Dに入力される。
図3に、補正回路220Dの動作を概念的に説明するための図であって、互いに直交するR軸とG軸とによって定義されるRG平面(二次元色空間)を示す。なお、R軸は、R成分(Rの画素値)の軸であり、G軸は、G成分(Gの画素値)の軸である。
本処理ステップS13では、補正回路220Dにより、胃炎等の所定の疾患の炎症強度を計算するために必要なRG平面内の基準軸が設定される。図4に、基準軸の説明を補助する図を示す。
本処理ステップS14では、補正回路220Dにより、全ての画素の中から所定の順序に従い一つの注目画素が選択される。
補正回路220Dには、後述のキャリブレーションモード時に算出された補正マトリックス係数が記憶されている。本処理ステップS15では、同一の病変部を異なる電子内視鏡システムで撮影したときのスコア値のばらつき(言い換えると、電子スコープの個体差)を抑えるため、補正回路220Dにより、処理ステップS14(注目画素の選択)にて選択された注目画素の画素データ(R,G)が補正マトリックス係数を用いて補正される。なお、補正マトリックス係数については、後述の[キャリブレーションモード時の動作]において詳細に説明する。
Rnew :補正後の注目画素の画素データ(R成分)
Gnew :補正後の注目画素の画素データ(G成分)
M11~M22:補正マトリックス係数
R :補正前の注目画素の画素データ(R成分)
G :補正前の注目画素の画素データ(G成分)
補正回路220Dにおいて現フレームの全ての画素に対して処理ステップS14(注目画素の選択)及びS15(画素データの補正)が実行されると、スコアリング回路220Eにより、処理ステップS15(画素データの補正)にて補正された各画素の画素データ(Rnew,Gnew)について、炎症強度を計算するための角度が算出される。具体的には、本処理ステップS16では、各画素について、ヘモグロビン変化軸AX1と粘膜変化軸AX2との交点(基準点)O’と画素対応点(Rnew,Gnew)とを結ぶ線分Lと、ヘモグロビン変化軸AX1とがなす角度θ(図3参照)が算出される。なお、基準点O’は、座標(-150,-75)に位置する。
体腔内の撮影画像の明るさが白色光Lの当たり具合によって変化すると、撮影画像の色味は、個人差、撮影箇所、炎症の状態等の影響があるものの、RG平面内において、概ね、症状レベルの最も高い炎症部位ではヘモグロビン変化軸AX1上に沿って変化し、症状レベルの最も低い炎症部位では粘膜変化軸AX2上に沿って変化する。また、中間の症状レベルの炎症部位の撮影画像の色味も同じ傾向で変化するものと推定される。すなわち、炎症部位に対応する画素対応点は、白色光Lの当たり具合によって変化すると、基準点O’を起点とした方位角方向にシフトする。言い換えると、炎症部位に対応する画素対応点は、白色光Lの当たり具合によって変化すると、角度θが一定のまま移動して基準点O’との距離が変わる。これは、角度θが撮影画像の明るさの変化に実質的に影響を受けないパラメータであることを意味する。
本処理ステップS18では、スコアリング回路220Eにより、現フレームの全ての画素の炎症強度を平均化した平均値(又は全ての画素の炎症強度の積算値)が撮影画像全体の炎症評価値として計算されると共に、計算した炎症評価値の表示データ(表示データ例:Score:○○)が生成される。
本実施形態では、炎症強度に応じた表示色で撮影画像をモザイク化したカラーマップ画像を表示することができる。カラーマップ画像を表示可能とするため、炎症強度の値と所定の表示色とを対応付けたテーブルがスコアリング回路220Eの所定の記憶領域に記憶されている。本テーブルでは、例えば、値5刻みで異なる表示色が対応付けられている。例示的には、炎症強度の値が0~5の範囲では黄色が対応付けられており、該値が5増える毎に色相環での色の並び順に従って異なる表示色が対応付けられており、該値が250~255の範囲では赤色が対応付けられている。
本処理ステップS20では、マッピング回路220Fにより、現フレームの各画素の色データが、処理ステップS19(カラーマップ画像上での表示色の決定)にて決定された表示色のデータに変換され、変換された表示色で表示される画素よりなるカラーマップ画像データが生成される。
本処理ステップS21では、出力回路220Cにより、プロセス回路220Bより入力される通常のカラー画像データに基づく通常のカラー画像と、処理ステップS20(カラーマップ画像データの生成)にて生成されたカラーマップ画像データに基づくカラーマップ画像とをオーバレイさせる割合を係数として、前者の画像データ(通常のカラー画像データ)と後者の画像データ(カラーマップ画像データ)とが加算される。
本処理ステップS22では、電子内視鏡システム1の動作モードが特殊モードとは別のモードに切り替えられたか否かが判定される。別のモードに切り替えられていないと判定される場合(S22:NO)、図2の特殊画像生成処理は、処理ステップS11(現フレームの画素データの入力)に戻る。一方、別のモードに切り替えられたと判定される場合(S22:YES)、図2の特殊画像生成処理は終了する。
出力回路220Cは、図2の処理ステップS21(オーバレイ処理)にて加算処理された画像データに基づいて通常のカラー画像とカラーマップ画像とのオーバレイ画像の表示データを生成すると共にモニタ300の表示画面の周辺領域(画像表示領域の周囲)をマスクするマスキング処理を行い、更に、マスキング処理により生成されるマスク領域に炎症評価値を重畳した、モニタ表示用の画面データを生成する。出力回路220Cは、生成されたモニタ表示用の画面データを所定のビデオフォーマット信号に変換して、モニタ300に出力する。
次に、キャリブレーションモード時の電子内視鏡システム1の動作について説明する。図6に、キャリブレーションモード時に実行されるキャリブレーション処理のフローチャートを示す。また、図7に、図6のキャリブレーション処理の説明を補助する図を示す。図6のキャリブレーション処理は、例えば工場出荷時に実行されるものであり、電子内視鏡システム1の動作モードがキャリブレーションモードに切り替えられた時点で開始される。
本処理ステップS31では、作業者による操作入力に従い、第一の指標(第一の色が塗布された面)が電子スコープ100によって撮影され、その撮影画像データ(RAW形式やYUV形式等)がPCに入力される。
作業者は、第一の指標に代えて第二の指標をキャリブレーション用治具にセットすることにより、電子スコープ100の画角内に第二の指標を固定配置する。ここで、第二の指標は、所定の疾患について健常であるときの生体組織の色である第二の色を持つ指標である。本実施形態において、第二の指標は、RG平面内の粘膜変化軸AX2上の所定点(後述の第二の目標点PT2)に対応する色が塗布された板状部材である。
作業者による操作入力に従い又は指定枚数(ここでは二枚)の撮影後自動的に、本処理ステップS33の実行が開始される。
本処理ステップS34では、キャリブレーション用ソフトウェアにより、処理ステップS32(第二の指標の撮影)にて撮影された第二の指標の撮影画像データから、第二の指標の実測値として第二の実撮影データ点PD2が算出される。例示的には、第一の実撮影データ点と同様に、第二の指標の画像内の中央領域の画素(例えば200×200画素)の平均値が第二の実撮影データ点PD2として算出される。
本処理ステップS35では、キャリブレーション用ソフトウェアにより、図7に示されるように、第一の実撮影データ点PD1及び第二の実撮影データ点PD2が、ここでの対象疾患(胃炎等)と関連付けられたRG平面に配置される。本処理ステップS35の実行により、各実撮影データ点がその色成分に応じて所定の疾患と関連付けられた所定の色空間に配置される。
図7に示されるように、ヘモグロビン変化軸AX1上には第一の実撮影データ点PD1に対応する第一の目標点PT1が設定され、粘膜変化軸AX2上には第二の実撮影データ点PD2に対応する第二の目標点PT2が設定されている。第一の目標点PT1は、第一の指標が持つ第一の色に対応し、第二の目標点PT2は、第二の指標が持つ第二の色に対応する。
・補正マトリックス係数の算出例
M11~M22 :補正マトリックス係数
REF11、REF21:第一の目標点PT1
REF12、REF22:第二の目標点PT2
MEA11、MEA21:第一の実撮影データ点PD1
MEA12、MEA22:第二の実撮影データ点PD2
本処理ステップS37では、処理ステップS36(補正マトリックス係数の算出)にて算出された補正マトリックス係数がプロセッサ200の補正回路220Dに保存(記憶)される。これにより、図6に示されるキャリブレーション処理が完了する。
Claims (14)
- コンピュータにより実行される方法であって、
所定の疾患に関する指標を撮影した撮影画像データを取得する取得ステップと、
取得された撮影画像データに応じた実際の撮影のデータ点をその色成分に応じて前記疾患と関連付けられた所定の色空間に配置する配置ステップと、
前記色空間内における前記データ点と所定の目標点との距離に基づいて電子内視鏡による撮影画像を構成する各画素の値を補正する補正値を算出する算出ステップと、
算出された補正値を記憶する記憶ステップと、
を含む、
補正データ生成方法。 - 前記取得ステップにて、
前記疾患について症状レベルが所定の第一のレベルであるときの生体組織の色である第一の色を持つ第一の指標を撮影した第一の撮影画像データと、該疾患について症状レベルが所定の第二のレベルであるときの生体組織の色である第二の色を持つ第二の指標を撮影した第二の撮影画像データを取得し、
前記配置ステップにて、
取得された第一、第二の撮影画像データに応じた第一、第二の前記データ点をその色成分に応じて前記色空間に配置し、
前記算出ステップにて、
前記色空間内における前記第一のデータ点と所定の第一の目標点との距離及び前記第二のデータ点と所定の第二の目標点との距離に基づいて前記補正値を算出する、
請求項1に記載の補正データ生成方法。 - ユーザによる症状レベルの指定操作を受け付けるステップと、
受け付けた症状レベルに対応する指標をユーザに報知するステップと、
を含む、
請求項2に記載の補正データ生成方法。 - 前記算出ステップにて、
前記第一のデータ点と前記第一の目標点との距離と、前記第二のデータ点と前記第二の目標点との距離との合計値を最小とするマトリックス係数を前記補正値として算出する、
請求項2又は請求項3に記載の補正データ生成方法。 - 前記色空間は、
R成分の軸と、該R成分の軸と直交するG成分の軸を含む二次元色空間である、
請求項1から請求項4の何れか一項に記載の補正データ生成方法。 - 前記第一の色は、
前記疾患について症状レベルが最も高いときの生体組織の色であり、
前記第一の目標点は、
前記色空間において、ヘモグロビン色素と相関の高い軸上に位置する点である、
請求項2を引用する、請求項3から請求項5の何れか一項に記載の補正データ生成方法。 - 前記第二の色は、
前記疾患について健常であるときの生体組織の色であり、
前記第二の目標点は、
前記色空間において、体腔内の粘膜の色味と相関の高い軸上に位置する点である、
請求項2を引用する、請求項3から請求項6の何れか一項に記載の補正データ生成方法。 - 所定の疾患に関する指標を撮影した撮影画像データを取得する取得手段と、
取得された撮影画像データに応じた実際の撮影のデータ点をその色成分に応じて前記疾患と関連付けられた所定の色空間に配置する配置手段と、
前記色空間内における前記データ点と所定の目標点との距離に基づいて電子内視鏡による撮影画像を構成する各画素の値を補正する補正値を算出する算出手段と、
算出された補正値を記憶する記憶手段と、
を備える、
補正データ生成装置。 - 前記取得手段は、
前記疾患について症状レベルが所定の第一のレベルであるときの生体組織の色である第一の色を持つ第一の指標を撮影した第一の撮影画像データと、該疾患について症状レベルが所定の第二のレベルであるときの生体組織の色である第二の色を持つ第二の指標を撮影した第二の撮影画像データを取得し、
前記配置手段は、
取得された第一、第二の撮影画像データに応じた第一、第二の前記データ点をその色成分に応じて前記色空間に配置し、
前記算出手段は、
前記色空間内における前記第一のデータ点と所定の第一の目標点との距離及び前記第二のデータ点と所定の第二の目標点との距離に基づいて前記補正値を算出する、
請求項8に記載の補正データ生成装置。 - ユーザによる症状レベルの指定操作を受け付ける手段と、
受け付けた症状レベルに対応する指標をユーザに報知する手段と、
を備える、
請求項9に記載の補正データ生成装置。 - 前記算出手段は、
前記第一のデータ点と前記第一の目標点との距離と、前記第二のデータ点と前記第二の目標点との距離との合計値を最小とするマトリックス係数を前記補正値として算出する、
請求項9又は請求項10に記載の補正データ生成装置。 - 前記色空間は、
R成分の軸と、該R成分の軸と直交するG成分の軸を含む二次元色空間である、
請求項8から請求項11の何れか一項に記載の補正データ生成装置。 - 前記第一の目標点は、
前記色空間において、ヘモグロビン色素と相関の高い軸上に位置する点である、
請求項9を引用する、請求項10から請求項12の何れか一項に記載の補正データ生成装置。 - 前記第二の目標点は、
前記色空間において、体腔内の粘膜の色味と相関の高い軸上に位置する点である、
請求項9を引用する、請求項10から請求項13の何れか一項に記載の補正データ生成装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017543849A JP6427280B2 (ja) | 2016-03-03 | 2017-02-03 | 補正データ生成方法及び補正データ生成装置 |
DE112017000025.4T DE112017000025T5 (de) | 2016-03-03 | 2017-02-03 | Verfahren zur Erzeugung von Korrekturdaten und Vorrichtung zur Erzeugung von Korrekturdaten |
US15/554,085 US10512433B2 (en) | 2016-03-03 | 2017-02-03 | Correction data generation method and correction data generation apparatus |
CN201780000889.5A CN107529957B (zh) | 2016-03-03 | 2017-02-03 | 修正数据生成方法以及修正数据生成装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016040599 | 2016-03-03 | ||
JP2016-040599 | 2016-03-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017150071A1 true WO2017150071A1 (ja) | 2017-09-08 |
Family
ID=59742721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/003945 WO2017150071A1 (ja) | 2016-03-03 | 2017-02-03 | 補正データ生成方法及び補正データ生成装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US10512433B2 (ja) |
JP (2) | JP6427280B2 (ja) |
CN (1) | CN107529957B (ja) |
DE (1) | DE112017000025T5 (ja) |
WO (1) | WO2017150071A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018181156A1 (ja) * | 2017-03-31 | 2018-10-04 | Hoya株式会社 | 電子内視鏡システム |
JP2019095328A (ja) * | 2017-11-24 | 2019-06-20 | 凸版印刷株式会社 | 呈色反応検出システム、呈色反応検出方法及びプログラム |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107146569B (zh) * | 2017-07-14 | 2019-02-12 | 武汉华星光电技术有限公司 | 适用rgbw显示的分区背光显示方法及装置 |
JP6956567B2 (ja) | 2017-08-30 | 2021-11-02 | Hoya株式会社 | 内視鏡 |
DE112019004084T5 (de) * | 2019-03-27 | 2021-05-06 | Hoya Corporation | Endoskopprozessor, informationsverarbeitungsvorrichtung, endoskopsystem, programm und informationsverarbeitungsverfahren |
CN114821440B (zh) * | 2022-05-12 | 2023-03-24 | 清研灵智信息咨询(北京)有限公司 | 一种基于深度学习的移动视频流内容识别分析方法 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6379631A (ja) * | 1987-08-07 | 1988-04-09 | オリンパス光学工業株式会社 | 内視鏡撮像装置 |
JPS63173182A (ja) * | 1987-01-13 | 1988-07-16 | Olympus Optical Co Ltd | 色彩画像処理方式 |
JPH01101960A (ja) * | 1987-10-15 | 1989-04-19 | Olympus Optical Co Ltd | 経内視鏡分光診断装置 |
JP2000041942A (ja) * | 1998-07-31 | 2000-02-15 | Olympus Optical Co Ltd | 内視鏡装置 |
JP2003093337A (ja) * | 2001-09-27 | 2003-04-02 | Fuji Photo Optical Co Ltd | 電子内視鏡装置 |
JP2010079522A (ja) * | 2008-09-25 | 2010-04-08 | Sapporo Medical Univ | 画像処理装置及び画像処理プログラム |
WO2012147505A1 (ja) * | 2011-04-27 | 2012-11-01 | オリンパスメディカルシステムズ株式会社 | 医用画像処理装置及び医用画像処理方法 |
JP2014018332A (ja) * | 2012-07-17 | 2014-02-03 | Hoya Corp | 画像処理装置及び内視鏡装置 |
Family Cites Families (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0646428Y2 (ja) | 1991-09-27 | 1994-11-30 | フジマル工業株式会社 | 笛付き湯沸かし器の把手取付け構造 |
JPH0823449A (ja) * | 1994-07-11 | 1996-01-23 | Fuji Xerox Co Ltd | 画像処理装置 |
DE4445820A1 (de) * | 1994-12-21 | 1996-06-27 | Hoechst Ag | Verfahren zum Entwickeln bestrahlter, strahlungsempfindlicher Aufzeichnungsmaterialien |
JPH1189789A (ja) * | 1997-09-24 | 1999-04-06 | Olympus Optical Co Ltd | 蛍光画像装置 |
JP2000330858A (ja) * | 1999-05-25 | 2000-11-30 | Fujitsu Ltd | 画像処理装置およびプログラム記憶媒体 |
JP4534340B2 (ja) | 2000-10-31 | 2010-09-01 | ソニー株式会社 | 色再現補正装置 |
AU2002324605A1 (en) * | 2001-08-03 | 2003-02-17 | Joseph A Izatt | Real-time imaging system and method |
US7042488B2 (en) | 2001-09-27 | 2006-05-09 | Fujinon Corporation | Electronic endoscope for highlighting blood vessel |
JP2005107211A (ja) * | 2003-09-30 | 2005-04-21 | Olympus Corp | 画像投影装置 |
WO2006087981A1 (ja) * | 2005-02-15 | 2006-08-24 | Olympus Corporation | 医用画像処理装置、管腔画像処理装置、管腔画像処理方法及びそれらのためのプログラム |
JP5173120B2 (ja) * | 2005-05-23 | 2013-03-27 | オリンパスメディカルシステムズ株式会社 | 内視鏡装置 |
US8027533B2 (en) * | 2007-03-19 | 2011-09-27 | Sti Medical Systems, Llc | Method of automated image color calibration |
JP2009165553A (ja) * | 2008-01-11 | 2009-07-30 | Olympus Medical Systems Corp | 医療用画像処理装置及び医療用撮像システム |
JP5281826B2 (ja) * | 2008-06-05 | 2013-09-04 | オリンパス株式会社 | 画像処理装置、画像処理プログラムおよび画像処理方法 |
KR101708726B1 (ko) * | 2010-04-28 | 2017-02-21 | 기븐 이미징 리미티드 | 생체내 영상들 일부 표시 시스템 및 방법 |
JP5830295B2 (ja) * | 2011-07-29 | 2015-12-09 | オリンパス株式会社 | 画像処理装置、画像処理装置の作動方法、及び画像処理プログラム |
CA2873496A1 (en) * | 2012-05-14 | 2013-11-21 | Luca Rossato | Encoding and decoding based on blending of sequences of samples along time |
JP6097629B2 (ja) | 2013-04-26 | 2017-03-15 | Hoya株式会社 | 病変評価情報生成装置 |
JP5622903B2 (ja) | 2013-08-05 | 2014-11-12 | オリンパス株式会社 | 画像処理装置、画像処理装置の作動方法および画像処理プログラム |
JP2015066262A (ja) * | 2013-09-30 | 2015-04-13 | 富士フイルム株式会社 | 画像処理装置、画像処理システム、及び画像処理方法 |
US9438771B2 (en) * | 2013-10-08 | 2016-09-06 | Canon Kabushiki Kaisha | Image processing apparatus, image pickup apparatus, image pickup system, image processing method, and non-transitory computer-readable storage medium |
JP5887367B2 (ja) * | 2014-01-30 | 2016-03-16 | 富士フイルム株式会社 | プロセッサ装置、内視鏡システム、及び内視鏡システムの作動方法 |
JP2016015995A (ja) * | 2014-07-04 | 2016-02-01 | Hoya株式会社 | 電子内視鏡システム及び電子内視鏡用プロセッサ |
-
2017
- 2017-02-03 US US15/554,085 patent/US10512433B2/en active Active
- 2017-02-03 DE DE112017000025.4T patent/DE112017000025T5/de active Pending
- 2017-02-03 JP JP2017543849A patent/JP6427280B2/ja active Active
- 2017-02-03 CN CN201780000889.5A patent/CN107529957B/zh active Active
- 2017-02-03 WO PCT/JP2017/003945 patent/WO2017150071A1/ja active Application Filing
-
2018
- 2018-10-26 JP JP2018201962A patent/JP2019063537A/ja active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS63173182A (ja) * | 1987-01-13 | 1988-07-16 | Olympus Optical Co Ltd | 色彩画像処理方式 |
JPS6379631A (ja) * | 1987-08-07 | 1988-04-09 | オリンパス光学工業株式会社 | 内視鏡撮像装置 |
JPH01101960A (ja) * | 1987-10-15 | 1989-04-19 | Olympus Optical Co Ltd | 経内視鏡分光診断装置 |
JP2000041942A (ja) * | 1998-07-31 | 2000-02-15 | Olympus Optical Co Ltd | 内視鏡装置 |
JP2003093337A (ja) * | 2001-09-27 | 2003-04-02 | Fuji Photo Optical Co Ltd | 電子内視鏡装置 |
JP2010079522A (ja) * | 2008-09-25 | 2010-04-08 | Sapporo Medical Univ | 画像処理装置及び画像処理プログラム |
WO2012147505A1 (ja) * | 2011-04-27 | 2012-11-01 | オリンパスメディカルシステムズ株式会社 | 医用画像処理装置及び医用画像処理方法 |
JP2014018332A (ja) * | 2012-07-17 | 2014-02-03 | Hoya Corp | 画像処理装置及び内視鏡装置 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018181156A1 (ja) * | 2017-03-31 | 2018-10-04 | Hoya株式会社 | 電子内視鏡システム |
US10939801B2 (en) | 2017-03-31 | 2021-03-09 | Hoya Corporation | Electronic endoscope system |
JP2019095328A (ja) * | 2017-11-24 | 2019-06-20 | 凸版印刷株式会社 | 呈色反応検出システム、呈色反応検出方法及びプログラム |
JP7062926B2 (ja) | 2017-11-24 | 2022-05-09 | 凸版印刷株式会社 | 呈色反応検出システム、呈色反応検出方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
US20180168512A1 (en) | 2018-06-21 |
JPWO2017150071A1 (ja) | 2018-03-15 |
DE112017000025T5 (de) | 2018-03-01 |
JP6427280B2 (ja) | 2018-11-21 |
CN107529957B (zh) | 2019-10-25 |
CN107529957A (zh) | 2018-01-02 |
JP2019063537A (ja) | 2019-04-25 |
US10512433B2 (en) | 2019-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6581730B2 (ja) | 電子内視鏡用プロセッサ及び電子内視鏡システム | |
JP6125740B1 (ja) | 内視鏡システム及び評価値計算装置 | |
WO2017150071A1 (ja) | 補正データ生成方法及び補正データ生成装置 | |
JP6113386B1 (ja) | 評価値計算装置及び電子内視鏡システム | |
JP6591688B2 (ja) | 電子内視鏡用プロセッサ及び電子内視鏡システム | |
JP6433634B2 (ja) | 電子内視鏡用プロセッサ及び電子内視鏡システム | |
US11559186B2 (en) | Evaluation value calculation device and electronic endoscope system | |
JP6420358B2 (ja) | 内視鏡システム及び評価値計算装置 | |
JP6926242B2 (ja) | 電子内視鏡用プロセッサ及び電子内視鏡システム | |
JP2018023497A (ja) | 色補正用治具及び電子内視鏡システム | |
JP2018011797A (ja) | 補正効果確認方法及び指標 | |
JP2018011796A (ja) | キャリブレーション方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2017543849 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15554085 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112017000025 Country of ref document: DE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17759542 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17759542 Country of ref document: EP Kind code of ref document: A1 |