WO2023281607A1 - 内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法 - Google Patents

内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法 Download PDF

Info

Publication number
WO2023281607A1
WO2023281607A1 PCT/JP2021/025365 JP2021025365W WO2023281607A1 WO 2023281607 A1 WO2023281607 A1 WO 2023281607A1 JP 2021025365 W JP2021025365 W JP 2021025365W WO 2023281607 A1 WO2023281607 A1 WO 2023281607A1
Authority
WO
WIPO (PCT)
Prior art keywords
region
image information
processor
lesion
display
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/025365
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
明広 窪田
大和 神田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Olympus Medical Systems Corp
Original Assignee
Olympus Medical Systems Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Olympus Medical Systems Corp filed Critical Olympus Medical Systems Corp
Priority to PCT/JP2021/025365 priority Critical patent/WO2023281607A1/ja
Priority to CN202180097925.0A priority patent/CN117241719A/zh
Priority to JP2023532905A priority patent/JP7592165B2/ja
Publication of WO2023281607A1 publication Critical patent/WO2023281607A1/ja
Priority to US18/382,556 priority patent/US12469247B2/en
Anticipated expiration legal-status Critical
Priority to US19/359,134 priority patent/US20260038227A1/en
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10068—Endoscopic image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10141—Special mode during image acquisition
    • G06T2207/10152—Varying illumination
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30028—Colon; Small intestine
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G06V2201/031—Recognition of patterns in medical or anatomical images of internal organs

Definitions

  • the present invention relates to an endoscope processor, an endoscope apparatus, and a diagnostic image generation method for detecting a lesion area from image information.
  • endoscopes have been widely used in the medical and industrial fields.
  • an operator finds and distinguishes a lesion by looking at an endoscopic image of the inside of the subject displayed on a display device, and treats the lesion using a treatment tool. can do
  • CAD Computer Aided Detection/Diagnosis
  • WO2019/087971 discloses a medical image processing apparatus that detects a lesion area with a first illumination light, discriminates the lesion type with a second illumination light, and specifies the degree of progress with a third illumination light. and an endoscopic device are described.
  • the first illumination light for detecting the lesion area is specifically illumination light for identification of Pattern 1 as described in FIG. 5 of the publication.
  • the present invention has been made in view of the above circumstances, and provides an endoscope processor, an endoscope apparatus, and a diagnostic image generation method capable of realizing a function of detecting lesions that may be overlooked with white light. It is intended to
  • An endoscope processor includes a processor, the processor detects a first region of a lesion candidate from first image information obtained by irradiating the first illumination light, detecting a second region of a lesion candidate from second image information obtained by irradiating a second illumination light having a spectrum different from light, and determining a display region of the lesion candidate based on the first region and the second region; Then, display image information is generated by superimposing the display area on the first image information.
  • An endoscope apparatus includes a light source device capable of irradiating a plurality of types of illumination light including a first illumination light and a second illumination light having a spectrum different from that of the first illumination light; an endoscope including an imaging device that acquires first image information by irradiating the first illumination light from a device and acquires second image information by irradiating the second illumination light from the light source device; Detecting a first region of a lesion candidate from one image information, detecting a second region of a lesion candidate from the second image information, and selecting a lesion candidate display region based on the first region and the second region.
  • an endoscope processor including a processor that generates display image information in which the display area is superimposed on the first image information; and a monitor that displays the display image information.
  • a diagnostic image generation method detects a first region of a lesion candidate from first image information obtained by irradiating first illumination light, 2 detecting a second area of the lesion candidate from second image information obtained by irradiating illumination light; selecting a display area of the lesion candidate based on the first area and the second area; is superimposed on the first image information to generate display image information.
  • FIG. 1 is a perspective view showing an example of the appearance of an endoscope apparatus according to a first embodiment of the present invention
  • FIG. FIG. 2 is a block diagram showing an example of the configuration of the endoscope apparatus according to the first embodiment
  • FIG. FIG. 2 is a block diagram showing an electrical configuration example of the endoscope processor according to the first embodiment
  • FIG. 2 is a block diagram showing a configuration example of a discriminator according to the first embodiment
  • 4 is a chart showing an example of image information in each discriminator and monitor in the first embodiment
  • 4 is a flowchart showing processing of the endoscope processor according to the first embodiment
  • FIG. 5 is a block diagram showing a configuration example of a discriminator according to the second embodiment of the present invention
  • 9 is a flowchart showing processing of the endoscope processor according to the second embodiment
  • FIG. 11 is a block diagram showing a configuration example of a discriminator according to the third embodiment of the present invention
  • FIG. 11 is a flow chart showing processing of the endoscope processor according to the third embodiment
  • FIG. 5 is a block diagram showing a configuration example of a discriminator according to the second embodiment of the present invention
  • 9 is a flowchart showing processing of the endoscope processor according to the second embodiment
  • FIG. 11 is a block diagram showing a configuration example of a discriminator according to the third embodiment of the present invention
  • FIG. 11 is a flow chart showing processing of the endoscope processor according to the third embodiment
  • FIG. 1 to 6 show a first embodiment of the present invention
  • FIG. 1 is a perspective view showing an example of the configuration of an endoscope device 1.
  • FIG. An endoscope apparatus 1 of this embodiment includes an endoscope 2 , a light source device 3 , an endoscope processor 4 and a monitor 5 .
  • the endoscope 2 includes an elongated insertion portion 9 to be inserted into a subject, an operation portion 10 for performing various operations related to the endoscope 2, a light source device 3 and an endoscope processor. and a universal cable 17 for connecting to .
  • the insertion portion 9 includes a distal end portion 6, a bending portion 7, and a flexible tube portion 8 in order from the distal end toward the proximal end.
  • the distal end portion 6 includes an illumination window through which illumination light is emitted to the subject, and an observation window through which return light from the subject is incident.
  • the endoscope 2 of the present embodiment is configured as an electronic endoscope, and an imaging device 21 (see FIG. 2) is provided at the distal end portion 6 .
  • the imaging device 21 includes an imaging optical system and an imaging device. The imaging optical system forms an optical image of a subject (subject image) on the imaging element with the light incident through the observation window.
  • the imaging device is an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor).
  • the imaging device photoelectrically converts a subject image to generate and output an imaging signal.
  • the imaging signal is transmitted to the endoscope processor 4 via the signal line.
  • the bending portion 7 is a bendable portion connected to the proximal end side of the distal end portion 6, and bends to change the direction in which the distal end portion 6 faces.
  • the flexible tube part 8 is a part that is connected to the proximal end side of the bending part 7 and has a possibility.
  • a bending wire for bending the bending portion 7 and a treatment instrument channel for inserting a treatment instrument are arranged in the insertion section 9 and the operation section 10 . Further, the above-described signal line connected to the imaging element and a light guide for transmitting illumination light are arranged in the insertion portion 9, the operation portion 10, and the universal cable 17 of the endoscope 2. ing.
  • the operation section 10 is provided with various switches including a bending operation section 14 for bending the bending section 7 via a bending wire, and a focus switch 15 .
  • a bending operation section 14 for bending the bending section 7 via a bending wire
  • a focus switch 15 When the imaging optical system has a variable power optical system, operating the focus switch 15 changes the focus position to the near point or the far point, and the subject image is magnified.
  • the bending operation section 14 includes a UD bending operation knob 12 for bending the bending section 7 in the vertical direction, and an RL bending operation knob 13 for bending the bending section 7 in the horizontal direction.
  • the bending portion 7 can bend in an oblique direction by combining bending in the vertical direction and bending in the horizontal direction.
  • a gripping portion 11 for gripping the endoscope 2 by an operator's hand and a treatment instrument channel insertion port 16 serving as an opening on the base end side of the treatment instrument channel are provided on the distal side of the operation section 10 . It is
  • the universal cable 17 extends from, for example, the proximal side surface of the operation section 10 .
  • a scope connector 17 a is provided at the proximal end of the universal cable 17 .
  • the scope connector 17 a detachably connects the endoscope 2 to the light source device 3 . By connecting the scope connector 17a to the light source device 3, it becomes possible to transmit the illumination light through the light guide.
  • a coiled electrical cable 18 extends from the side of the scope connector 17a.
  • An electrical connector 18 a provided at the extending end of the electrical cable 18 is detachably connected to the endoscope processor 4 .
  • the imaging device is electrically connected to the endoscope processor 4 .
  • the endoscope processor 4 is electrically connected to a monitor 5 that is a display device.
  • the endoscope processor 4 processes the imaging signal output from the imaging element of the endoscope 2 to generate image information for display.
  • the display image information is output from the endoscope processor 4 to the monitor 5 and displayed on the monitor 5 as a display image including an endoscopic image.
  • the monitor 5 also includes a speaker 5a for outputting sound.
  • FIG. 2 is a block diagram showing an example of the configuration of the endoscope device 1. As shown in FIG.
  • the endoscope 2 includes the imaging device 21 as described above.
  • the imaging device 21 acquires first image information (white light image information, which will be described later) by capturing an image of the subject irradiated with the first illumination light from the light source device 3, and irradiates the second illumination light from the light source device 3.
  • Second image information (first special light image information and second special light image information described later) is acquired by imaging the object to be examined.
  • the light source device 3 can emit a plurality of types of illumination light including first illumination light and second illumination light having a spectrum different from that of the first illumination light.
  • the light source device 3 of this embodiment includes a white light source 31 , a first special light source 32 and a second special light source 33 .
  • the white light source 31 emits white light for observation.
  • the first special light source 32 emits first special light having a spectrum different from that of white light.
  • the second special light source 33 emits white light and second special light having a spectrum different from that of the first special light.
  • the white light is the first illumination light, and the first special light and the second special light are the second illumination light.
  • the light source device 3 includes a plurality of light sources that emit light of each color such as R (red), G (green), B (blue), V (violet), A (amber), and the light sources of each color are combined.
  • the white light source 31, the first special light source 32, and the second special light source 33 described above are configured.
  • the light source device 3 includes a light emitting device such as an LED (Light Emitting Diode) or an LD (Laser Diode).
  • the light source device 3 includes a V-LED that emits violet (V) light with a center wavelength of about 405 nm, a B-LED that emits blue (B) light with a center wavelength of about 445 nm, and a B-LED with a center wavelength of about 445 nm.
  • a G-LED that emits green (G) light with a wavelength of 540 nm and an R-LED that emits red (R) light with a center wavelength of about 630 nm are provided.
  • the light source device 3 is equipped with a prism, a mirror, an optical fiber, or an optical filter for adjusting the wavelength band or the amount of light, etc., as required.
  • the light source device 3 of this embodiment sequentially emits white light, first special light, and second special light for each frame.
  • the imaging device 21 captures white light image information (hereinafter referred to as a white light image), first special light image information (hereinafter referred to as a first special light image), second special light image information (hereinafter referred to as a second special light image). (referred to as a light image) are sequentially acquired, and after the second special light image, a white light image is acquired again.
  • white light image and the first special light image are acquired in one frame each, while the second special light image is acquired in two frames, and so on.
  • the endoscope processor 4 includes an image processing unit 41, a white light discriminator 42, a first special light discriminator 43, a second special light discriminator 44, a lesion area selection unit 45, and a display processing unit 46. , a bus 47 and a control unit 48 .
  • the number may be two or four or more.
  • it functions as any of the white light discriminator 42, the first special light discriminator 43, and the second special light discriminator 44. It may be configured to
  • FIG. 3 is a block diagram showing an electrical configuration example of the endoscope processor 4. As shown in FIG. Although the functional configuration of the endoscope processor 4 is shown in FIG. 2, the endoscope processor 4 includes, for example, a processor 4a and a memory 4b as an electrical configuration.
  • the processor 4a includes, for example, an ASIC (Application Specific Integrated Circuit) including a CPU (Central Processing Unit) or the like, or an FPGA (Field Programmable Gate Array).
  • the memory 4b is a storage medium such as RAM (Random Access Memory), flash memory, or disk storage medium.
  • the memory 4b includes a computer-readable non-transitory storage medium for recording a processing program.
  • the processor 4a reads and executes the processing program stored in the memory 4b, thereby fulfilling the functions of the units shown in FIG.
  • the configuration is not limited to this, and the processor 4a may be configured as a dedicated electronic circuit that performs the function of each section.
  • FIG. 4 is a block diagram showing a configuration example of the discriminators 42, 43, and 44.
  • Each of the white light discriminator 42, the first special light discriminator 43, and the second special light discriminator 44 is a lesion discriminator 4c that detects a lesion candidate area from image information obtained by irradiating illumination light. It has The lesion discriminator 4c includes, for example, artificial intelligence (AI) that has learned lesion images.
  • AI artificial intelligence
  • the image processing unit 41 performs various types of processing such as demosaicing, noise correction, color correction, contrast correction, and gamma correction on the image information output from the imaging device 21, and outputs an image signal in a format that can be output to the monitor 5 (display image information).
  • the white light discriminator 42 is the first discriminator, and the first special light discriminator 43 and the second special light discriminator 44 are the second discriminators.
  • the white light discriminator 42 includes an AI learned by machine learning, deep learning, or the like from lesion images captured as white light images.
  • the white light discriminator 42 detects a lesion candidate region (first area).
  • the white light discriminator 42 also calculates a reliability score of the detected lesion candidate region.
  • the confidence score indicates the degree of certainty (certainty) that the lesion candidate region is actually a lesion.
  • the first special light discriminator 43 includes an AI learned by machine learning, deep learning, etc., from the lesion image captured as the first special light image.
  • the first special light discriminator 43 irradiates the subject with the first special light emitted from the first special light source 32 and detects the lesion from the endoscopic image (first special light image) acquired by the imaging device 21 .
  • a candidate region (the second region of the lesion candidate) is detected.
  • the first special optical discriminator 43 calculates a reliability score of the detected lesion candidate region.
  • the second special light discriminator 44 includes an AI learned by machine learning, deep learning, etc., from the lesion image captured as the second special light image.
  • the second special light discriminator 44 irradiates the subject with the second special light emitted from the second special light source 33, and identifies the lesion from the endoscopic image (second special light image) acquired by the imaging device 21.
  • a candidate region (the second region of the lesion candidate) is detected.
  • the second special optical discriminator 44 calculates a reliability score of the detected lesion candidate region.
  • the first special optical discriminator 43 and the second special optical discriminator 44 can be configured, for example, as discriminators that detect lesion candidate regions at different depths from the mucosal surface (superficial layer, middle layer, deep layer). Detection of a lesion candidate region is performed, for example, based on an image in which blood vessel information at a target depth is emphasized.
  • As special light for emphasizing blood vessel information wavelengths of narrow-band light that sufficiently reaches the target depth and have a difference in the absorption coefficient ⁇ a of oxidized and reduced hemoglobin, and wavelengths of narrow-band light at an isosbestic point where there is no difference.
  • Illumination light of such a wavelength set is known as illumination light for NBI (Narrow Band Imaging).
  • the discriminator for superficial lesions identifies superficial lesions on the mucosal surface or relatively shallow from the mucosal surface (depth of several tens of ⁇ m from the mucosal surface).
  • the special light that emphasizes superficial blood vessel information includes, for example, violet light (405 nm) as reference light and blue light (445 nm) as measurement light, and the amount of violet light is greater than that of blue light. It's a big light.
  • the superficial lesion discriminator is a discriminator learned from lesion images captured with special light that emphasizes superficial blood vessel information.
  • the discriminator for intermediate-layer lesions identifies intermediate-layer lesions that are intermediate in depth from the mucosal surface (depth of several tens to several hundred ⁇ m).
  • the special light for emphasizing middle-layer blood vessel information includes, for example, blue light (473 nm) as measurement light, green light as reference light, and red light as reference light, where the amount of blue light is the amount of green light. and the amount of green light is greater than that of red light.
  • the discriminator for intermediate-layer lesions is a discriminator learned from lesion images captured with special light that emphasizes intermediate-layer blood vessel information.
  • the deep-type lesion discriminator identifies deep-type lesions that are deep from the mucosal surface (from the muscularis mucosae to the submucosa layer).
  • Special light for emphasizing deep-layer blood vessel information includes, for example, blue light as reference light, green light as reference light, and red light (630 nm) as measurement light, and the amount of green light is the amount of blue light. , and the amount of blue light is greater than that of red light, and is learned from lesion images captured with special light.
  • the second discriminator is a special light (RDI (Red Dichromatic Imaging ) may be a discriminator learned from lesion images captured with illumination light for ).
  • RDI illumination light for example, three colors of green, amber, and red light of specific wavelengths are used. Therefore, the plurality of types of second illumination light preferably includes at least one of the NBI illumination light and the RDI illumination light.
  • the first special optical discriminator 43 is a superficial lesion discriminator
  • the second special optical discriminator 44 is a middle layer lesion discriminator.
  • the lesion area selection unit 45 selects the lesion candidate area detected by the white light discriminator 42, the lesion candidate area detected by the first special light discriminator 43, and the lesion candidate detected by the second special light discriminator 44.
  • a lesion candidate display area is selected based on the area and the area.
  • the following methods (1) to (3) can be used as the display area selection method by the lesion area selection unit 45.
  • the following methods (1) to (3) are all based on the reliability score of the lesion candidate region (first region) of the white light image and the reliability score of the lesion candidate region (second region) of the first special light image.
  • a method of calculating a plurality of reliability scores of a reliability score and a reliability score of a lesion candidate region (second region) in a second special light image, and selecting a display region based on the plurality of reliability scores. is.
  • region 1 is the lesion candidate region detected by the white light discriminator 42
  • region 2 is the lesion candidate region detected by the first special light discriminator 43
  • region 2 is the lesion candidate region detected by the second special light discriminator 44.
  • the candidate area is called area 3 .
  • region 1 there are cases where no lesion candidate is detected and region 1 does not exist, and there are cases where one or more lesion candidates are detected in one image and one or more regions 1 exist. .
  • areas 2 and 3 may have 0, 1, or a plurality of areas.
  • regions that do not overlap are selected as display regions as they are.
  • regions 1 to 3 first extract the region whose reliability score is equal to or higher than a predetermined threshold (specified value), and among the extracted regions, for multiple regions whose positions overlap each other, the highest reliability score is selected as the display area.
  • regions that do not overlap are selected as display regions as they are.
  • the reliability score is weighted according to the observation target part of the subject (the organ targeted for endoscopic examination), and the method of (2) is applied based on the weighted reliability score to display Select the area for use.
  • the reliability score of region 1 is referred to as score 1
  • the reliability score of region 2 is referred to as score 2
  • the reliability score of region 3 is referred to as score 3.
  • a weighting factor by which score 1 is multiplied is called weighting factor 1
  • a weighting factor by which score 2 is multiplied is called weighting factor 2
  • a weighting factor by which score 3 is multiplied is called weighting factor 3.
  • the weighting factor 2 is made larger than the weighting factors 1 and 3, and the method (2) is applied to select the display area.
  • the weighting factor 1 and the weighting factor 3 are set to 0, only the area 2 detected by the first special optical discriminator 43, which is a discriminator for superficial lesions, is selected. is the same as selecting the first special optical discriminator 43 as .
  • the weighting factor 3 is made larger than the weighting factors 1 and 2, and the method (2) is applied to select the display area.
  • the weighting factor 1 and the weighting factor 2 are set to 0, only the area 3 detected by the second special optical discriminator 44, which is a medium-layer lesion discriminator, will be selected. is the same as selecting the second special optical discriminator 44 as .
  • a lesion candidate area (first area) in the white light image, a lesion candidate area (second area) in the first special light image, and a lesion candidate area (second area) in the second special light image ) is selected as the display area.
  • the weighting according to the organ may be switched according to a user instruction (that is, manually), or may be determined automatically by the control unit 48 based on the characteristics of the endoscopic image, or may be switched automatically according to the endoscopic image.
  • the insertion length of the insertion portion 9 of the endoscope 2 may be detected, and the control portion 48 may make a determination based on the detection result and perform the operation automatically. The determination may be made automatically by the control unit 48 based on the detection result of the detection sensor.
  • a white light image is transmitted from the image processing unit 41 to the display processing unit 46 via the white light discriminator 42 and the lesion area selection unit 45 . Furthermore, the display area selected by the lesion area selection unit 45 is transmitted to the display processing unit 46 .
  • a bus 47 is a transmission path through which each unit in the endoscope processor 4 transmits and receives commands and information.
  • the control unit 48 controls the image processing unit 41 , the white light discriminator 42 , the first special light discriminator 43 , the second special light discriminator 44 , the lesion area selection unit 45 , and the display processing unit 46 via the bus 47 . and control them.
  • the control unit 48 includes a motion detection unit 48a.
  • the motion detector 48a detects motion among the white light image, the first special light image, and the second special light image. Motion detection by the control unit 48 may be performed, for example, by image analysis, or may be performed based on the detection result of the sensor by incorporating an acceleration sensor or the position detection sensor described above into the distal end portion 6 of the endoscope 2. .
  • the motion of the image is caused by the movement of the imaging device 21 provided at the distal end portion 6 of the endoscope 2 relative to the subject.
  • the types of image movement include, for example, vertical and horizontal movement on the screen, rotational movement of the imaging device 21 relative to the subject, and movement of the tip portion 6 toward or away from the subject.
  • the control unit 48 transmits the image motion information detected by the motion detection unit 48 a to the lesion area selection unit 45 and the display processing unit 46 .
  • the lesion area selection unit 45 aligns the images (corrects the positional deviation) (thus aligns the candidate lesion areas in the images). ), select a display area from areas 1 to 3.
  • the display processing unit 46 aligns the display area with the white light image based on the image motion information transmitted from the control unit 48 . However, the alignment of the display area with respect to the white light image may be performed by the lesion area selection section 45 . Then, the display processing unit 46 superimposes the display area on the white light image to generate display image information, and outputs it to the monitor 5 .
  • the display area superimposed on the white light image may be, for example, the outline of the merged area, or may be a marker (for example, a square frame) indicating the range of the merged area.
  • the monitor 5 displays the display image on the monitor screen according to the display image information input from the display processing unit 46 .
  • FIG. 5 is a chart showing an example of image information in each classifier 42, 43, 44 and the monitor 5.
  • the white light discriminator 42 detects the lesion candidate region 51 a from the white light image 51 .
  • the first special light discriminator 43 detects a lesion candidate region 52a from the first special light image 52.
  • the second special light discriminator 44 detects a lesion candidate region 53 a from the second special light image 53 .
  • the monitor 5 displays the display image 50 on which the display area 50a is superimposed on the monitor screen.
  • the display area 50a is an area obtained by merging, for example, the lesion candidate area 51a, the lesion candidate area 52a, and the lesion candidate area 53a.
  • the display of the discrimination result 50b and the degree of progress 50c shown in FIG. 5 will be described in a later embodiment.
  • FIG. 6 is a flowchart showing the processing of the endoscope processor 4.
  • FIG. FIG. 6 shows an example of sequentially acquiring a white light image, a first special light image, and a second special light image every three frames.
  • the light source device 3 emits white light
  • the imaging device 21 acquires a white light image.
  • the acquired white light image is input to the endoscope processor 4 (step S1).
  • the input white light image is processed by the image processing unit 41 and then sent to the white light discriminator 42 and the display processing unit 46 .
  • the white light discriminator 42 detects a lesion candidate region from the white light image by the lesion discriminator 4c in the white light discriminator 42, and calculates a reliability score for each detected lesion candidate region (step S2 ).
  • the control unit 48 determines whether or not the reliability score calculated by the white light discriminator 42 is equal to or greater than a specified value (threshold value) for each lesion candidate region. (Step S3). If no lesion candidate region is detected, the control unit 48 skips the processing of step S3 and proceeds to step S4.
  • control unit 48 determines that there is no lesion (step S4), and detects the lesion candidate region. is not transmitted from the white light discriminator 42 to the lesion area selection unit 45 even if there is.
  • control unit 48 causes the white light discriminator 42 to transmit the lesion candidate area to the lesion area selection unit 45 .
  • the light source device 3 emits the first special light that emphasizes the superficial blood vessels, and the imaging device 21 acquires the first special light image.
  • the acquired first special light image is input to the endoscope processor 4 (step S5).
  • the input first special light image is processed by the image processing unit 41 and then sent to the first special light discriminator 43 .
  • the first special light discriminator 43 detects a lesion candidate region from the first special light image by the lesion discriminator 4c in the first special light discriminator 43, and calculates a reliability score for each detected lesion candidate region. (step S6).
  • the control unit 48 determines whether the reliability score calculated by the first special light discriminator 43 is equal to or greater than a specified value (threshold value) for each lesion candidate region. Determine (step S7). If no lesion candidate region is detected, the control unit 48 skips the processing of step S7 and proceeds to step S8.
  • control unit 48 determines that there is no lesion (step S8), and detects the lesion candidate region. is not transmitted from the first special optical discriminator 43 to the lesion area selection unit 45.
  • control unit 48 causes the first special optical discriminator 43 to transmit the lesion candidate area to the lesion area selection unit 45 .
  • the light source device 3 emits second special light that emphasizes the middle-layer blood vessels, and the imaging device 21 acquires a second special light image.
  • the acquired second special light image is input to the endoscope processor 4 (step S9).
  • the input second special light image is processed by the image processing unit 41 and then sent to the second special light discriminator 44 .
  • the second special light discriminator 44 detects a lesion candidate region from the second special light image by the lesion discriminator 4c in the second special light discriminator 44, and calculates a reliability score for each detected lesion candidate region. (step S10).
  • the control unit 48 determines whether the reliability score calculated by the second special light discriminator 44 is equal to or greater than a specified value (threshold value) for each lesion candidate region. Determine (step S11). If no lesion candidate region is detected, the control unit 48 skips the processing of step S11 and proceeds to step S12.
  • control unit 48 determines that there is no lesion (step S12), and detects the lesion candidate region. is not transmitted from the second special optical discriminator 44 to the lesion area selection unit 45 even if there is.
  • control unit 48 causes the second special optical discriminator 44 to transmit the lesion candidate area to the lesion area selection unit 45 .
  • the lesion area selection unit 45 selects a display area from the lesion candidate areas obtained based on the n to (n+2) frame images (step S13).
  • the lesion area selection unit 45 aligns and merges all the input candidate lesion areas as described above to form a display area.
  • the lesion candidate regions processed by the lesion region selection unit 45 are all regions with a reliability score equal to or higher than a specified value.
  • the display processing unit 46 aligns the display areas and performs image synthesis to superimpose them on the white light image (first image information) to generate display image information (step S14).
  • the generated display image information is output from the endoscope processor 4 to the monitor 5 , and the display image is displayed on the monitor screen of the monitor 5 .
  • the subsequent (n+3), (n+4), and (n+5)-th frames are processed in the same manner as the above-described n, (n+1), and (n+2)-th frames. The same applies thereafter.
  • the frame rate will decrease. Therefore, if the display image is displayed based on the image of the n to (n+2) frames, then the display image is displayed based on the image of the (n+1) to (n+3) frames, and then the image of the (n+2) to (n+4) frames is displayed.
  • the frame rate may be prevented from lowering by sequentially performing such operations as displaying the display image based on the frame rate.
  • a plurality of lesion candidate regions are detected from a plurality of image information obtained by irradiating a plurality of illumination lights having different spectra including white light, and from the plurality of lesion candidate regions, Since display image information is generated by selecting a display area and superimposing the selected display area on a white light image, a function of detecting a lesion that may be overlooked with white light can be realized. In addition, details of the subject that are dark and difficult to see with the special light image can be visually recognized with the white light image.
  • the first special light and the second special light for example, lesions with different depths from the mucosal surface can be detected from each image.
  • illumination light for NBI Near Band Imaging
  • RDI Red Dichromatic Imaging
  • the lesion detection accuracy can be improved.
  • the operator can concentrate on observing the area that is highly likely to be a lesion.
  • a lesion for which a diagnostic method has been established by varying which lesion candidate region detected from image information related to illumination light is selected as a display region according to the organ that is the observation target site of the subject.
  • Accurate computer aided imaging diagnosis CAD: Computer Aided Detection/Diagnosis
  • the lesion candidate regions detected from a plurality of image information are aligned in accordance with the results of motion detection, a display region is selected and display image information is generated. Even if there is movement, marker display or the like can be performed at an appropriate position on the white light image.
  • a computer-assisted image diagnosis in which a display area of a lesion candidate is selected by comprehensively judging from a plurality of types of images including a white light image and a special light image, and the display area is displayed on the white light image with a marker or the like.
  • FIG. 7 and 8 show a second embodiment of the present invention
  • FIG. 7 is a block diagram showing a configuration example of discriminators 42, 43, and 44.
  • FIG. 7 portions that are the same as those in the first embodiment described above are assigned the same reference numerals, and the description thereof is omitted as appropriate, and only the points of difference will be mainly described.
  • the discrimination result for the lesion candidate region is displayed.
  • each of the white light discriminator 42, the first special light discriminator 43, and the second special light discriminator 44 of this embodiment includes the lesion discriminator 4c and the differential discriminator 4d. It has
  • the differential classifier 4d includes, for example, an AI that has learned lesion images.
  • the differential discriminator 4d discriminates each lesion type for one or more lesion candidate regions detected by the lesion discriminator 4c, and calculates a reliability score of the discriminated lesion type.
  • the differential discriminator 4d discriminates, for example, that the lesion candidate region is "polyp” and calculates that the reliability score for "polyp” is, for example, "60%".
  • the differential classifier 4d does not always output one discrimination result, for example, “Polyp confidence score is 60%”, “Ulcerative colitis confidence score is 10%”, “Clone It is also possible to output a discrimination result for multiple types of lesions, such as "a disease with a confidence score of less than 1%".
  • lesion discriminator 4c and the differential discriminator 4d are shown as separate blocks in FIG. 7, one AI may function as both blocks.
  • FIG. 8 is a flowchart showing the processing of the endoscope processor 4. FIG. In FIG. 8, portions different from FIG. 6 will be described below.
  • the white light discriminator 42 performs the process of step S2 on the white light image acquired in the n-th frame, and the lesion candidate region detected by the lesion discriminator 4c in the white light discriminator 42 is classified into a white light image. Discrimination is performed by the discriminating discriminator 4 d in the optical discriminator 42 .
  • the differential classifier 4d calculates a differential result of the lesion candidate region and a reliability score for the differential result (step S21). Note that the differential classifier 4d skips the processing of step S21 when the lesion candidate region is not detected by the lesion classifier 4c.
  • the first special light discriminator 43 performs the process of step S6, and the lesion discriminator 4c in the first special light discriminator 43 detects The lesion candidate region is discriminated by the discrimination discriminator 4 d in the first special optical discriminator 43 .
  • the differential classifier 4d calculates a differential result of the lesion candidate region and a reliability score for the differential result (step S22). Note that the differential classifier 4d skips the process of step S22 when no lesion candidate region is detected by the lesion classifier 4c.
  • the second special light discriminator 44 performs the process of step S10, and the lesion discriminator 4c in the second special light discriminator 44 detects The lesion candidate region is discriminated by the discrimination discriminator 4 d in the second special optical discriminator 44 .
  • the differential discriminator 4d calculates the discrimination result of the lesion candidate region and the reliability score for the discrimination result (step S23). Note that the differential classifier 4d skips the process of step S23 when no lesion candidate region is detected by the lesion classifier 4c.
  • the lesion area selection unit 45 performs the process of step S13, and also determines the reliability score of the discrimination result obtained in step S21, the reliability score of the discrimination result obtained in step S22, and the discrimination result obtained in step S23. The results are compared with the reliability score to determine which discrimination result to display, and the determined discrimination result is output to the display processing unit 46 (step S24).
  • the lesion area selection unit 45 may determine, for example, the discrimination result with the highest reliability score as the discrimination result to be displayed. In addition, the lesion area selection unit 45 determines several (that is, a plurality of) discrimination results in order from the highest reliability score as the discrimination results to be displayed, and displays the reliability scores side by side with the discrimination results to be displayed. I don't mind.
  • the display processing unit 46 aligns the display area and performs image synthesis to superimpose it on the white light image (first image information), and further performs image synthesis to include the discrimination result in the vicinity of the white light image to create an image for display.
  • Information is generated (step S14A).
  • the generated display image information is output from the endoscope processor 4 to the monitor 5 , and the display image is displayed on the monitor screen of the monitor 5 . As a result, a discrimination result 50b as shown in FIG. 5 is displayed.
  • FIG. 9 and 10 show a third embodiment of the present invention
  • FIG. 9 is a block diagram showing a configuration example of discriminators 42, 43, and 44.
  • FIG. 9 portions that are the same as those in the above-described first and second embodiments are denoted by the same reference numerals, and descriptions thereof are omitted as appropriate, and only different points are mainly described.
  • the degree of progression of the lesion is displayed.
  • the white light discriminator 42, the first special light discriminator 43, and the second special light discriminator 44 of this embodiment are all in addition to the lesion discriminator 4c and the differential discriminator 4d. , and a progress discriminator 4e.
  • the progress classifier 4e includes, for example, an AI that has learned lesion images.
  • the progress discriminator 4e discriminates the progress of the lesion discriminated by the discrimination discriminator 4d with respect to the lesion candidate region, and calculates the reliability score of the progress.
  • the lesion discriminator 4c, the differential discriminator 4d, and the progress discriminator 4e are described as separate blocks, but one AI may be configured to function as three blocks.
  • the endoscopic classification of polyps includes the NICE (The Narrow-band imaging International Colorectal Endoscopic) classification and the JNET (The Japan NBI (Narrow Band Imaging) Expert Team) classification.
  • NICE Type 1 represents hyperplastic lesions
  • NICE Type 2 represents adenoma to intramucosal cancer (so-called M cancer)
  • NICE Type 3 represents submucosal invasion cancer (so-called SM cancer).
  • endoscopic findings classification of ulcerative colitis includes Mayo classification, Matts classification, and UCEIS (Ulcerative Colitis Endoscopic. Index of Severity) classification.
  • Mayo0 is a grade representing normal or inactive (including remission).
  • Mayo 1 is a grade representing mild disease, which generally presents with redness, poor vascularity, or mild hemorrhage.
  • Mayo2 is a grade representing moderate disease, and is generally characterized by marked redness, disappearance of blood vessels, easy bleeding, adhesion of purulent secretions, coarse mucous membranes, erosions, or partial ulcers.
  • Mayo 3 is a grade representing severe (active stage), and is generally a condition in which obvious spontaneous bleeding, edema, ulcers (including extensive ulcers), etc. are observed. Also, dysplasia associated with ulcerative colitis may be identified.
  • the endoscopic classification of Crohn's disease includes SESCD (Simple Endoscopic Score for Crohn's Disease).
  • SESCD Simple Endoscopic Score for Crohn's Disease
  • the lesion area selection unit 45 determines the multiple discrimination results to be displayed in descending order of reliability score, the degree of progression is also identified for each of the multiple discrimination results.
  • FIG. 10 is a flowchart showing the processing of the endoscope processor 4. FIG. In FIG. 10, portions different from FIG. 8 will be described below.
  • the white light discriminator 42 performs the processing of steps S2 and S21.
  • the degree of progress is discriminated by the degree of progress discriminator 4 e in the white light discriminator 42 .
  • the progress discriminator 4e calculates a progress discrimination result and a reliability score for the discriminated progress (step S31).
  • the differential classifier 4d skips the process of step S31 when no lesion candidate region is detected by the lesion classifier 4c.
  • the first special light discriminator 43 performs the processing of steps S6 and S22, and the discrimination discriminator 4d in the first special light discriminator 43
  • the degree of progression of the differentiated lesion is identified by the degree of progression identifier 4 e in the first special optical identifier 43 .
  • the progress discriminator 4e calculates the discrimination result of the progress and the reliability score for the discriminated progress (step S32). Note that the differential classifier 4d skips the process of step S32 when no lesion candidate region is detected by the lesion classifier 4c.
  • the second special light discriminator 44 performs the processing of steps S10 and S23, and the discrimination discriminator 4d in the second special light discriminator 44
  • the degree of progression of the differentiated lesion is identified by the degree of progression identifier 4 e in the second special optical identifier 44 .
  • the progress discriminator 4e calculates the discrimination result of the progress and the reliability score for the discriminated progress (step S33). Note that the differential classifier 4d skips the process of step S33 when no lesion candidate region is detected by the lesion classifier 4c.
  • the lesion area selection unit 45 performs the processes of steps S13 and S24, determines the degree of progression corresponding to the discrimination result determined to be displayed in step S24 based on the reliability score, and displays the determined degree of progression. It outputs to the processing unit 46 (step S34).
  • the lesion area selection unit 45 determines, for example, “Mayo1” with the highest reliability score as the degree of progress, and outputs it to the display processing unit 46 .
  • the display processing unit 46 aligns the display area and performs image synthesis to superimpose it on the white light image (first image information), and further performs image synthesis to include the discrimination result and the degree of progress in the vicinity of the white light image.
  • image information for display is generated (step S14B).
  • the generated display image information is output from the endoscope processor 4 to the monitor 5 , and the display image is displayed on the monitor screen of the monitor 5 .
  • a discrimination result 50b and a degree of progress 50c as shown in FIG. 5 are displayed.
  • substantially the same effects as those of the above-described first and second embodiments can be obtained, and the degree of progression of a lesion can be identified and image information for display including the degree of progression can be generated. Therefore, it is possible to reduce variations in the subjective diagnosis of the operator with respect to the degree of progression of the lesion.
  • the present invention has been mainly described above as an endoscope processor and an endoscope apparatus having the endoscope processor, the present invention is not limited to this.
  • the present invention may be a diagnostic image generation method that performs the same processing as the endoscope processor.
  • the present invention may be a computer program for causing a computer to perform processing similar to that of an endoscope processor, a non-temporary computer-readable recording medium for recording the computer program, or the like.
  • the present invention is not limited to the above-described embodiment as it is, and in the implementation stage, the constituent elements can be modified and embodied without departing from the scope of the invention.
  • various aspects of the invention can be formed by appropriate combinations of the plurality of constituent elements disclosed in the above embodiments. For example, some components may be omitted from all components shown in the embodiments. Furthermore, components across different embodiments may be combined as appropriate. As described above, it goes without saying that various modifications and applications are possible without departing from the gist of the invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Surgery (AREA)
  • Multimedia (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Optics & Photonics (AREA)
  • Endoscopes (AREA)
PCT/JP2021/025365 2021-07-05 2021-07-05 内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法 Ceased WO2023281607A1 (ja)

Priority Applications (5)

Application Number Priority Date Filing Date Title
PCT/JP2021/025365 WO2023281607A1 (ja) 2021-07-05 2021-07-05 内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法
CN202180097925.0A CN117241719A (zh) 2021-07-05 2021-07-05 内窥镜处理器、内窥镜装置以及诊断用图像生成方法
JP2023532905A JP7592165B2 (ja) 2021-07-05 2021-07-05 内視鏡プロセッサ、内視鏡装置、および内視鏡装置の作動方法
US18/382,556 US12469247B2 (en) 2021-07-05 2023-10-23 Endoscope processor, endoscope device, and method of generating diagnostic image
US19/359,134 US20260038227A1 (en) 2021-07-05 2025-10-15 Endoscope processor, endoscope device, and method of generating diagnostic image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/025365 WO2023281607A1 (ja) 2021-07-05 2021-07-05 内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/382,556 Continuation US12469247B2 (en) 2021-07-05 2023-10-23 Endoscope processor, endoscope device, and method of generating diagnostic image

Publications (1)

Publication Number Publication Date
WO2023281607A1 true WO2023281607A1 (ja) 2023-01-12

Family

ID=84800437

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/025365 Ceased WO2023281607A1 (ja) 2021-07-05 2021-07-05 内視鏡プロセッサ、内視鏡装置、および診断用画像生成方法

Country Status (4)

Country Link
US (2) US12469247B2 (https=)
JP (1) JP7592165B2 (https=)
CN (1) CN117241719A (https=)
WO (1) WO2023281607A1 (https=)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024202789A1 (ja) * 2023-03-28 2024-10-03 富士フイルム株式会社 医療支援装置、内視鏡システム、医療支援方法、及びプログラム
TWI871715B (zh) * 2023-07-27 2025-02-01 臺北醫學大學 內視鏡測距方法及內視鏡系統

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7603560B2 (ja) * 2021-09-17 2024-12-20 Hoya株式会社 コンピュータプログラム、情報処理方法及び内視鏡
CN119624893B (zh) * 2024-11-22 2025-09-09 珠海开云科技有限公司 一种肺部内窥镜图像导航识别方法和系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011224038A (ja) * 2010-04-15 2011-11-10 Olympus Corp 画像処理装置及びプログラム
JP2012005512A (ja) * 2010-06-22 2012-01-12 Olympus Corp 画像処理装置、内視鏡装置、内視鏡システム、プログラム及び画像処理方法
WO2017104046A1 (ja) * 2015-12-17 2017-06-22 オリンパス株式会社 内視鏡装置
WO2018221033A1 (ja) * 2017-06-02 2018-12-06 富士フイルム株式会社 医療画像処理装置、内視鏡システム、診断支援装置、並びに医療業務支援装置
WO2019083019A1 (ja) * 2017-10-26 2019-05-02 富士フイルム株式会社 医療画像処理装置、及び、内視鏡装置
WO2020008834A1 (ja) * 2018-07-05 2020-01-09 富士フイルム株式会社 画像処理装置、方法及び内視鏡システム
WO2020017213A1 (ja) * 2018-07-20 2020-01-23 富士フイルム株式会社 内視鏡画像認識装置、内視鏡画像学習装置、内視鏡画像学習方法及びプログラム

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6293911B1 (en) * 1996-11-20 2001-09-25 Olympus Optical Co., Ltd. Fluorescent endoscope system enabling simultaneous normal light observation and fluorescence observation in infrared spectrum
US6527708B1 (en) * 1999-07-02 2003-03-04 Pentax Corporation Endoscope system
US7272252B2 (en) * 2002-06-12 2007-09-18 Clarient, Inc. Automated system for combining bright field and fluorescent microscopy
US7697975B2 (en) * 2003-06-03 2010-04-13 British Colombia Cancer Agency Methods and apparatus for fluorescence imaging using multiple excitation-emission pairs and simultaneous multi-channel image detection
JP4723281B2 (ja) * 2005-05-16 2011-07-13 Ｈｏｙａ株式会社 電子内視鏡システム
US9111343B2 (en) * 2011-01-18 2015-08-18 Roche Diagnostics Hematology, Inc. Microscope slide coordinate system registration
JP5502812B2 (ja) 2011-07-14 2014-05-28 富士フイルム株式会社 生体情報取得システムおよび生体情報取得システムの作動方法
US10602918B2 (en) * 2013-12-31 2020-03-31 Karl Storz Imaging, Inc. Switching between white light imaging and excitation light imaging leaving last video frame displayed
JP6660707B2 (ja) * 2015-10-23 2020-03-11 Hoya株式会社 内視鏡システム
WO2018155560A1 (ja) 2017-02-24 2018-08-30 富士フイルム株式会社 内視鏡システム、プロセッサ装置、及び、内視鏡システムの作動方法
JP6834019B2 (ja) 2017-10-30 2021-02-24 富士フイルム株式会社 医療画像処理装置、及び、内視鏡装置
WO2020110214A1 (ja) 2018-11-28 2020-06-04 オリンパス株式会社 内視鏡システム、及び、内視鏡用画像処理方法、並びに、内視鏡用画像処理プログラム

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011224038A (ja) * 2010-04-15 2011-11-10 Olympus Corp 画像処理装置及びプログラム
JP2012005512A (ja) * 2010-06-22 2012-01-12 Olympus Corp 画像処理装置、内視鏡装置、内視鏡システム、プログラム及び画像処理方法
WO2017104046A1 (ja) * 2015-12-17 2017-06-22 オリンパス株式会社 内視鏡装置
WO2018221033A1 (ja) * 2017-06-02 2018-12-06 富士フイルム株式会社 医療画像処理装置、内視鏡システム、診断支援装置、並びに医療業務支援装置
WO2019083019A1 (ja) * 2017-10-26 2019-05-02 富士フイルム株式会社 医療画像処理装置、及び、内視鏡装置
WO2020008834A1 (ja) * 2018-07-05 2020-01-09 富士フイルム株式会社 画像処理装置、方法及び内視鏡システム
WO2020017213A1 (ja) * 2018-07-20 2020-01-23 富士フイルム株式会社 内視鏡画像認識装置、内視鏡画像学習装置、内視鏡画像学習方法及びプログラム

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024202789A1 (ja) * 2023-03-28 2024-10-03 富士フイルム株式会社 医療支援装置、内視鏡システム、医療支援方法、及びプログラム
TWI871715B (zh) * 2023-07-27 2025-02-01 臺北醫學大學 內視鏡測距方法及內視鏡系統

Also Published As

Publication number Publication date
JPWO2023281607A1 (https=) 2023-01-12
US20260038227A1 (en) 2026-02-05
US20240046599A1 (en) 2024-02-08
CN117241719A (zh) 2023-12-15
JP7592165B2 (ja) 2024-11-29
US12469247B2 (en) 2025-11-11

Similar Documents

Publication Publication Date Title
JP7592165B2 (ja) 内視鏡プロセッサ、内視鏡装置、および内視鏡装置の作動方法
US8303494B2 (en) Electronic endoscope system, processing apparatus for electronic endoscope, and image processing method
JP6577088B2 (ja) 内視鏡システム
US10426318B2 (en) Image processing apparatus, endoscope system, and image processing method
JP5452300B2 (ja) 電子内視鏡システム、電子内視鏡用のプロセッサ装置、電子内視鏡システムの作動方法、病理観察装置および病理顕微鏡装置
US20180218499A1 (en) Image processing apparatus, endoscope system, and image processing method
JPWO2018159363A1 (ja) 内視鏡システム及びその作動方法
JP7559240B2 (ja) 内視鏡プロセッサ、内視鏡装置、診断用画像表示方法及び診断用画像処理プログラム
JP6471173B2 (ja) 画像処理装置、内視鏡装置の作動方法、画像処理プログラムおよび内視鏡装置
JP7387859B2 (ja) 医用画像処理装置、プロセッサ装置、内視鏡システム、医用画像処理装置の作動方法及びプログラム
WO2010122884A1 (ja) 蛍光画像装置及び蛍光画像取得方法
US20210385367A1 (en) Endoscope apparatus, information storage medium, control method of endoscope apparatus, and processing device
JPWO2017057021A1 (ja) 画像解析装置、画像解析システム、画像解析装置の作動方法
CN112689469A (zh) 内窥镜装置、内窥镜处理器及内窥镜装置的操作方法
JPWO2016110984A1 (ja) 画像処理装置、画像処理装置の作動方法、画像処理装置の作動プログラムおよび内視鏡装置
WO2016121811A1 (ja) 画像処理装置及び画像処理方法、並びに内視鏡システム
US11978209B2 (en) Endoscope system, medical image processing device, and operation method therefor
JP7105300B2 (ja) 内視鏡システム及び内視鏡システムの作動方法
WO2022230607A1 (ja) 医療画像処理装置、内視鏡システム、及び医療画像処理装置の作動方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21949243

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023532905

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 202180097925.0

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21949243

Country of ref document: EP

Kind code of ref document: A1