Abstract: An image processing apparatus includes a processor. The processor is configured to acquire image information from an endoscope during observation of an inside of a subject, generate an organ model from the acquired image information, identify an unobserved region that is not observed by the endoscope in the organ model, estimate a top and a bottom and an azimuth of an image pickup visual field of the endoscope with respect to the organ model, set a display direction of the organ model based on the top and the bottom and the azimuth of the image pickup visual field, and output the organ model to the monitor, the organ model being associated with the identified unobserved region.

Abstract: An endoscope processor includes a processor. The processor detects a first region of a lesion candidate from first image information which is acquired by irradiation with first illumination light; detects a second region of a lesion candidate from second image information acquired by irradiation with second illumination light having a different spectrum from the first illumination light; selects a region for display of the lesion candidate out of the first region and the second region, corresponding to an observation target site of a subject; and generates image information for display, in which the region for display is superimposed on the first image information.

Abstract: An endoscope processor includes a processor. The processor discriminates, in first image information acquired by applying first illumination light, between first region image information constituted of an object of an interest subject and second region image information constituted of an object of a non-interest subject, generates third region image information of a region in second image information acquired by applying second illumination light, the region including at least a part of a region of the second region image information, the second illumination light having a wavelength different from a wavelength of the first illumination light and passing through the object of the non-interest subject, and combines the first region image information and the third region image information, to generate a partial transparent image in which the object of the non-interest subject of the first image information is made transparent.

Abstract: An endoscopic image processing apparatus includes a processor having a lesion recognizing function capable of recognizing a lesioned part included in an image generated by applying predetermined processing. The processor has the lesion recognizing function implemented by performing machine learning using, as a plurality of learning images, a plurality of past observation images generated through the predetermined processing, and the processor performs conversion processing for converting, based on a setting value for learning image equivalent to a past setting value for observation image used in the predetermined processing performed at generation of each of the plurality of learning images, the image into an image for lesion recognition used for processing corresponding to the lesion recognizing function.

Abstract: An image processing apparatus for endoscope includes a processor. The processor sequentially receives a plurality of observation images of an endoscope, detects one or more lesioned parts from each of the plurality of observation images, analyzes visibility of at least one of a distance from the endoscope, an occupied area, a shape, a size, a position in the observation image, a color, luminance, or an organ part relating to the detected lesioned part, sets a display extension time of a detection result of the lesioned part according to the visibility, and outputs the observation image to which the detection result of the lesioned part is added.

Abstract: A processor of an endoscope system detects from the observation images a lesion area which is an observation target of the endoscope, judges a level of an oversight risk which is a risk that an operator may overlook the lesion area, on the basis of the observation images, and controls notification methods of detection of the lesion area on the basis of the level of the oversight risk. The processor displays the marker image indicating the lesion area only in a second image region of the display apparatus when a level of the oversight risk relating to the lesion area is a first level and displays the marker image in both a first image region and the second image region which is smaller than the first image region when a level of the oversight risk relating to the lesion area is a second level higher than the first level.

Abstract: A diagnosis support system includes a processor. The processor is connected to a plurality of classifiers that are different in performance. The processor displays performance information of each of the classifiers side by side, receives a user's selection of the performance information displayed side by side, and inputs an input image to the classifier associated with the performance information selected by the user.

Abstract: An image processing apparatus includes a processor including hardware, the processor being configured to: estimate, based on image information from a medical device that includes at least an endoscope, a plurality of procedure actions of an operator of the endoscope; perform different supports respectively for procedures by the operator, according to an estimation result of the procedure actions; and output a display for the supports to a display.

Abstract: A diagnosis support apparatus performs identification for a plurality of support items, which are identification classifications about diagnosis support, and the diagnosis support apparatus is provided with a processor. The processor performs analysis processing for acquiring analysis results including an analysis result about an observation mode by analyzing at least one of an input signal specifying the observation mode and an observation image obtained by observing an inside of a subject with an endoscope; performs support item setting processing for setting a support item corresponding to the analysis results obtained by the analysis processing, among the plurality of support items, which are the identification classifications; and generates diagnosis support information, which is information used for diagnosis of a legion candidate area included in the observation image, based on an identification index corresponding to the set support item and the observation image.

Abstract: A training data generating system includes a processor. The processor acquires a plurality of medical images. The processor associates medical images with each other which are included in the plurality of medical images based on similarities of an imaging target to generate an associated image group including medical images associated with each other. The processor outputs, to a display, an application target image to be an image as an application target of representative training information based on the associated image group. The processor accepts input of representative contour information indicative of a contour of a specific region in the application target image as the representative training information. The processor applies contour information, as training information, to each medical image included in the associated image group based on the representative training information input to the application target image.

Abstract: An image recording system includes a processor. The processor acquires a time series RAW image group including a plurality of time series RAW images in a first time section. The processor extracts, from the time series RAW image group, a recording candidate RAW image group included in a second time section as a part of the first time section. The processor records at least one RAW image included in the recording candidate RAW image group as a recording target RAW image which is a RAW image to be recorded. The processor selects the recording target RAW image from the recording candidate RAW image group. The processor converts the RAW image which is not selected as the recording target RAW image from the recording candidate RAW image group or the time series RAW image group to compressed data, and records the compressed data.

Abstract: An endoscope apparatus includes a processor. The processor conducts analysis whether an endoscope image has been appropriately captured or not on the basis of the endoscope image. The processor acquires correction restriction information that is at least one of a restriction regarding a size of a lumen of an image-captured portion or a restriction regarding a submucosa state of the image-captured portion. The processor generates correction information regarding correction of image-capturing conditions for allowing the endoscope image to be appropriately captured under a restriction of the correction restriction information in a case where it is analyzed that the endoscope image has not been appropriately captured, and outputs the correction information on a monitor.

Abstract: An image processing apparatus includes an input unit, an estimation unit, an acquisition unit, a production unit, and a display control unit. The input unit acquires examination information including an endoscope image. The estimation unit estimates an image pickup site based on the endoscope image. The acquisition unit acquires, from the examination information, image pickup information corresponding to the endoscope image and indicating a state of at least one of an endoscope or a subject when the endoscope image is picked up. The production unit produces a model map and associates the image pickup information with a virtual site based on a result of the estimation by the estimation unit. The display control unit controls a display device.

Abstract: A medical image data creation apparatus for training acquires a first medical image, acquires a second medical image that is different from the first medical image and is obtained by photographing a substantially same spot as in the first medical image, creates lesion region information concerning a lesion part in the second medical image, and creates medical image data for training in which the first medical image and the lesion region information are associated with each other.

Abstract: An image processing apparatus includes a processor. The processor receives endoscope images to be determined, in each of which an image of an inside of a body of a subject is picked up, determines whether or not an endoscope image for comparison concerning a predetermined inspection site, and the endoscope images to be determined are same or similar, determines whether or not an observation mode of each of the endoscope images to be determined is a condition suitable for automatic recording, and automatically records a predetermined number of the endoscope images to be determined in a recording unit, when the endoscope images to be determined and the endoscope image for comparison are determined to be the same or similar and when the observation mode is the condition suitable for automatic recording.

Abstract: A diagnosis assisting apparatus includes a processor. The processor is configured to detect at least one target region from an acquired image and output position information of the target region. The processor is also configured to classify the target region based on predetermined classification conditions corresponding to diagnosis indices and output diagnosis assisting information indicating a degree of seriousness of the target region. The processor is then configured to control a display image such that a first period, during which the diagnosis assisting information is displayed in a first region, is different from a second period, during which the position information is superimposed on the image in a second region and is displayed.

Abstract: An information processing apparatus includes a processor. The processor acquires a medical image, identifies the acquired medical image and acquires an identification result, analyzes a motion relating to interpretation of the medical image by a user to acquire a motion analysis result, and compares the identification result and the motion analysis result and acquires a comparison result relating to coincidence or noncoincidence of the identification result and the motion analysis result.

Abstract: A diagnosis support apparatus includes a processor including at least one piece of hardware. The processor identifies, based on physical information including one or more kinds of information capable of estimating a state of a diagnosis target organ of a subject, one abnormal symptom appearing in the diagnosis target organ, performs, as lesion extraction processing for extracting a lesion candidate region from an endoscopic image, different processing specialized for each abnormal symptom that appears in the diagnosis target organ, and performs the lesion extraction processing corresponding to the identified one abnormal symptom.

Abstract: An image recording device includes a processor. The processor acquires time-series images of endoscopy, temporarily records all of the time-series images of the endoscopy in a buffer memory, retrieves the time-series images temporarily recorded in the buffer memory and identifies an appearance of a lesion from the retrieved time-series images, and records in a memory a predetermined image of the time-series images temporarily recorded in the buffer memory, according to the identified appearance of the lesion.

Abstract: An endoscope system includes an endoscope and an image processing device attached to one another. The image processing device includes at least one processor configured to perform operations of determining an operator's action based on an action signal from an endoscope inserted into a subject body, deciding whether an image is set as a detection target image based on the operator's action and detecting a specific region from the detection target image. The processor performs an operation of determining whether the operator's action at a time of capturing the image is a treatment action to give the subject body a treatment. Furthermore, the processor detects, from the image, a region, which exhibits a specular reflection and whose time change in area and position is large, as a washed region and then determine the operator's action at the time of capturing the image is the treatment action when the washed region is detected.