Abstract: A learning model preparation method includes: acquiring a non-specific binding specimen image representing a non-specific binding specimen that allows a reagent to act on a tissue containing the endogenous protein, the reagent developing a color in a non-specific binding region in which an endogenous protein exists; and preparing a first learning model by setting the non-specific binding specimen image to first learning data, and by allowing a learning device to learn the non-specific binding region, based on the first learning data.

Abstract: An information processing device includes: a processor including hardware, the processor being configured to cause a display to display a second image according to an input of an operation, the second image corresponding to a field of view corresponding to at least part of a first image contained in imaging data that is generated by capturing an observation subject, analyze change of the field of view over time to calculate an attention degree, and set a region of interest in the first image contained in the imaging data according to the attention degree.

Abstract: An information processing device includes: a processor including hardware. The processor is configured to analyze, based on gaze data obtained by detecting a gaze of a user and input externally, an attention degree of the gaze of the user with respect to an observation image, allocate importance corresponding to the attention degree to speech data representing speech of the user, the speech data being input externally and being associated with a same time axis as a time axis of the gaze data, record the speech data and the importance in a storage, and set a region of interest in the observation image according to the attention degree and the importance.

Abstract: An image processing device includes a processor including hardware. The processor is configured to: sequentially perform, on all at least two types of stains, an extraction process to extract a stained area due to a target stain from a single stain image of the target stain, starting from a stain having high specificity with regard to a target site; and sequentially perform a correction process, on all at least one type of second stain except for a first stain having the highest specificity among the at least two types of stains, to correct the single stain image by excluding stained areas of all stains having higher specificity than the target stain from the single stain image of the target stain, starting from the stain having the high specificity.

Abstract: An information-processing apparatus includes a display displaying an image; a memory recording voice data having a voice pronounced at each of plural observation points of the image; a gaze detector generating gaze data by detecting a gaze of a user; a voice input device generating voice data associated with a time axis identical to that of the gaze data by receiving a voice of the user; and a processor to analyze a attention period where a attention degree of the gaze to each of the plural observation points is a predetermined value or greater, based on the gaze data, set a period where the voice is pronounced with respect to the voice data as an important voice period, based on the voice data, and generate calibration data based on a time lag between the attention period and the important voice period.

Abstract: An image processing apparatus includes: a fluorescence intensity information storage configured to store therein fluorescence intensity information and fluorescence intensity information; and a processor including hardware.

Abstract: A learning model preparation method includes: acquiring a non-specific binding specimen image representing a non-specific binding specimen that allows a reagent to act on a tissue containing the endogenous protein, the reagent developing a color in a non-specific binding region in which an endogenous protein exists; and preparing a first learning model by setting the non-specific binding specimen image to first learning data, and by allowing a learning device to learn the non-specific binding region, based on the first learning data.

Abstract: An information processing apparatus is disclosed which includes a hardware processor configured to, analyze an attention degree of a gaze of a user, on the basis of gaze data in which the gaze of the user is detected, the gaze data being input externally, and assign an important degree according to the attention degree that is analyzed with respect to speech data of the user, the speech data being input externally, and is associated with a time axis that is a same as that of the gaze data to be recorded in a memory.

Abstract: An information processing apparatus is disclosed which includes a hardware processor configured to, analyze an attention degree of a gaze of a user, on the basis of gaze data in which the gaze of the user is detected, the gaze data being input externally, and assign an important degree according to the attention degree that is analyzed with respect to speech data of the user, the speech data being input externally, and is associated with a time axis that is a same as that of the gaze data to be recorded in a memory.

Abstract: An information processing apparatus includes a processor comprising hardware, the processor being configured to execute: setting an utterance period, in which an uttering voice includes a keyword having an importance degree of a predetermined value or more, as an important period with respect to user's voice data input from an external device; and allocating a corresponding gaze period corresponding to the set important period to gaze data that is input from an external device and is correlated with the same time axis as in the voice data, and recording the corresponding gaze period in a memory.

Abstract: An information-processing apparatus includes a display displaying an image; a memory recording voice data having a voice pronounced at each of plural observation points of the image; a gaze detector generating gaze data by detecting a gaze of a user; a voice input device generating voice data associated with a time axis identical to that of the gaze data by receiving a voice of the user; and a processor to analyze a attention period where a attention degree of the gaze to each of the plural observation points is a predetermined value or greater, based on the gaze data, set a period where the voice is pronounced with respect to the voice data as an important voice period, based on the voice data, and generate calibration data based on a time lag between the attention period and the important voice period.

Abstract: An image processing device includes a processor including hardware. The processor is configured to: sequentially perform, on all at least two types of stains, an extraction process to extract a stained area due to a target stain from a single stain image of the target stain, starting from a stain having high specificity with regard to a target site; and sequentially perform a correction process, on all at least one type of second stain except for a first stain having the highest specificity among the at least two types of stains, to correct the single stain image by excluding stained areas of all stains having higher specificity than the target stain from the single stain image of the target stain, starting from the stain having the high specificity.

Abstract: An image processing apparatus includes: a fluorescence intensity information storage configured to store therein fluorescence intensity information and fluorescence intensity information; and a processor including hardware.

Abstract: Provided is a system for observing an object that emits fluorescence when irradiated with excitation light. The system includes: a hole unit having holes on a plane perpendicular to an optical axis of the objective lens to allow the excitation light to pass through the holes in a direction parallel to the optical axis; and an imaging unit including: an imaging lens configured to focus the fluorescence; a microlens array having microlenses arranged on a plane perpendicular to an optical axis of the imaging lens; and an image sensor having pixels configured to: receive the fluorescence via the objective lens, at least one of the holes, and the microlens array, the fluorescence being emitted when the object is irradiated with the excitation light having passed through at least one of the holes and the objective lens; and output an image signal in accordance with an intensity of the received fluorescence.

Abstract: An image processing apparatus includes an image input unit configured to input a plurality of images acquired by imaging a specimen stained with non-fluorescent dye at a plurality of wavelength bands that are different from one another and a characteristic amount calculation unit configured to calculate a characteristic amount representing auto-fluorescence emitted by the specimen based on the plurality of images.

Abstract: An image processing apparatus includes an image acquisition unit that acquires image information representing a fluorescence observation image of a specimen stained with hematoxylin-eosin, a spectrum generation unit that generates a plurality of spectra each representing a wavelength distribution of fluorescence intensity in a plurality of pixels in the fluorescence observation image, a pixel extraction unit that extracts at least two pixel groups with a feature of a particular spectrum from the plurality of pixels, and an image generation unit that generates an image based on the extracted pixel groups.

Abstract: An image processing apparatus includes: an image acquiring unit configured to acquire image information representing an image acquired by irradiating a gland duct with excitation light and observing fluorescence generated in the gland duct; a fluorescence intensity computation unit configured to compute a value corresponding to intensity of the fluorescence as fluorescence intensity based on the image information; and an image determination unit configured to determine whether or not an endocrine cell exists in the gland duct based on the fluorescence intensity computed by the fluorescence intensity computation unit, and to determine abnormality of the gland duct based on a determination result of the endocrine cell.

Abstract: An endoscope device includes: an insertion portion having an imaging optical system on a distal end of the insertion portion and configured to be inserted into a living body; a pressure detecting unit provided on the distal end of the insertion portion or ahead of the distal end and configured to detect contact with the living body by pressure; and an imaging unit configured to image an inside of the living body through the imaging optical system when a detection result of the pressure detecting unit satisfies a predetermined condition.

Abstract: An image processing apparatus includes: an image acquiring unit configured to acquire image information representing an image acquired by irradiating a gland duct with excitation light and observing fluorescence generated in the gland duct; a fluorescence intensity computation unit configured to compute a value corresponding to intensity of the fluorescence as fluorescence intensity based on the image information; and an image determination unit configured to determine whether or not an endocrine cell exists in the gland duct based on the fluorescence intensity computed by the fluorescence intensity computation unit, and to determine abnormality of the gland duct based on a determination result of the endocrine cell.

Abstract: An image processing apparatus includes an image acquisition unit that acquires image information representing a fluorescence observation image of a specimen stained with hematoxylin-eosin, a spectrum generation unit that generates a plurality of spectra each representing a wavelength distribution of fluorescence intensity in a plurality of pixels in the fluorescence observation image, a pixel extraction unit that extracts at least two pixel groups with a feature of a particular spectrum from the plurality of pixels, and an image generation unit that generates an image based on the extracted pixel groups.