An image processing apparatus includes a first acquisition unit that acquires a first pixel signal output from a first pixel, a second acquisition unit that acquires a second pixel signal output from a second pixel having a size smaller than that of the first pixel, a temperature detection unit that detects temperature; a composition gain determination unit that determines a composition gain corresponding to the detected temperature, and a composition unit that composes the first pixel signal and the second pixel signal multiplied by the composition gain.

There are provided a learning apparatus, a learning method, an image processing apparatus, an endoscope system, and a program that enable generation of training data on the basis of output data from a learning model for which learning is performed by using normality data. A first learning model (500) is generated by performing first learning using normality data (502) as learning data or by performing first learning using as learning data, normality mask data (504) that is generated by making a part of normality data be lost, and second training data to be applied to a second learning model that identifies identification target data is generated by using output data output from the first learning model in response to input of abnormality data to the first learning model.

An assist device includes: a processor configured to generate a fluorescence image based on an imaging signal that is generated by capturing an image of fluorescence caused by excitation light that is applied to a living tissue, calculate a fluorescence intensity based on the fluorescence image, based on the fluorescence intensity, estimate a placement period during which a medical tool is placed in a lumen, and output placement period information on the placement period and an observation image obtained by capturing an image of the living tissue.

A special observation image is obtained by performing an image pickup of an object to be observed illuminated with special light. Bs-image signals of the special observation image are assigned to brightness signals Y to generate a first observation image for display. Gs-image signals of the special observation image are assigned to brightness signals Y to generate a second observation image for display. The first observation image for display and the second observation image for display are automatically switched and displayed on a monitor.

A special observation image is obtained by performing an image pickup of an object to be observed illuminated with special light. Bs-image signals of the special observation image are assigned to brightness signals Y to generate a first observation image for display. Gs-image signals of the special observation image are assigned to brightness signals Y to generate a second observation image for display. The first observation image for display and the second observation image for display are automatically switched and displayed on a monitor.

Offset illumination using multiple emitters in a fluorescence imaging system is described. A system includes an emitter for emitting pulses of electromagnetic radiation and an image sensor comprising a pixel array for sensing reflected electromagnetic radiation. The emitter comprises a first emitter and a second emitter for emitting different wavelengths of electromagnetic radiation. The system is such that at least a portion of the pulses of electromagnetic radiation emitted by the emitter comprises electromagnetic radiation having a wavelength from about 770 nm to about 790 nm.

A stylet assembly and method of forming an in vivo image acquiring stylet assembly. The stylet assembly includes an elongate flexible body and an image acquiring device that is supported at a location that is offset from an in vivo facing terminal end of the stylet assembly. A terminal end portion of the stylet assembly is defined by a manipulator that is oriented to extend in a crossing direction relative to a longitudinal axis of the elongate body. The terminal end portion of the stylet assembly is steerable relative to the elongate body and is operable to manipulate positions or adjacent anatomy and/or effectuate guidance of the imaging device relative thereto during use.

A stylet assembly and method of forming an in vivo image acquiring stylet assembly. The stylet assembly includes an elongate flexible body and an image acquiring device that is supported at a location that is offset from an in vivo facing terminal end of the stylet assembly. A terminal end portion of the stylet assembly is defined by a manipulator that is oriented to extend in a crossing direction relative to a longitudinal axis of the elongate body. The terminal end portion of the stylet assembly is steerable relative to the elongate body and is operable to manipulate positions or adjacent anatomy and/or effectuate guidance of the imaging device relative thereto during use.

An exemplary medical system includes a first electrical circuit on a printed circuit board (PCB) and configured to generate data, a second electrical circuit on the PCB and electrically isolated from the first electrical circuit, and a radio frequency (RF) communication interface assembly on the PCB. The RF communication interface assembly includes an RF transmitter electrically coupled to the first electrical circuit and electrically isolated from the second electrical circuit, an RF receiver out of direct RF signal path alignment with the RF transmitter, electrically coupled to the second electrical circuit, and electrically isolated from the first electrical circuit, and a waveguide between the RF transmitter and the RF receiver and configured to guide an RF signal representative of the data between the RF transmitter and the RF receiver.

An endoscope observation assistance apparatus includes an image information acquiring part to acquire and display a captured image of a luminal organ captured by the endoscope device on a display, a lesion information acquisition part to detect a predetermined lesion based on the captured image and to acquire lesion information regarding the lesion, a lesion disappearance determination part to track the lesion based on the captured image and the lesion information and to determine whether or not the lesion has disappeared from the captured image, and a notification part to notify a determination result when the lesion disappearance determination part determines that the lesion has disappeared from the captured image. Alternatively, the notification part may notify a lesion detection when a short time period passes after the lesion detection by the lesion information acquisition part.