Provided are: an image diagnosis assistance apparatus capable of assisting diagnosis of an endoscopic image captured by an endoscopist; a data collection method; an image diagnosis assistance method; and an image diagnosis assistance program. The image diagnosis assistance apparatus is provided with: a lesion assessment unit that assesses, by a convolutional neural network, the denomination and the position of a lesion which is present in a digestive system endoscopic image of a patient captured by a digestive system endoscopic imaging device and information about accuracies thereof; and a display control unit that performs control for generating an analysis result image in which the denomination and the position of the lesion and the accuracies thereof are displayed and for displaying the image on the digestive system endoscopic image.

Systems and methods for assisting user with hearing by amplifying sound using an amplifier with gain and amplitude controls for a plurality of frequencies; and applying a learning machine to identify an aural environment and adjust the amplifiers for optimum hearing.

There are provided a medical image processing device, and endoscope system, a diagnosis support method, and a program which can support diagnosis by avoiding an inappropriate report in a case where any of site information of an observation target and lesion type information detected from a medical image is incorrect. The medical image processing device includes at least one processor. The at least one processor acquires the medical image, acquires the site information indicating a site of an observation target included in the medical image, in a human body, detects a lesion from the medical image to acquire the lesion type information indicating a lesion type, determines presence or absence of a contradiction between the site information and the lesion type information, and decides a report mode of the site information and the lesion type information on the basis of a determination result.

Airway management methods, devices, assemblies and systems. Methods, devices, assemblies and systems may include robotic movement and control of an intubation tube introducer or guide, and may include utilizing image data from one or more image sensors. The methods, devices, assemblies and systems may optionally be used in endotracheal intubation procedures.

An illumination control device includes an image data acquirer, a control data acquirer, and a light source controller. The image data acquirer acquires target imaging-related data related to the target imaging in a case in which target imaging is performed in which an image of an inserter inserted into a hole part continuous with a target is captured by an imaging device together with the target. The control data acquirer acquires control data based on the acquired target imaging-related data. The light source controller controls an illumination state of a light source provided around an optical axis of the imaging device, based on the acquired control data.

The present invention relates to a hysteresis compensation control apparatus of a flexible tube and a method thereof for compensation control of hysteresis of a surgical instrument disposed in a channel of an overtube. The hysteresis compensation control apparatus includes: an input unit receiving image information and tension information of a flexible surgical instrument required for mode switching; a mode switching determining unit for determining a current state of the surgical instrument on the basis of the image information of the surgical instrument, and generating a control mode switching signal according to the current state of the surgical instrument; a mode switching unit for switching a control mode from a flexible tube control based on the image information to a flexible tube control based on the tension information according to the control mode switching signal; and a compensation control unit for compensatingly controlling a flexible surgical instrument having hysteresis characteristics on the basis of a tension error value calculated by a learning model.

The present disclosure relates generally to medical imaging, and more specifically to machine-learning techniques for clarifying and enhancing intraoperative images. The system can receive one or more intraoperative images depicting a biological tissue and smoke; input the one or more intraoperative images into a trained neural network to obtain a clarified image depicting the biological tissue that is less obscured by smoke than at least one of the received one or more intraoperative images; enhance, using an equalization algorithm, contrast in the clarified image to obtain an enhanced clarified intraoperative image; and display, on a display, the enhanced clarified intraoperative image, which can be used for decision making within or outside surgeries.

An area of interest within a visual output of a surgical site is identified. An area of interest within a visual output of a surgical site is identified. A zoom operation on the area of interest to generate a magnified area of interest is performed. An occluded region around the area of interest within the visual output is determined based on an amount of zoom associated with the zoom operation. The occluded region is a region of the visual output that becomes occluded by placing a magnified area of interest over the area of interest within the visual output. A non-linear compression to the occluded region of the visual output to generate a compressed occluded region is applied. The magnified area of interest to include the compressed occluded region is updated.

Systems, devices, and methods for providing an endoluminal transhepatic access to a patient pancreaticobiliary system in an endoscopic procedure are disclosed. An example of a transhepatic access procedure comprises navigating a steerable elongate instrument through a body cavity or channel and exiting to a access site of liver, puncturing the liver from the access site, extending the steerable elongate instrument through the liver and into the pancreaticobiliary system and performing an operation therein. Following the operation, the steerable elongate instrument can be retreated, and the access site of liver can be closed with a closure means. Apparatus and methods of training a machine-learning model and using said model to identify patient candidacy for retrograde access based on images of patient anatomy are also disclosed.

A processor for an endoscope according to an aspect is characterized by including: a controller executing program code to perform: acquiring, by the controller, an endoscopic image captured using first system information; discriminating a part of a subject using a first learning model that outputs a discrimination result of discriminating the part of the subject in a case in which the acquired endoscopic image is input; acquiring, by the controller, a setting image associated with the discrimination result output by the first learning model; and outputting second system information using a second learning model that outputs the second system information in a case in which the acquired setting image and the part of the subject are input.