An endoscopic vessel harvesting system for surgical removal of a blood vessel to be used for coronary bypass uses endoscopic instruments for isolating and severing the vessel. An endoscopic camera in the endoscopic instruments captures images from a distal tip of the instrument within a dissected tunnel around the vessel. An image processor assembles a three-dimensional model of the tunnel from a series of images captured by the endoscopic camera. An augmented-reality display coupled to the image processor renders (e.g., visibly displays to the user in their field of view) a consolidated map representing the three-dimensional model along with a marker in association with the map indicating a current location of the distal tip.

An intraoral imaging apparatus, a medical apparatus, and a program capable of providing auxiliary data for determination regarding diseases having differences in intraoral findings are provided. The intraoral imaging apparatus includes: an imaging device that acquires an intraoral image; a light source that emits light to a subject of the imaging device; a storage apparatus that stores an algorithm for performing determination of a specific disease; and an arithmetic apparatus, in which the arithmetic apparatus executes: a determination process of determining a possibility of the predetermined disease based on the image and the algorithm; and an output process of outputting a result of the determination process.

An image processing system includes a processor, the processor performing processing, based on association information of an association between a biological image captured under a first imaging condition and a biological image captured under a second imaging condition, of outputting a prediction image corresponding to an image in which an object captured in an input image is to be captured under the second imaging condition. The association information is indicative of a trained model obtained through machine learning of a relationship between a first training image captured under the first imaging condition and a second training image captured under the second imaging condition. The processor is capable of outputting a plurality of different kinds of prediction images based on a plurality of trained models and the input image, and performs processing, based on a given condition, of selecting the prediction image to be output among a plurality of prediction images.

The application relates to devices and methods for analysing a colonoscopy video or a portion thereof, and for assessing the severity of ulcerative colitis in a subject by analysing a colonoscopy video obtained from the subject. Analysing a colonoscopy video comprises using a first deep neural network classifier to classify image data from the subject colonoscopy video or portion thereof into at least a first severity class (more severe endoscopic lesions) and a second severity class (less severe endoscopic lesions), wherein the first deep neural network has been trained at least in part in a weakly supervised manner using training image data from a plurality of training colonoscopy videos, the training image data comprising multiple sets of consecutive frames from the plurality of training colonoscopy videos, wherein frames in a set have the same severity class label. Devices and methods for providing a tool for analysing colonoscopy videos are also described.

Methods, systems, and computer-readable media for detecting image degradation during a surgical procedure are provided. A method includes receiving images of a surgical instrument; obtaining baseline images of an edge of the surgical instrument; comparing a characteristic of the images of the surgical instrument to a characteristic of the baseline images of the edge of the surgical instrument, the images of the surgical instrument being received subsequent to obtaining the baseline images of the edge of the surgical instrument and being received while the surgical instrument is disposed at a surgical site in a patient; determining whether the images of the surgical instrument are degraded, based on the comparing of the characteristic of the images of the surgical instrument and the characteristic of the baseline images of the surgical instrument; and generating an image degradation notification, in response to a determination that the images of the surgical instrument are degraded.

A method for supporting a user, a corresponding computer program product, a corresponding data medium, and a corresponding imaging system are provided. According to the method, a three-dimensional (3D) data set depicting a target object is provided, and at least one two-dimensional (2D) image of the target object is automatically acquired. The 2D image and the 3D data set are automatically registered with each other by a 2D/3D registration. A spatial direction in which the 2D/3D registration exhibits greatest uncertainty is automatically specified. A signal for aligning an instrument that is provided for the purpose of examining the target object is then automatically generated and output as a function of the specified spatial direction in order to support the user.

The present disclosure relates to a method for filtering selectively obstacle to be an obstacle to machine learning according to a learning purpose and a system thereof. A system for filtering obstacle data in machine learning of medical images may include an obstacle data definition unit configured to receive definitions of obstacle data according to a machine learning purpose; a filter generation unit configured to generate a filter for filtering the obstacle data; and a filtering unit configured to remove obstacle data in machine learning using the generated filter.

A surgical operation support apparatus 1 for performing effective display with respect to a target site image according to the situation has a detection unit 2 that detects a target site image from an image capturing an inside of a living body, an estimation unit 3 that estimates whether the target site image is being observed, and a display information generation unit 4 that generates a first display for facilitating observation of the target site image, if it is estimated that the target site image is being observed.

A support device for an endoscope comprises a tubular member configured for removable attachment to an outer surface of the endoscope near, or at, its distal end and a plurality of projecting elements extending outward from the outer surface of the tubular member and circumferentially spaced from each other. The device includes an optically transparent cover coupled to the tubular member and configured for covering the distal end of the endoscope when the tubular member is attached to the outer surface of the endoscope. The projecting elements provide support for the endoscope, improve visualization and center the scope as it passes through a body lumen, such as the colon. In addition, the cover seals the distal end of the endoscope to protect the scope and its components from debris, fluid, pathogens and other biomatter.

An image processing apparatus includes a processor including hardware. The processor is configured to: set a first acquisition condition and a second acquisition condition for a video processor configured to acquire a first image that is based on a display-purpose acquisition condition for acquiring an image for display at a frame rate for viewing and a second image that is based on an analysis-purpose acquisition condition for acquiring an image for image analysis at a frame rate that is lower than the frame rate for viewing, in a mixed manner, the first acquisition condition including the display-purpose acquisition condition, the second acquisition condition including the display-purpose acquisition condition and the analysis-purpose acquisition condition; generate support information based on an image analysis result; and control switching between the first acquisition condition and the second acquisition condition according to the image analysis result.