Systems and methods are provided for delivering consistent high quality, cost efficient results in fixed or mobile endoscopy facilities, without requiring the continuous real-time involvement of a fellowship trained gastroenterologist, by integrating patient specific information into decision support systems and AI/machine learning systems employed during the planning and examination phases of the endoscopy procedure.

A system includes a robotic arm, an autosteroscopic display, a user image capture device, an image processor, and a controller. The robotic arm is coupled to a patient image capture device. The autostereoscopic display is configured to display an image of a surgical site obtained from the patient image capture device. The image processor is configured to identify a location of at least part of a user in an image obtained from the user image capture device. The controller is configured to, in a first mode, adjust a three dimensional aspect of the image displayed on autostereoscopic display based on the identified location, and, in a second mode, move the robotic arm or instrument based on a relationship between the identified location and the surgical site image.

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.

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 System for image processing (IPS), in particular for lung imaging. The system (IPS) comprises an interface (IN) for receiving at least a part of a 3D image volume (VL) acquired by PAT an imaging apparatus (IA1) of a lung (LG) of a subject (PAT) by exposing the subject (PAT) to a first interrogating signal. A layer definer (LD) of the system (IPS) is configured to define, in the 3D image volume, a layer object (LO) that includes a representation of a surface (S) of the lung (LG). A renderer (REN) of the system (IPS) is configured to render at least a part of the layer object (LO) in 3D at a rendering view (V.sub.p) for visualization on a display device (DD).

A system for displaying medical imaging data comprising one or more data inputs, one or more processors, and one or more displays, wherein the one or more data inputs are configured for receiving first image data generated by a first medical imaging device, wherein the first image data comprises a field of view (FOV) portion and a non-FOV portion, and the one or more processors are configured for identifying the non-FOV portion of the first image data and generating cropped first image data by removing at least a portion of the non-FOV portion of the first image data, and transmitting the cropped first image data for display in a first portion of the display and additional information for display in a second portion of the display.

Presented herein is a method of using a manually-operated light plane generating module to make accurate measurements of the dimensions of an object seen in an image taken by an endoscopic camera. The method comprises: providing the light plane generating module with distinctive features, introducing the light plane generating module until the distinctive features are visible in the image, aligning the light plane across the object, and providing a processor device and software configured to analyze the camera images. Also described are diagnostic or therapeutic endoscopic tools that comprise an attached light plane generating module to provide the tool with integrated light plane measurement capabilities, wherein the tool is configured to be used in the described method.

A processing device includes a processor, the processor being configured to: acquire a captured image of an inside of a lumen; acquire lumen structure information indicating a structure of the lumen; determine whether the captured image can be analyzed or not and output analysis allowability/non-allowability information indicating whether the captured image is in an analysis allowable state or not based on the captured image and first determination criteria; associate the analysis allowability/non-allowability information with the structure of the lumen based on the analysis allowability/non-allowability information and the lumen structure information to identify an analyzable portion and an unanalyzable portion of the structure of the lumen; and determine that the identified unanalyzable portion is a missed portion based on position and orientation information of a distal end of an insertion section to be inserted in the lumen and second determination criteria.

A medical system includes a processor. The processor is configured to calculate a presence probability of a lesion in a not-yet-observed region inside a hollow organ of a patient, the not-yet-observed region being specified on the basis of an image that has been captured by an imaging sensor of an endoscope inside the hollow organ, and spatial disposition information of a distal end of an insertion part of the endoscope.

An image selection support device supports the selection of a still image based on captured image data obtained by an endoscope. By using a first still image acquired based on the captured image data at a time when an operator of the endoscope performs an acquisition operation of the still image, and one or more second still images acquired from the captured image data at a time different from the time when the acquisition operation is performed, the image selection support device extracts a third still image having an imaging time point that satisfies a predetermined condition with an imaging time point of the first still image from among the second still images, and associates the first still image with the third still image.