The present disclosure relates to computer-implemented systems and methods for training and using generative adversarial networks to detect abnormalities in images of a human organ. In one implementation, a method is provided for training a neural network system, the method may include applying a perception branch of an object detection network to frames of a first subset of a plurality of videos to produce a first plurality of detections of abnormalities. Further, the method may include using the first plurality of detections and frames from a second subset of the plurality of videos to train a generator network to generate a plurality of artificial representations of polyps, and training an adversarial branch of the discriminator network to differentiate between artificial representations of the abnormalities and true representations of abnormalities. Additionally, the method may include retraining the perception branch based on difference indicators between the artificial representations of abnormalities and true representations of abnormalities included in frames of the second subset of plurality of videos and a second plurality of detections.

A processor for an endoscope or the like that assists an endoscopic examination using an appropriate reference image is provided. A processor for an endoscope includes an image acquisition unit that acquires an endoscope image; a region acquisition unit that inputs the endoscope image acquired by the image acquisition unit to a first learning model that outputs a target region corresponding to a predetermined region to be photographed when the endoscope image is input to acquire the target region; and an image output unit that outputs the endoscope image acquired by the image acquisition unit and an index indicating the target region acquired by the region acquisition unit with the endoscope image and the index superimposed.

A handle of a medical device may comprise an actuator; a lock movable relative to the actuator and having a feature movable relative to the actuator; and a rack having plurality of teeth separated from one another by a plurality of gaps. The lock may be configured to move the feature from (a) a first configuration, in which the feature is disposed in the gap, between two of the plurality of teeth, such that the two teeth inhibit the actuator from rotating; to (b) a second configuration, in which the feature is disposed outside of the gap, such that the actuator is rotatable. In the second configuration, the teeth may be disposed between the feature and the actuator.

Systems, methods, and workflows for concomitant procedures are disclosed. In one aspect, the method includes manipulating a flexible instrument using a first robotic arm of a robotic system, manipulating a rigid instrument using a second robotic arm of the robotic system, displaying feedback from the flexible instrument, and displaying feedback from the rigid instrument.

A method of ion imaging is disclosed that includes automatically sampling a plurality of different locations on a sample using a front device which is arranged and adapted to generate aerosol, smoke or vapour from the sample. Mass spectral data and/or ion mobility data corresponding to each location is obtained and the obtained mass spectral data and/or ion mobility data is used to construct, train or improved a sample classification model.

A method is disclosed comprising providing a biological sample on a swab, directing a spray of charged droplets onto a surface of the swab in order to generate a plurality of analyte ions, and analysing the analyte ions.

An overtube device and an endoscope assembly are provided, the overtube device includes an overtube body having a proximal end and a distal end, the overtube body is provided with a bore which extending from the distal end to the proximal end of the overtube body, the bore is configured to allow a passing portion of the endoscope assembly to pass therethrough; a pulling lumen is formed in the overtube body, which extends from the distal end to the proximal end of the overtube body, the pulling lumen is configured to allow a pulling part to pass therethrough, and the distal end of the pulling part is fixed with the distal end of the overtube body.

A deep learning-based examination and diagnosis assistance system and apparatus for early digestive tract cancer comprising a feature extraction network, an image classification model, an endoscope classifier, and an early cancer recognition model. The feature extraction network is used for performing initial feature extraction on endoscope images based on a neural network model; the image classification model is used for performing extraction on the initial features to acquire image classification features; the endoscope classifier is used for performing feature extraction on the initial features to acquire endoscope classification features and classify gastroscope/colonoscope images; the early cancer recognition model is used for splicing the initial features, the endoscope classification features, and the image classification features to acquire the probability of early cancer lesions in white light images, electronic dye images or chemical dye images of a corresponding site or acquire a flushing prompt or position recognition prompt for the corresponding site.

Embodiments of the invention include a medical device for accessing a patient's body portion and used for diagnosis and treatment of medical conditions. Embodiments of the invention may include a particular endoscopic positioning mechanism for placing an endoscope and an additional treatment device within desired body portions in order to assist in diagnosis and treatment of anatomical diseases and disorders. In particular, a medical device according to an embodiment of the invention may include an outer flexible tube and a positioning mechanism configured for rotating one portion of the flexible tube relative to another portion of the flexible tube.

Devices and methods to measure gastric residual volume (GRV) are described where at least one additive component (a GRV indicator) may be dispersed in a body lumen such as a stomach. The GRV indicator may changes a physical (chemical, electrical, thermal, mechanical, optical, etc.) characteristic within the stomach by a measureable degree. This degree of change and/or the rate of return to the previous state, may be used to determine the GRV of a patient. The determined GRV can also be used to automatically or semi-automatically control the patient's feeding rate and/or volume and/or frequency to adequately nourish the patient but avoid complications. The physical characteristic(s) may also be used to detect that the feeding catheter or tube is in the correct location (ie stomach vs lung or esophagus.