A method for characterizing a state of an end effector of an ultrasonic device is disclosed. The ultrasonic device including an electromechanical ultrasonic system defined by a predetermined resonant frequency. The electromechanical ultrasonic system further including an ultrasonic transducer coupled to an ultrasonic blade. The method including applying, by an energy source, a power level to the ultrasonic transducer; measuring, by a control circuit coupled to a memory, an impedance value of the ultrasonic transducer; comparing, by the control circuit, the impedance value to a reference impedance value stored in the memory; classifying, by the control circuit, the impedance value based on the comparison; characterizing, by the control circuit, the state of the electromechanical ultrasonic system based on the classification of the impedance value; and adjusting, by the control circuit, the power level applied to the ultrasonic transducer based on the characterization of the state of the end effector.

A method of detecting colon polyps disclosed in the present disclosure includes: (a) receiving an image captured by an endoscope inserted into colon of a test subject; (b) recognizing each image section including colonic mucosa and colonic blood vessels in the image; (c) determining whether a colonic vascular bed is disconnected in each image section; (d) displaying a first visual effect representing a vascular bed in which the colonic blood vessels are disconnected; and (e) displaying a second visual effect representing a continuous vascular bed of the colonic blood vessels, wherein operation (b) is configured to recognize each image section through a deep learning model, which is machine learned based on blood vessel data in a plurality of colonic images of the test subject obtained from external annotators, and a degree of disconnection of the vascular bed and a blood vessel pattern.

A system for controlling a medical image capture device during surgery, the system including: circuitry configured to receive a first image of the surgical scene, captured by the medical image capture device from a first viewpoint, and additional information of the scene; determine, for the medical image capture device, in accordance with the additional information and previous viewpoint information of surgical scenes, one or more candidate viewpoints from which to obtain an image of the surgical scene; provide, in accordance with the first image of the surgical scene, for each of the one or more candidate viewpoints, a simulated image of the surgical scene from the candidate viewpoint; control the medical image capture device to obtain an image of the surgical scene from the candidate viewpoint corresponding to a selection of one of the one or more simulated images of the surgical scene.

A method and device for multimodal imaging of dermal and mucosal lesions. The method includes using at least two imaging modalities from which one is a 3D scan of the lesion, and, additionally providing information on the distance and angulation between scanning device and the dermis or mucosa and mapping at least the second modality over the 3D data.

An artificial intelligence system is trained and used to detect regions of interest on mechanically-enhanced or otherwise mechanically-altered tissue. An internal imaging device (e.g., endoscope) with a mechanical enhancement element alters tissue from its natural state or orientation such that regions of interest on the tissue may be more clearly distinguished from the surrounding tissue. Images of such mechanically-altered tissue are used to train an artificial intelligence system to detect regions of interest with greater accuracy.

The invention relates to a medical optical system. The medical optical system comprises: —a microendoscope (3) for capturing histological images, each of which displays a microscopic tissue section (16) of a macroscopic tissue region (15) with a tumor (23); and—a classification device (31) for classifying the macroscopic tissue sections (16) displayed in the histological images as at least one respective tissue section that represents the tumor (23) or a tissue section that represents healthy tissue and for outputting a classification result for each classified microscopic tissue section (16). The medical optical system additionally comprises a combination device (37) which generates a macroscopic classification image (43) by combining the classification results, said classification image representing the location of the tumor (23) in the macroscopic tissue region (15).

An image processing device acquires an image obtained by irradiating an area of a living body with light having a wavelength of 955 [nm] to 2025 [nm]. The image processing device inputs the acquired image to a learned model or a statistical model generated in advance for detecting, from the image, a tumor present in the area, and determines whether or not a tumor is present at each point in the image.

A portable endoscopic system comprising an imaging unit for an endoscopic procedure. The imaging unit has an imaging coupler for receiving imaging information from an imaging assembly of an endoscope; a display integrated into a housing of the imaging unit; an image processing unit for processing the received imaging information into images of a time series and to displaying the image in real-time; a motion sensor configured to detect a motion of the housing; and a detection processing unit. The detection processing unit is configured to classify at least one anatomical feature in each image of the time series based on an artificial intelligence classifier; determine a confidence metric of the classification; determine a motion vector based on the detected motion; and display, concurrently with the corresponding image, the classification of the at least one anatomical feature, the determined confidence metric, and the determined motion vector.

An apparatus, system and process for identifying one or more different tissue types are described. The method may include applying a configuration to one or more programmable light sources of an imaging system, where the configuration is obtained from a machine learning model trained to distinguish between the one or more different tissue types captured in image data. The method may also include illuminating a scene with the configured one or more programmable light sources, and capturing image data that includes one or more types of tissue depicted in the image data. Furthermore, the method may include analyzing color information in the captured image data with the machine learning model to identify at least one of the one or more different tissue types in the image data, and rendering a visualization of the scene from the captured image data that visually differentiates tissue types in the visualization.

Various embodiments of the present disclosure encompass manipulative endoscopic guidance device employing an endoscopic viewing controller (20) for controlling a display of an endoscopic view (11) of an anatomical structure, and a manipulative guidance controller (30) for controlling a display of one or more guided manipulation anchors (50-52) within the display of the endoscopic view (11) of the anatomical structure. A guided manipulation anchor (50-52) is representative of a location marking and/or a motion directive of a guided manipulation of the anatomical structure (e.g., grasping, pulling, pushing, sliding, reorienting, tilting, removing, or repositioning of the anatomical structure). The manipulative guidance controller (30) may generate an anchor by analyzing a correlation of the endoscopic view (11) of the anatomical structure with a knowledge base of image(s), model(s) and/or details corresponding to the anatomical structure and by deriving the anchor based on a degree of correlation of the endoscopic view (11) of the anatomical structure with the knowledge base.