An image processing apparatus includes a processor including hardware, the processor being configured to: determine whether or not an overlapping portion is present in imaging areas included in a plurality of images captured by a plurality of imagers, respectively, the plurality of imagers being are inserted into a subject to capture images of an observation target at different positions from each other; determine whether or not each of the plurality of imagers is inserted to a focal point position at which the observation target is in focus; and generate a composite image that is composed of the plurality of images when it is determined that each of the plurality of imagers is inserted to the focal point position and that the overlapping portion is present in the imaging areas.

A system and method allow creation of surgical annotations during surgery. A digital image of a treatment site in a region of patient anatomy is captured using a camera and is displayed on an image display. The system displays an overlay marking an anatomic region of interest in the displayed image. During the course of the surgery, panning of the image results in the anatomic region of interest being outside the displayed field of view. In response to user input, the displayed image is subsequently panned such that the anatomic region of interest and the displayed overlay return to the displayed field of view.

Systems and methods for electromagnetic distortion detection are disclosed. In one aspect, the system includes an electromagnetic (EM) sensor configured to generate an EM sensor signal in response to detection of the EM field. The system may also include a processor configured to calculate a baseline value of a metric indicative of a position of the EM sensor at a first time and calculate an updated value of the metric during a time period after the first time. The processor may be further configured to determine that a difference between the updated value and the baseline value is greater than a threshold value and determine that the EM field has been distorted in response to the difference being greater than the threshold value.

An image processing apparatus including a processor comprising hardware. The processor being configured to: divide an imaging signal that is obtained by capturing an image of an inside of a subject into a first base component and a detail component, the first base component corresponding to an illumination component of an object, the detail component corresponding to a reflectance component of the object; generate a second base component by performing a color enhancement process on the first base component for increasing color gradation in a predetermined color space; and synthesize the second base component and the detail component to output a synthesized signal. Where the color enhancement process is an enhancement processing on the first base component for extending a color distribution range of at least one component of an L component, an a component, and a b component in a Lab color space.

An electronic endoscope system includes a plotting unit which plots pixel correspondence points, which correspond to pixels that constitute an intracavitary color image that has a plurality of color components, on a target plane according to color components of the pixel correspondence points, the target plane intersecting the origin of a predetermined color space; an axis setting unit which sets a reference axis in the target plane based on pixel correspondence points plotted on the target plane; and an evaluation value calculating unit which calculates a prescribed evaluation value with respect to the captured image based on a positional relationship between the reference axis and the pixel correspondence points.

An endoscope scope includes: an imaging device that acquires image information; a color filter disposed on pixels of the imaging device and in which primary-color pixels and complementary-color pixels coexist; a detector that detects whether or not an image processor that generates an observation image based on the acquired image information via the color filter is compatible with the image information consisting of an array in which the primary-color pixels and the complementary-color pixels coexist; and a converter that performs Bayer-conversion processing for converting the image information to a Bayer array in a case in which the detector detects that the image processor is not compatible with the image information consisting of the array, and that does not perform the Bayer-conversion processing on the image information in a case in which the detector detects that the image processor is compatible with the image information consisting of the array.

The present disclosure relates to computer-implemented systems and methods for detecting a feature-of-interest in a video. In one implementation, a computer-implemented system may include a discriminator network and a generative network. The discriminator network may include a perception branch and an adversarial branch, the perception branch being configured to output detections of the feature-of-interest in the video. The generative network may be configured to receive detections of the feature-of-interest from the perception branch of the discriminator network and generate artificial representations of the feature-of-interest based on the detections from the perception branch. Further, the adversarial branch may be configured to provide an output identifying differences between the false representations and true representations of the feature-of-interest, and the perception branch may be further configured to be trained by the output of the adversarial branch so that false representations are not detected by the perception branch as true representations.

Proposed is a technology that enables a video signal (endoscopic image) output from an imaging unit to be processed without signal conversion according to an MIPI D-PHY standard. The present disclosure proposes an endoscope system including: an endoscope device that includes an endoscope-side connector unit; a processor that includes a processor-side connector unit; and an attenuation correction unit that corrects attenuation of a video signal from an image sensor disposed at a distal end portion of the endoscope device (FIG. 3).

A diagnosis support system includes a processor. The processor is connected to a plurality of classifiers that are different in performance. The processor displays performance information of each of the classifiers side by side, receives a user's selection of the performance information displayed side by side, and inputs an input image to the classifier associated with the performance information selected by the user.

Surgical systems are provided. In one exemplary embodiment, a surgical system includes a first scope device having a first portion within an extraluminal space and a second portion positioned within an intraluminal space. The first scope device transmits image data of a first scene. A second scope device is disposed within the extraluminal space and transmits image data of a second scene. The first portion of the first instrument is present within the field of view of the second scope device to track the first scope device relative to the second scope device. A controller receives the transmitted image data of the first and second scenes, to determine a relative distance from the first scope device to the second scope device within the extraluminal space, and to provide a merged image. At least one of the first and second scope device in the merged image is a representative depiction thereof.