A method of identifying the presence of a suspect region such as a polyp in a body cavity of a subject includes generating successive images of a body cavity of the subject, and comparing the successive images of the body cavity, wherein a suspect region of the body cavity is likely present when the successive images are different in terms of intensity, surroundings, registration, and/or protrusions. Also provided is an apparatus comprising a processor and an endoscope having a camera and one or more illuminators such that the processor is configured to compare the images acquired from the camera and the one or more illuminators to identify the presence of a suspect region such as a polyp.

An image processing apparatus includes: an abnormality candidate region detection unit that detects an abnormality candidate region based on a contour edge of a mucosal wall or a surface shape of the mucosal wall in an intraluminal image of a body; and an abnormal region specifying unit that specifies an abnormal region based on texture information of the abnormality candidate region,

The present disclosure relates to systems and methods for processing real-time video and detecting objects in the video. In one implementation, a system is provided that includes an input port for receiving real-time video obtained from a medical image device, a first bus for transferring the received real-time video, and at least one processor configured to receive the real-time video from the first bus, perform object detection by applying a trained neural network on frames of the received real-time video, and overlay a border indicating a location of at least one detected object in the frames. The system also includes a second bus for receiving the video with the overlaid border, an output port for outputting the video with the overlaid border from the second bus to an external display, and a third bus for directly transmitting the received real-time video to the output port.

A system and method assist gastroscopic image diagnosis based on artificial intelligence. The processor in the system analyzes each video frame of a gastroscopic image using at least one medical image analysis algorithm and detects whether a finding suspected of being a lesion is present in the video frame. When the finding suspected of being a lesion is present in the video frame, the processor calculates the coordinates of the location of the finding suspected of being a lesion. The processor generates display information, including whether the finding suspected of being a lesion is present and the coordinates of the location of the finding suspected of being a lesion.

The present disclosure relates to computer-implemented systems and methods for training and using generative adversarial networks. In one implementation, a system for training a generative adversarial network may include at least one processor that may provide a first plurality of images including representations of a feature-of-interest and indicators of locations of the feature-of-interest and use the first plurality and indicators to train an object detection network. Further, the processor(s) may provide a second plurality of images including representation of the feature-of-interest, and apply the trained object detection network to the second plurality to produce a plurality of detections of the feature-of-interest. Additionally, the processor(s) may provide manually set verifications of true positives and false positives with respect to the plurality of detections, use the verifications tr train a generative adversarial network, and retrain the generative adversarial network using at least one further set of images, further detections, and further manually set verifications.

A computer-implemented system is provided that receives a real-time video captured from a medical image device during a medical procedure. The real-time video may include a plurality of frames. The system may be adapted to detect an object of interest in the plurality of frames and apply one or more neural networks configured to identify a plurality of characteristics of the detected object of interest, such as classification, size, and/or location. In some embodiments, the system is adapted to identify, based on one or more of the plurality of characteristics, a medical guideline and present, in real-time on a display device during the medical procedure, information for the medical guideline.

The present technology relates to an endoscope system in which resolution and an S/N ratio are adjusted to be well-balanced depending on an imaging condition, and further capable of changing a processing load depending on the imaging condition, a method for operating the endoscope system, and a program.

From an image signal in a body cavity imaged by an endoscope apparatus, a low frequency image including a low frequency component and a high frequency image including a high frequency component are extracted. The low frequency image is reduced by a predetermined reduction ratio, and, after image quality improvement processing is performed, is enlarged by an enlargement ratio corresponding to the reduction ratio. At that time, based on condition information indicating an imaging state, when brightness at the time of imaging is sufficient and the high frequency component does not include noise components a lot, the low frequency image and the high frequency image are added to be output as an output image. In addition, based on the condition information, when the brightness at the time of imaging is not sufficient and the high frequency component includes the noise components a lot, only the low frequency image is output as the output image. The present technology can be applied to the endoscope system.

An image processing system connected to an endoscope and processing in real-time endoscopic images to identify suspicious tissues such as polyps or cancer. The system applies preprocessing tools to clean the received images and then applies in parallel a plurality of detectors both conventional detectors and models of supervised machine learning-based detectors. A post processing is also applied in order select the regions which are most probable to be suspicious among the detected regions. Frames identified as showing suspicious tissues can be marked on an output video display. Optionally, the size, type and boundaries of the suspected tissue can also be identified and marked.

Method and apparatus of reconstruction of images from an in vivo multi-camera capsule are disclosed. In one embodiment of the present invention, the capsule comprises two cameras with overlapped fields of view (FOVs). Intra-image based pose estimation is applied to the sub-images associated with the overlapped area to improve the pose estimation for the capsule device. In another embodiment, two images corresponding to the two FOVs are fused by using disparity-adjusted, linear weighted sum of the overlapped sub-images. In yet another embodiment, the images from the multi-camera capsule are stitched for time-space representation.

An endoscope image processing apparatus includes a detection section configured to receive an observation image of a subject, to detect a feature region in the observation image based on a predetermined feature value for the observation image, and further to output a parameter relating to an erroneous detection rate of the detected feature region, a notification section configured to notify, to a surgeon, detection of the feature region in the observation image through notification processing and to generate a first display image including the observation image in a case where the feature region is detected by the detection section, and an enhancement processing section configured to generate a second display image in the observation image to allow the surgeon to estimate probability of erroneous detection from a display image in the case where the feature region is detected by the detection section.