The application relates to devices and methods for analysing a colonoscopy video or a portion thereof, and for assessing the severity of ulcerative colitis in a subject by analysing a colonoscopy video obtained from the subject. Analysing a colonoscopy video comprises using a first deep neural network classifier to classify image data from the subject colonoscopy video or portion thereof into at least a first severity class (more severe endoscopic lesions) and a second severity class (less severe endoscopic lesions), wherein the first deep neural network has been trained at least in part in a weakly supervised manner using training image data from a plurality of training colonoscopy videos, the training image data comprising multiple sets of consecutive frames from the plurality of training colonoscopy videos, wherein frames in a set have the same severity class label. Devices and methods for providing a tool for analysing colonoscopy videos are also described.

There is provided a method, comprising: feeding 2D image(s) of an internal surface of a colon captured by an endoscopic camera, into a machine learning model, wherein the 2D image(s) excludes a depiction of an external measurement tool, wherein the machine learning model is trained on records, each including 2D images of the internal surface of the colon of a respective subject labelled with ground truth labels of respective bounding boxes enclosing respective polyps and at least one of an indication of size and a type of the respective polyp indicating likelihood of developing maligiancy, obtaining a bounding box for a polyp and at least one of an indication of size and type of the polyp, and generating instructions for presenting within the GUI, an overlay of the bounding box over the polyp and the at least one of the indication of size and type of the polyp.

An image recording system includes a processor. The processor acquires a time series RAW image group including a plurality of time series RAW images in a first time section. The processor extracts, from the time series RAW image group, a recording candidate RAW image group included in a second time section as a part of the first time section. The processor records at least one RAW image included in the recording candidate RAW image group as a recording target RAW image which is a RAW image to be recorded. The processor selects the recording target RAW image from the recording candidate RAW image group. The processor converts the RAW image which is not selected as the recording target RAW image from the recording candidate RAW image group or the time series RAW image group to compressed data, and records the compressed data.

Detections in video frames of a video signal, which are output from a machine learning model, are associated to generate a detection chain. Display of a detection in the video signal is caused based on a position of the detection in the detection chain, the confidence value of the detection and the location of the detection.

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.

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.

A medical image processing device a reference image that is a medical image with which boundary line information related to a boundary line that is a boundary between an abnormal region and a normal region and landmark information related to a landmark that is a characteristic structure of the subject are associated and a captured image that is the medical image captured in real time, detects the landmark from the captured image, calculates a ratio of match between the landmark included in the reference image and the landmark included in the captured image, estimates a correspondence relationship between the reference image and the captured image on the basis of the ratio of match and information regarding the landmarks included in the reference image and the captured image, and generates a superimposition image in which the boundary line associated with the reference image is superimposed on the captured image on the basis of the correspondence relationship.

Disclosed are various embodiments of systems and methods of deep learning for colorectal polyp screening and providing a prediction of neoplasticity of a polyp. A video of a colonoscopy procedure can be captured. Frames from the video or images associated with the colonoscopy procedure can be extracted. A model for classifying objects that appear in the frames or the images can be obtained. A classification can be determined for a polyp that appears in at least one of the frames or images based on applying the frames or images to an input layer of the model.

A user-interface for visualizing a colonoscopy procedure includes a video region and a navigational map upon which coverage annotations are displayed. A live video feed received from a colonoscope is displayed in the video region. The navigational map depicts longitudinal sections of a colon. The coverage annotations are presented on the navigation map and indicate whether one or more of the longitudinal sections is deemed adequately inspected or inadequately inspected during the colonoscopy procedure.

Embodiments of a system, a machine-accessible storage medium, and a computer-implemented method are described in which operations are performed. The operations comprising receiving a plurality of image frames associated with a video of an endoscopy procedure, generating a probability estimate for one or more image frames included in the plurality of image frames, and identifying a transition in the video when the endoscopy procedure transitions from a first phase to a second phase based, at least in part, on the probability estimate for the one or more image frames. The probability estimate includes a first probability that one or more image frames are associated with a first phase of the endoscopy procedure.