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.

Identifying polyps or lesions in a colon. In some variations, computer-implemented methods for polyp detection may be used in conjunction with an endoscope system to analyze the images captured by the endoscopic system, identify any polyps and/or lesions in a visual scene captured by the endoscopic system, and provide an indication to the practitioner that a polyp and/or lesion has been detected.

Example embodiments of the present invention relate to an image processing apparatus. The apparatus may include a processor and memory storing instructions that when executed on the processor cause the processor to perform the operations of detecting a deep region of a duct in an image and extracting a plurality of contour edges of an inner wall of the duct in the image. The apparatus then may identify a plurality of convex regions among the plurality of contour edges, analyze a respective curvature of each of the plurality of convex regions to identify a convex direction for each of the plurality of convex regions, and detect, as an abnormal region, a convex region having a convex direction directed toward the deep region.

An image processing apparatus including: a memory to store intraluminal images captured by a medical device inserted into a living body, the intraluminal images being associated with time series; and a processor to detect an abnormal area from intraluminal images captured by a medical device inserted into a living body, set a similar abnormal section where the abnormal areas being similar to each other are included, generate information related to the similar abnormal section, extract an intraluminal image that is used as a representative image from among the intraluminal images belonging to the similar abnormal section, control the display device to display the representative image, extract, as the information related to the similar abnormal section from among the intraluminal images, non-representative images which are part of intraluminal images other than the representative image, and control a display device to display the information related to the similar abnormal section.

An image processing device includes a processor comprising hardware, wherein the processor is configured to execute: acquiring intraluminal images; generating, for each of the intraluminal images, lesion information by estimating a visual point with respect to a lesion region extracted from each of the intraluminal images and analyzing a three-dimensional structure of the lesion, the lesion information indicating any of a top portion, a rising portion, and a marginal protruding portion in the lesion region; and extracting, based on the lesion information, a target image satisfying a prescribed condition from the intraluminal images.

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.

Disclosed herein are methods for identifying polyps or lesions in a colon. In some variations, computer-implemented methods for polyp detection may be used in conjunction with an endoscope system to analyze the images captured by the endoscopic system, identify any polyps and/or lesions in a visual scene captured by the endoscopic system, and provide an indication to the practitioner that a polyp and/or lesion has been detected.

An image processing device includes: a specific candidate area extracting unit configured to extract a specific candidate area that satisfies a predetermined condition from an intraluminal image captured inside a body lumen; a reference area setting unit configured to set a reference area that includes at least a part of the specific candidate area; a local area extracting unit configured to extract local areas based on the reference area; a local feature data calculator configured to calculate local feature data that is feature data of each of the local areas; a weight setting unit configured to set a weight depending on each of the local areas based on the specific candidate area; and a feature data integrating unit configured to integrate the local feature data.

An endoscopic image processing apparatus includes a processor, and the processor performs processing for detecting a region-of-interest from sequentially inputted observation images; performs enhancement processing of a position corresponding to the region-of-interest, on the observation images of the subject inputted after a first period elapses from a time point of a start of detection of the region-of-interest, when the region-of-interest is continuously detected; and sets the first period based on at least one of position information indicating a position of the region-of-interest in the observation images and size information indicating a size of the region-of-interest in the observation images.

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.