An image processing device includes a processor, and the processor decides whether or not to perform image processing on the medical image on the basis of an imaging condition of the medical image and/or an image analysis result obtained by analyzing the medical image. The processor performs, for the medical image on which the processor has decided to perform the image processing, at least one of calculation of an index value related to a stage of ulcerative colitis, determination of the stage of the ulcerative colitis, or determination of remission or non-remission of the ulcerative colitis on the basis of denseness of superficial blood vessels, intramucosal hemorrhage, and extramucosal hemorrhage that are obtained from the medical image.

An endoscope processor according to one aspect includes an image acquisition unit that acquires a captured image from an endoscope, a first correction unit that corrects the captured image acquired by the image acquisition unit, a second correction unit that corrects the captured image acquired by the image acquisition unit, and an output unit that outputs an endoscopic image based on the captured image corrected by the first correction unit and a recognition result using a trained image recognition model in which the recognition result is output in a case where the captured image corrected by the second correction unit is input.

A medical endoscope image recognition method is provided. In the method, endoscope images are received from a medical endoscope. The endoscope images are filtered with a neural network, to obtain target endoscope images. Organ information corresponding to the target endoscope images is recognized via the neural network. An imaging type of the target endoscope images is identified according to the corresponding organ information with a classification network. A lesion region in the target endoscope images is localized according to an organ part indicated by the organ information. A lesion category of the lesion region in an image capture mode of the medical endoscope corresponding to the imaging type is identified.

Systems and methods are provided for delivering consistent high quality, cost efficient results in fixed or mobile endoscopy facilities, without requiring the continuous real-time involvement of a fellowship trained gastroenterologist, by integrating patient specific information into decision support systems and AI/machine learning systems employed during the planning and examination phases of the endoscopy procedure.

An image processing method is provided, including: obtaining a target image; invoking an image recognition model including: a backbone network, a pooling module and a dilated convolution module that are connected to the backbone network and that are parallel to each other, and a fusion module connected to the pooling module and the dilated convolution module; performing feature extraction on the target image by extracting, using the backbone network, a feature map of the target image, separately processing, using the pooling module and the dilated convolution module, the feature map, to obtain a first result outputted by the pooling module and a second result outputted by the dilated convolution module, and fusing the first result and the second result by using the fusion module into a model recognition result of the target image; and determining a semantic segmentation labeled image of the target image based on the model recognition result.

A deep learning-based examination and diagnosis assistance system and apparatus for early digestive tract cancer comprising a feature extraction network, an image classification model, an endoscope classifier, and an early cancer recognition model. The feature extraction network is used for performing initial feature extraction on endoscope images based on a neural network model; the image classification model is used for performing extraction on the initial features to acquire image classification features; the endoscope classifier is used for performing feature extraction on the initial features to acquire endoscope classification features and classify gastroscope/colonoscope images; the early cancer recognition model is used for splicing the initial features, the endoscope classification features, and the image classification features to acquire the probability of early cancer lesions in white light images, electronic dye images or chemical dye images of a corresponding site or acquire a flushing prompt or position recognition prompt for the corresponding site.

A method and apparatus for sharpening gastrointestinal (GI) images are disclosed. A target distance between the target region and the imaging apparatus is determined for a target region in the regular image. One or more filter parameters of a de-blurring filter are selected from stored filter parameters according to the target distance. A processed target region is generated by applying the de-blurring filter to the target region to improve sharpness of the target region. A method for characterizing an imaging apparatus is also disclosed. The imaging apparatus is placed under a controlled environment. Test pictures for one or more test patterns are captured at multiple test distances in a range including a focus distance using the imaging apparatus. One or more parameters associated a target point spread function are determined from each test picture for characterizing image formation of the imaging apparatus at the selected distance.

Methods, systems and computer program products for recognition of partially digested medications are provided. Aspects include receiving an image depicting regurgitated stomach contents of an individual and obtaining medical data regarding the individual. Aspects also include analyzing the image, by a recognition model, to identify one or more pills depicted in the image and a percentage of the one or more pills that has not been digested. Aspects further include performing an action based on the medical data, the identification of the one or more pill and the percentage of the one or more pills that has not been digested.

An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line, and displaying the combined image on the display.

Systems and methods are disclosed for identifying images that contain polyps. An exemplary method for identifying images includes: accessing images of a gastrointestinal tract (GIT) captured by a capsule endoscopy device, where: each image of the images is suspected to include a polyp and is associated with a probability of containing the polyp, and the images include seed images, where each seed image is associated with one or more images of the images. The image(s) associated with each seed image is identified as suspected to include the same polyp as the associated seed image. The method includes applying a polyp detection system on the seed images to identify seed images which include polyps, where the polyp detection system is applied to each seed image of based on the image(s) associated with the seed image and the probabilities associated with the seed image and with the associated image(s).