An upper gastrointestinal bleeding monitoring system includes a detection device and a signal processing device to determine bleeding condition of an upper gastrointestinal tract by using relation of time and intensity ratios of RGB three primary colors. The detecting device is placed to the upper gastrointestinal tract of a patient via his/her mouth or nasal passage and then stay the upper gastrointestinal tract for several days for detection of bleeding. The signal processing device may receive and display signal from the detection device to help medical professionals check if bleeding occurs in an upper gastrointestinal tract. Moreover, a procedure of determination of bleeding in an upper gastrointestinal tract with the upper gastrointestinal bleeding monitoring system is described.

A tracer detection device includes an enclosed body, and a plurality of tracer sensors, a battery, a memory, and a transmitter, each disposed within the enclosed body. The plurality of tracer sensors is configured to detect measurement values at a surface and underneath the surface of a gastrointestinal tract. The battery is configured to power the plurality of tracer sensors. The memory is configured to receive measurement values detected by the plurality of tracer sensors. The transmitter is configured to transmit measurement values detected by the plurality of tracer sensors to an external device after the enclosed body has passed through the gastrointestinal tract. The enclosed body includes a steering feature that ensures the enclosed body is oriented in an intended direction. The plurality of tracer sensors triggers release of a drug. The plurality of tracer sensors estimate distances to gastrointestinal walls for normalizing signals.

This disclosure features methods and compositions for treating diseases of the gastrointestinal tract with IL-10 or an IL-10 agonist.

A method for operating an accessory device to capture calibration data. The method can include capturing an image of a portion of a user's body that includes the user's stoma and at least two reference locations, and storing distance scale information representative of a distance between the two reference locations. The method further includes processing the captured image, including: identifying the reference locations, identifying the stoma, and generating calibration data representative of one or more stoma parameters as a function of the identified reference locations, identified stoma and the distance scale information. The calibration data can be stored.

A method for evaluating a gastrointestinal tract may include characterizing one or more disease parameters using objective measures obtained from imaging data of a gastrointestinal tract. The one or more disease parameters reflect a measure of at least one of lesions, ulcers, bleeding, stenosis, and vasculature. The method may also include using the one or more characterized disease parameters to classify a disease state.

The current disclosure relates to methods and devices for measuring concentrations of analytes in the gastrointestinal tract of a subject by orally administering a smart pill to the subject, the smart pill comprising two or more sensors, a reference electrode, a power source, a communication interface and electronic circuits, each sensor being able to measure an analyte in the gastrointestinal tract of said subject, wherein the two or more sensors measure different analytes, measuring a concentration of two or more analytes using the two or more sensors, wherein one of the sensors is a pH sensor for measuring hydrogen ions, and wherein the pH sensor is able to locate the smart pill in the gastrointestinal tract by correlating the measured hydrogen ion concentration to a location in the gastrointestinal tract, and transmitting, using the communication interface, the measured concentrations from the two or more sensors to a base device located outside of the body of the subject.

Computational techniques are applied to video images of polyps to extract features and patterns from different perspectives of a polyp. The extracted features and patterns are synthesized using registration techniques to remove artifacts and noise, thereby generating improved images for the polyp. The generated images of each polyp can be used for training and testing purposes, where a machine learning system separates two types of polyps.

An upper gastrointestinal bleeding monitoring system includes a detection device and a signal processing device to determine bleeding condition of an upper gastrointestinal tract by using relation of time and intensity ratios of RGB three primary colors. The detecting device is placed to the upper gastrointestinal tract of a patient via his/her mouth or nasal passage and then stay the upper gastrointestinal tract for several days for detection of bleeding. The signal processing device may receive and display signal from the detection device to help medical professionals check if bleeding occurs in an upper gastrointestinal tract. Moreover, a procedure of determination of bleeding in an upper gastrointestinal tract with the upper gastrointestinal bleeding monitoring system is described.

A method for evaluating a gastrointestinal tract may include characterizing one or more disease parameters using objective measures obtained from imaging data of a gastrointestinal tract. The one or more disease parameters reflect a measure of at least one of lesions, ulcers, bleeding, stenosis, and vasculature. The method may also include using the one or more characterized disease parameters to classify a disease state.

A method for diagnosing a gastric lesion from endoscopic images is provided. The method comprises: acquiring a plurality of gastric lesion images; generating a dataset by linking the plurality of gastric lesion images with patient information; preprocessing the dataset in a way that is applicable to a deep learning algorithm; and building an artificial neural network by training the artificial neural network by using the preprocessed dataset as input and gastric lesion classification results as output.