The present disclosure provides a system for predicting diabetic retinopathy progression. The system includes an image-capturing module and a processing unit. The image-capturing module is configured to capture a first fundus image of a user at a first time and a second fundus image of the user at a second time different from the first time. The processing unit is configured to receive the first fundus image and the second fundus image, compare the first fundus image and the second fundus image and indicate a difference between the first fundus image and the second fundus image. The processing unit is also configured to provide a prediction in a diabetic retinopathy progression of the user based on the difference. A method for predicting diabetic retinopathy progression is also provided in the present disclosure.

A teleoperated system comprises a display, a master input device, and a control system. The control system is configured to determine an orientation of an end effector reference frame relative to a field of view reference frame, determine an orientation of a master input device reference frame relative to a display reference frame, establish an alignment relationship between the master input device reference frame and the display reference frame, and command, based on the alignment relationship, a change in a pose of the end effector in response to a change in a pose of the master input device. The alignment relationship is independent of a position relationship between the master input device reference frame and the display reference frame. In one aspect, the teleoperated system is a telemedical system such as a telesurgical system.

A method is for providing an aggregate algorithm for processing medical data. In an embodiment, a multitude of local algorithms are trained by machine learning. The training of each respective local algorithm is performed on a respective local system using respective local training data. A respective algorithm dataset concerning the respective local algorithm is transferred to an aggregating system that generates the aggregate algorithm based on the algorithm datasets.

A method is for providing an aggregate algorithm for processing medical data. In an embodiment, a multitude of local algorithms are trained by machine learning. The training of each respective local algorithm is performed on a respective local system using respective local training data. A respective algorithm dataset concerning the respective local algorithm is transferred to an aggregating system that generates the aggregate algorithm based on the algorithm datasets.

Provided is a medical video processing system capable of moderating changes in image quality of medical video resulted from encoding, and, an encoder used for the medical video system. A medical video system 1000 has a monitor group 300 and an encoder 400 that accept medical video input from a switches 100 through separate transmission paths, and the encoder 400 subjects the input medical video to encoding as well as image quality adjustment.

A method and system for validating a parameter in a medical study are disclosed. The method includes receiving the medical study from a source. A processor determines a first parameter of the medical study to be validated. An imaging protocol is received from a configuration file in an imaging unit. The imaging protocol includes a second parameter corresponding to the first parameter in the medical study. The processor determines if there is a mismatch of the first parameter in the medical study and the second parameter in the imaging protocol. If there is a mismatch, the processor corrects the first parameter in the medical study based on the second parameter in the imaging protocol to validate the medical study.

A method and system for validating a parameter in a medical study are disclosed. The method includes receiving the medical study from a source. A processor determines a first parameter of the medical study to be validated. An imaging protocol is received from a configuration file in an imaging unit. The imaging protocol includes a second parameter corresponding to the first parameter in the medical study. The processor determines if there is a mismatch of the first parameter in the medical study and the second parameter in the imaging protocol. If there is a mismatch, the processor corrects the first parameter in the medical study based on the second parameter in the imaging protocol to validate the medical study.

Methods and systems are provided for processing different-modality digital images of tissue. The method includes, for each image, detecting biological entities in the image and generating an entity graph comprising entity nodes, representing respective biological entities, interconnected by edges representing interactions between entities represented by the entity nodes. The method also includes selecting, from each image, anchor elements comprising elements corresponding to anchor elements of at least one other image, and generating an anchor graph in which anchor nodes, representing respective anchor elements, are interconnected with entity nodes of the entity graph for the image by edges indicating relations between entity nodes and anchor nodes. The method further includes generating a multimodal graph by interconnecting anchor nodes of the anchor graphs for different images via correspondence edges indicating correspondence between anchor nodes, and processing the multimodal graph to output multimodal data, derived from the plurality of images, for medical evaluation.

Methods and systems are provided for processing different-modality digital images of tissue. The method includes, for each image, detecting biological entities in the image and generating an entity graph comprising entity nodes, representing respective biological entities, interconnected by edges representing interactions between entities represented by the entity nodes. The method also includes selecting, from each image, anchor elements comprising elements corresponding to anchor elements of at least one other image, and generating an anchor graph in which anchor nodes, representing respective anchor elements, are interconnected with entity nodes of the entity graph for the image by edges indicating relations between entity nodes and anchor nodes. The method further includes generating a multimodal graph by interconnecting anchor nodes of the anchor graphs for different images via correspondence edges indicating correspondence between anchor nodes, and processing the multimodal graph to output multimodal data, derived from the plurality of images, for medical evaluation.

An objective of the present invention is to provide a disease prediction system for assessing, by means of a simple method, the possibility that an animal may contract a disease in the future, and the like. The disease prediction system is provided with a reception means for receiving an input of a facial image of an animal excluding a human and an assessment means for outputting, by using a learned model, a prediction regarding contraction of a disease by the animal as inferred from the facial image of the animal that has been input to the reception means, the disease prediction system being characterized in that the learned model is a learned model that performs learning by using facial images of animals excluding humans and the presence or absence of a contracted disease within a predetermined period from the time of imaging the animals as training data, inputs a facial image of an animal, and outputs a prediction regarding whether the animal may contract a disease.