The technology is provided to effectively visualize culture statuses related to a plurality of culture targets.

Provided is a control device including a display control unit that controls dynamic display related to a culture status of a culture target including a cell having a division potential, the culture status being estimated along a time series by morphological analysis using a learned model generated on the basis of a machine learning algorithm, in which the display control unit controls comparative display of the culture statuses of a plurality of the culture targets. Furthermore, provided is a control method including controlling, by a processor, dynamic display related to a culture status of a culture target including a cell having a division potential, the culture status being estimated along a time series by morphological analysis using a learned model generated on the basis of a machine learning algorithm, and controlling the display further including controlling comparative display of the culture statuses of a plurality of the culture targets.

In capturing an image of an observation target in a time series, the image of the observation target is captured with a high degree of accuracy.

Provided is a control device including an image capturing control unit that controls image capturing of an observation target including a cell having division potential in a time series. The image capturing control unit controls at least one of a relative horizontal position or a relative focal position between an image capturing unit that performs the image capturing and the observation target on the basis of a recognition result of the observation target calculated with use of a pre-trained model generated on the basis of a machine learning algorithm.

A computer-implemented method is for providing a clinical information. In an embodiment, the computer-implemented method includes receiving input data including a graph representation of a plurality of disease lesions of a patient; applying a trained function to the input data to generate the clinical information, the trained function being based on a graph machine learning model; and providing the clinical information, the clinical information including at least one information for prediction of the disease progression, survival or therapy response of the patient.

Apparatus, systems, and methods to improve imaging quality control, image processing, identification of findings in image data, and generation of notification at or near a point of care for a patient are disclosed and described. An example imaging apparatus includes a memory including chest image data and instructions and a processor. The example processor is to execute the instructions to at least: process the chest image data using a trained learning network in real time after acquisition of the chest image data to identify a pneumothorax in the chest image data; receive feedback regarding the identification of the pneumothorax; and, when the feedback confirms the identification of the pneumothorax, trigger a notification at the imaging apparatus to notify a healthcare practitioner regarding the pneumothorax and prompt a responsive action with respect to a patient associated with the chest image data.

A system and method for automated respirator fit testing by comparing three-dimensional (3D) images are disclosed. An example embodiment is configured to: obtain at least one three-dimensional facial image of an individual at an initial visit (Visit X); capture at least one current 3D facial image of the individual at a subsequent visit (Visit X+n); convert the Visit X image and the Visit X+n image to numerical data for computation and analysis; identify reference points in the Visit X data and the Visit X+n data; determine if the Visit X data and the Visit X+n data is sufficiently aligned; determine if any differences between the VISIT X data and the VISIT X+n data are greater than a pre-defined set of Allowable Deltas (ADs); and record a pass status if the differences between the VISIT X data and the VISIT X+n data are not greater than the pre-defined ADs.

A method is disclosed for providing a virtual tomographic stroke follow-up examination image. In an embodiment, the method includes: receiving a sequence of temporally successive tomographic perfusion imaging data sets of a region for examination; calculating the virtual tomographic stroke follow-up examination image of the region for examination by applying a trained machine learning algorithm to the sequence of temporally successive tomographic perfusion imaging data sets received; and providing the virtual tomographic stroke follow-up examination image calculated.

An ophthalmologic information processing apparatus includes an acquisition unit and a determination unit. The acquisition unit is configured to acquire a captured image of a subject's eye. The determination unit is configured to determine whether or not the captured image acquired by the acquisition unit is an analysis error image including a predetermined analysis error factor.

A method, an apparatus and a system for cell detection are provided. In the apparatus, a hyperspectrum module is used to capture information across electromagnetic spectrums from an image, a stereo camera module is used to capture three-dimensional image information, and the hyperspectrum module and the stereo camera module form a trinocular micro spectrometer. A microscopic optical module is provided for the two modules to form hyperspectrum and three-dimensional image information from a cell and its split cells via a lens. In the method, a series of continuous images are obtained within a time period. An observation image array with a plurality of observation image zones are provided to retrieve coordinates of a plurality of feature points at different times. Finally, a holistic cellular activity can be obtained by analyzing continuous hyperspectrum and 3D image information from the images over time.

The present disclosure is directed towards systems and methods that leverage machine-learned models to decrease the rate at which abnormal sites are missed during a gastroenterological procedure. In particular, the system and methods of the present disclosure can use machine-learning techniques to determine the coverage rate achieved during a gastroenterological procedure. Measuring the coverage rate of the gastroenterological procedure can allow medical professionals to be alerted when the coverage output is deficient and thus allow an additional coverage to be achieved and as a result increase in the detection rate for abnormal sites (e.g., adenoma, polyp, lesion, tumor, etc.) during the gastroenterological procedure.

A computer-implemented system is described for identifying and retrieving similar radiology images to a query image. The system includes one or more fetchers receiving the query image and retrieving a set of candidate similar radiology images from a data store. One or more scorers receive the query image and the set of candidate similar radiology images and generate a similarity score between the query image and each candidate image. A pooler receives the similarity scores from the one or more scorers, ranks the candidate images, and returns a list of the candidate images reflecting the ranking. The scorers implement a modelling technique to generate the similarity score capturing a plurality of similarity attributes of the query image and the set of candidate similar radiology images and annotations associated therewith. For example, the similarity attributes could be patient, diagnostic and/or visual similarity, and the modelling techniques could be triplet loss, classification loss, regression loss and object detection loss.