In the present invention, information is analyzed, the positional relationship of cells/microbes in the optical axis direction is detected, and motility of cells/microbes is evaluated even in an out-of-focus view from an image obtained by a single image capture in an observation view of the cells/microbes. The present invention is provided with an optical system used to measure microparticles present in a sample liquid in a sample container, a drive mechanism for driving the sample container and/or a portion of the optical system in order to three-dimensionally search a bottom surface of the sample container, a control unit for controlling the optical system or the drive mechanism, an image processing unit for dividing an image of microparticles in the sample container at a first time and a second time into an in-focus region and an out-of-focus region and acquiring information relating to the microparticles, and a display unit for displaying the information relating to the microparticles as information representing a temporal change between the first time and the second time.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.

A method for deep learning video microscopy-based antimicrobial susceptibility testing of a bacterial strain in a sample by acquiring image sequences of individual bacterial cells of the bacterial strain in a subject sample before, during, and after exposure to each antibiotic at different concentrations. The image sequences are compressed into static images while preserving essential phenotypic features. Data representing the static images is input into a pre-trained deep learning (DL) model which generates output data; and antimicrobial susceptibility for the bacterial strain is determined from the output data.

A movement of an area whose shape changes for each respiration or for each heartbeat is displayed. A diagnosis support program that analyzes images of a human body and displays analysis results, the program causing a computer to execute: processing of acquiring a plurality of frame images from a database that stores the images (S1); processing of specifying a respiratory cycle based on pixels in a specific area in each of the frame images (S2); processing of detecting a lung field based on the specified respiratory cycle (S3); processing of dividing the detected lung field into a plurality of block areas (S4) and calculating a change in image in a block area in each of the frame images (S5); processing of performing a Fourier analysis of a change in image in each block area in each of the frame images (S6); and processing of displaying each image after the Fourier analysis on a display as a pseudo color image (S7).

A computer-implemented method for providing a cardiac motion classification based on Cardiac Magnetic Resonance (CMR) image data, wherein the CMR image data comprise a plurality of image frames, I(x, y, z, t), acquired for respective two-dimensional slices in at least one longitudinal direction, z, of the heart and for a plurality of times, t, the method including: a myocardium segmentation step of inputting the plurality of image frames into two or more trained neural networks, applying the trained neural networks in parallel, and fusing an output of each of the trained neural networks into a single output indicating a segmentation, for each of the plurality of image frames, between a first portion indicating muscle tissue of the heart and a second portion indicating surrounding tissue of the heart muscle, and determining a corresponding mask of muscle tissue for the first portion; a slice classification step of assigning each of the plurality of image frames in each slice, z, to an anatomic layer of the heart; a movement feature extraction and classification step of, for each of the masks and the corresponding anatomic layers, extracting a movement feature of the heart and classifying the movement feature into one of a number of pre-determined movement features; an associating step of associating the classified movement feature with the corresponding layer for the cardiac motion classification.

A medical-information processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires medical image data that is obtained during imaging on the subject in a resting state in the time phase where the relationship between the volume of blood flow and the pressure in a blood vessel in the cardiac cycle of the subject indicates a proportional relationship. The processing circuitry extracts the structure of a blood vessel, included in the medical image data, applies fluid analysis to the structure of the blood vessel to obtain a first index value, which is obtained based on the pressure in the blood vessel on the upstream side of a predetermined position within the blood vessel and the relation equation between the volume of blood flow and the pressure in the blood vessel in the resting state, and a second index value, which is obtained based on the pressure in the blood vessel on the downstream side of the predetermined position and the relation equation, and calculates the pressure ratio, which is the ratio of the first index value to the second index value.

Disclosed are a software for analyzing images of a fertilized egg, the software providing a means for executing a process including: (a) a step of measuring the difference in area between the female pronucleus and the male pronucleus from images of a fertilized egg obtained in a period of 1 to 10 hours before the time of occurrence of male and female pronuclear membrane breakdown as a reference; (b) a step of measuring the difference in are between the female pronucleus and the male pronucleus from images of the fertilized egg obtained immediately before the time of occurrence of male and female pronuclear membrane breakdown as the reference; and (c) a step of storing the measured values of the area difference obtained in the step (a) and the area difference obtained in the step (b), to be readable at any time as needed, and an apparatus incorporating this software.

A framework for quantitative evaluation of time-varying data. In accordance with one aspect, the framework delineates a volume of interest in a four-dimensional (4D) Digital Subtraction Angiography (DSA) dataset (204). The framework then extracts a centerline of the volume of interest (206). In response to receiving one or more user-selected points along the centerline (208), the framework determines at least one blood dynamics measure associated with the one or more user-selected points (210), and generates a visualization based on the blood dynamics measure (212).

A detecting method adapted to detect a detecting cassette is provided. A detecting cassette is placed into a device main body to be located at a detecting region inside the device main body. At least one image of the detecting region is captured by an image capturing unit. Whether a function of the image capturing unit is normal is determined by a determining unit according to a grayscale value of the at least one image. If the function of the image capturing unit is normal, a detection result is determined by the determining unit according to a portion of the at least one image corresponding to the detecting cassette.

Provided is an observation device including: a stereo image-acquisition optical system that acquires images of cells floating in a culture fluid inside a culture vessel; and an analyzer that calculates a cell density of the cells on the basis of the images acquired by the stereo image-acquisition optical system, wherein the analyzer identifies a three-dimensional position of each of the cells included in the images and calculates the cell density on the basis of the number of cells present within a predetermined three-dimensional region.