The invention relates to a computer-implemented method for automatically detecting anatomical structures (3) in a medical image (1) of a subject, the method comprising applying an object detector function (4) to the medical image, wherein the object detector function performs the steps of: (A) applying a first neural network (40) to the medical image, wherein the first neural network is trained to detect a first plurality of classes of larger-sized anatomical structures (3a), thereby generating as output the coordinates of at least one first bounding box (51) and the confidence score of it containing a larger-sized anatomical structure; (B) cropping (42) the medical image to the first bounding box, thereby generating a cropped image (11) containing the image content within the first bounding box (51); and (C) applying a second neural network (44) to the cropped medical image, wherein the second neural network is trained to detect at least one second class of smaller-sized anatomical structures (3b), thereby generating as output the coordinates of at least one second bounding box (54) and the confidence score of it containing a smaller-sized anatomical structure.

A computer-implemented system and method for predicting female sex bovine offspring to result from a bovine embryo by processing video image data of the embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data.

A data processing method that is suitable for obtaining quantitative information from data obtained by OCT imaging. The image processing method includes acquiring original image data corresponding to a three-dimensional image of a cultured embryo obtained by optical coherence tomography imaging of the embryo and executing a region segmentation the three-dimensional image into a plurality of regions on the basis of the original image data. In the region segmentation, a local thickness calculation is performed on the three-dimensional image to determine an index value indicating a size of an object included in the three-dimensional image, the three-dimensional image is segmented into a region indicated by the index value greater than a predetermined first threshold and a region indicated by the index value less than the first threshold, and each of the regions resulting from the segmentation is further segmented by the watershed algorithm.

Disclosed herein include systems, devices, and methods for detecting embryo polarization from a 2D image generated from a 3D image of an embryo that is not fluorescently labeled using a convolutional neural network (CNN), e.g., deep CNN.

Systems and methods are provided for enhanced heart medical imaging operations, particularly as by incorporating use of artificial intelligence (AI) based fetal heart functional analysis and/or real-time and automatic ejection fraction (EF) measurement and analysis.

Disclosed in the present invention are a method and apparatus for the identification of fetal cross-sections based on ultrasound dynamic images; the method includes: inputting sequentially each frame of fetal ultrasound images from acquired multiple consecutive frames of fetal ultrasound images into a predetermined feature-detecting model for analysis; acquiring a sequentially exported analysis from the feature-detecting model as feature information for each frame of fetal ultrasound images; corresponding to each frame of fetal ultrasound images, identifying a cross-section by the categories of the part and the structural feature. Obviously, for a fetal ultrasound image, the implementation of the present invention may improve the identified accuracy, identified efficiency, and the standardization of the cross-section, by acquiring the part features and structural features from consecutive multi-frame fetal ultrasound images and identifying the cross-section by combining the part features and structural features.

Methods and systems are for improvements to in-vitro fertilization using morpho-kinetic signatures. These improvements are achieved by analyzing a series of images of a developing embryo (e.g., time-lapse images) as opposed to a single static image. For example, due to the difficulty in identifying clear distinctions between morphological states based on static images, as well as the unpredictability of morpho-kinetic development of an embryo, the system analyzes the development of an embryo as a whole over a given time frame (e.g., fertilization to blastulation), which provides a better prediction of the viability of a given embryo. The analysis may take the form of a morpho-kinetic signature, which itself may be used to determine an optimal time to transfer and/or implant an embryo into a patient.

A plurality of ultrasound frames of a fetus are acquired using an ultrasound scanner, which may be oriented arbitrarily with respect to the fetus during the acquisition. The ultrasound frames are processed against an artificial intelligence model to predict a different cut line on each of the ultrasound frames. Each cut line is predicted to be exterior to an image of the fetus appearing on the ultrasound frame. The different cut lines on the plurality of ultrasound frames are then used to identify ultrasound data in the image frames to generate a 3D representation of the fetus.

The present invention teaches a method of predicting the potential for manifestation of various medical conditions by analyzing human placenta comprising and including determining the need for early monitoring, intervention or potential treatment for medical conditions likely to manifest as a child grows older and investigating the potential for various medical conditions. The method includes selecting and identifying a sample of the placenta to analyze by algorithms and preparing the sample to be analyzed. The sample is captured by obtaining a three-dimensional digital image of the chorionic surface of the sample by a selected capturing device. The physician corrects for errors in the digital image and loads the data into a computer for analysis. The digital image data is analyzed using algorithms to determine the vascular structure of the placenta, which is interpreted and analyzed to determine the potential for manifestation of various medical conditions.

There is disclosed a non-transitory computer-readable recording medium having stored therein an information processing program for causing a computer to execute a process. The process includes: specifying a first region, a second region and a third region from a nondestructive inspection image, the first region corresponding to a recess-free shape, the second region corresponding to a detection target included in the recess-free shape, the third region corresponding to a reference object included in the recess-free shape; specifying a first straight line that divides the first region into two and that passes through the third region; obtaining two intersections of the first straight line and an outer circumference of the recess-free shape; specifying a second straight line that passes through a center point of the two intersections and that is orthogonal to the first straight line; and outputting information indicative of a position of the detection target in the nondestructive inspection image, using a coordinate system using the first straight line and the second straight line as axes.