Systems, devices and methods for performing deep learning process to determine the characteristics of structures of the eye. Deep leaning, imaging devices and methods for laser and phacoemulsification operations. An integrated imaging device, laser-ultrasound, including femto-phaco, system and a computer vision device. Methods of training and using computer vision devices in ophthalmic treatment systems and therapies.

A non-transitory computer-readable storage medium stores a program to cause a computer to perform: acquiring a first analysis result obtained by a computer process on a first medical image of a patient; acquiring a second analysis result obtained by a computer process on a second medical image of the patient; and comparing the first analysis result and the second analysis result and in a situation in which there is a difference, outputting in a manner different from the situation in which there is no difference.

The present disclosure provides a method for ultrasound image processing. an ultrasound image may be obtained. The ultrasound image may be associated with the blood flow velocity. An envelope curve may be determined based on ultrasound image. A plurality of first maximum points of the envelope curve may be determined. A plurality of second maximum points may be obtained by screening the plurality of first maximum points based on amplitude features of the plurality of first maximum points. A plurality of third maximum points may be obtained by correcting the plurality of second maximum points according to time features of the plurality of second maximum points. One or more parameters relating to the blood flow velocity may be determined based on the plurality of third maximum points.

A crop recipe optimization method includes placing crops in an incubator, taking a plurality of images of the crops for measuring crop growth, obtaining a growth score from the plurality of images of the crop, generating, based on the obtained growth score and yield information of the crops, an optimized crop recipe from an artificial intelligence (AI) algorithm, and applying the optimized crop recipe to growing crops in a farm. The plurality of images are associated with one or more crop recipes, and each of the one or more crop recipes represents a set of environmental parameters inside the incubator.

According to one embodiment, a medical image processing apparatus includes processing circuitry. The processing circuitry acquires correspondence information, based on 3D medical image data of an object, that corresponds a blood vessel to information on a dominant area of the blood vessel in a region of the object. The processing circuitry acquires a plurality of X-ray images each including the blood vessel that are collected at different time phases on the object. The processing circuitry identifies, based on the plurality of X-ray images, a flow changed vessel in which blood flow has changed between the different time phases. The processing circuitry performs registration between the flow changed vessel and the 3D medical image data. The processing circuitry estimates information on the dominant area corresponding to the flow changed vessel based on registration results and the acquired correspondence information.

Apparatus and methods are described for use with an output device, and a blood sample that was drawn from a subject. A microscope system acquires first and second images of the blood sample at respective times. A computer processor determines whether, between acquisitions of the first and second images, there was relative motion between at least one erythrocyte within the sample and at least one entity within the sample, by comparing the first and second images to one another. At least partially in response thereto, the computer processor determines whether the entity is an extra-erythrocytic or an intra-erythrocytic entity, and generates an output on the output device, at least partially in response thereto. Other applications are also described.

Disclosed is a method of automated crop monitoring based on the processing and analysis of a large number of high resolution aerial images that map an area of interest using computer vision and machine learning techniques. The method comprises receiving 120 or retrieving image data containing a plurality of high resolution images of crops in an area of interest for monitoring, identifying 130 one or more crop features of each crop in each image, determining 140, for each identified crop feature, one or more crop feature attributes, and generating or determining 160 one or more crop monitoring outputs based, at least in part, on the crop features and crop feature attributes. Also disclosed is a method generating field camera specific training data for the machine learning model used to analyse the received image data.

According to the present invention, one or more image pairs, each consisting of a fluoroscopic image and an angiographic image taken from the same position and the same viewing direction onto the patient and each being a non-stitched image, are acquired. A live fluoroscopic image is registered individually with the fluoroscopic image within the at least one of the one or more image pairs, such that the spatial relationship between the live fluoroscopic image and the at least one fluoroscopic image, and thus with the one or more angiographic images and the one or more image pairs in general, becomes known. Angiographic information representing the vascular structure can then be taken from those parts of the angiographic images within the one or more image pairs which overlap with the live fluoroscopic image and be overlayed over the live fluoroscopic image.

An ultrasound diagnostic apparatus includes an ultrasound probe, a reference image holding unit that holds an ultrasound image acquired by fixing the position of the ultrasound probe as a reference image, a movement vector calculation unit that calculates a movement vector between two ultrasound images, a movement vector integration unit that integrates the movement vectors from the time when the reference image is held until the current time, a deformed image generation unit that generates a deformed image in which the reference image is moved and changed on the basis of an integration result, a tomographic plane determination unit that compares the deformed image with the current ultrasound image, to determine whether or not tomographic planes of the reference image and the current ultrasound image are the same as each other, and a determination result notification unit that notifies a user of a determination result.

A method for predicting the morphological changes of liver tumor after ablation based on deep learning includes: obtaining a medical image of liver tumor before ablation and a medical image of liver tumor after ablation; preprocessing the medical image of liver tumor before ablation and the medical image of liver tumor after ablation; obtaining a preoperative liver region map, postoperative liver region map, and postoperative liver tumor residual image map; obtaining a transformation matrix by a Coherent Point Drift (CPD) algorithm and obtaining a registration result map according to the transformation matrix; training the network by a random gradient descent method to obtain a liver tumor prediction model; using the liver tumor prediction model to predict the morphological changes of liver tumor after ablation. The method provides the basis for quantitatively evaluating whether the ablation area completely covers the tumor and facilitates the postoperative treatment plan for the patient.