The invention relates to a computer-assisted method for position determination for an intraocular lens supported by machine learning. The method comprises providing a scan result for an eye. The scan result here represents an image of an anatomical structure of the eye. The method further comprises use of a trained machine learning system for the direct determination of a final location of an intraocular lens to be fitted, wherein digital data of the scan of the eye is used as the input data for the machine learning system.

Methods and systems for determining interaction between cells are described wherein the method includes determining or receiving a sequence of images representing manipulating first cells, in a holding space, the holding space including a functionalized wall comprising second cells, the manipulating including settling of the first cells onto the functionalized wall and applying a force on the settled first cells; detecting groups of pixels representing first cells in first images representing the settling of the first cells onto the functionalized wall; tracking locations of detected first cells in the first images; and, determining settling events, a settling event being determined if a cell in a first image is not distinguishable from background of the first image, the location in the image at which a cell settling event is detected defining a cell settling location; detecting groups of pixels representing cells in second images captured during the application of the force and tracking locations of detected cells, wherein tracked locations of a detected cell in the second images form a tracking path, the first location of the tracking path defining a pop-up event, the location in a second image at which a pop-up event is detected defining a pop-up location; and, determining detachment events based on the settling locations and based on the pop-up locations, a detachment event defining a first cell being detached from a second cell due to application of the force on the first cell, and determining information about the interaction between first and second cells based on the force applied to the first cells.

The disclosure discloses a method, a device, a system and a computer storage medium for obtaining the CT perfusion imaging parameter maps of brain. The method includes: obtaining CT perfusion images, pre-processing the CT perfusion images, and obtaining discrete contrast agent concentration curves C(n) of each pixel point in the brain tissue; reading the acquisition time information of the CT perfusion images to obtain the acquisition time arrays T(n); intercepting the acquisition time arrays T(n) to obtain the relative acquisition time arrays t(n); combining the discrete contrast agent concentration curves C(n) with the corresponding relative acquisition time arrays t(n) to obtain the discrete time-concentration curves C(t.sub.n) of each pixel point in the brain tissue; after fitting or interpolating the discrete time-concentration curves C(t.sub.n), re-discretizing at the same time interval, and obtaining the discrete time-concentration curves C(n)′ of each pixel point in brain tissue.

A wound-size measuring method for use in a portable electronic device is provided. The method includes the following steps: obtaining an input image via a camera device of the portable electronic device; using a CNN (convolutional neural network) model to recognize the input image, and selecting a part of the input image with the highest probability of containing a wound as an output wound image; and calculating an actual height and an actual width of the output wound image according to a lens-focal-length parameter reported by an operating system running on the portable electronic device, a plurality of reference calibration parameters corresponding to a pitch angle of the portable electronic device, and a pixel-height ratio and a pixel-width ratio of the output wound image.

Methods and systems are provided for analyzing diffusion weighted images (DWI) using impeded diffusion fraction models for quantitative imaging diagnostic assay of cancer, such as glandular tissue cancers. The Impeded diffusion fraction models are tissue and cancer independent and generate a single score representative of multi-compartment diffusion fractions occurring within each voxel of a DWI image.

A method and apparatus for identifying blood vessels in ultrasound images and displaying blood vessels in ultrasound images are described. In some embodiments, the method is implemented by a computing device and includes receiving ultrasound images that include a blood vessel, and determining, with a neural network implemented at least partially in hardware of the computing device, diameters of the blood vessel in the ultrasound images. The diameters include a respective diameter of the blood vessel for each ultrasound image of the ultrasound images. The method includes determining a blood vessel diameter based on the diameters of the blood vessel, selecting a color based on the blood vessel diameter, and indicating, in one of the ultrasound images, the blood vessel with an indicator having the color.

A combination unit generates a plurality of composite two-dimensional images from a plurality of tomographic images acquired by performing tomosynthesis imaging on an object using different generation methods. In this case, the combination unit generates a first composite two-dimensional image having a quality corresponding to a two-dimensional image acquired by simple imaging or a second composite two-dimensional image in which a structure included in the object has been highlighted as at least one of the plurality of composite two-dimensional images.

The present invention provides a comprehensive detection device and method for a cancerous region, and belongs to the technical field of deep learning. In the present invention, a cancerous region detection network is trained for preprocessed and annotated CT image data to predict bounding box coordinates of a cancerous region and a corresponding cancer confidence score; a clinical analysis network is trained for preprocessed clinical data with a cancer risk level to predict a cancer probability value of a corresponding patient; and a predicted cancer probability value is weighted to a predicted cancer confidence score to realize a comprehensive determination of the cancerous region. The present invention can detect a cancerous region with high accuracy and high performance.

Methods and systems are provided for extracting cardiac frequency angiographic phenomena for an unconstrained vascular object from an angiographic study. In one example, a computer may obtain a series of angiographic image frames obtained at a rate faster than cardiac frequency. Each image frame may comprise a plurality of pixels, and each pixel may have a corresponding intensity. The computer may apply an optical flow technique to the angiographic image frames to generate a plurality of paths corresponding to a displacement of respective pixels from image frame to image frame. The computer may further generate a spatiotemporal reconstruction of cardiac frequency angiographic phenomena based on the plurality of paths and the corresponding intensities associated with respective pixels of the paths, and output for display the spatiotemporal reconstruction of cardiac frequency angiographic phenomena in one or more images.

This patent includes a method for utilizing imaging biomarkers to improve pharmacologic dosing strategies. Specifically, biomarker specific CT and MM examination protocols are disclosed. Dose adjustments based on imaging biomarkers are discussed. Longitudinal analysis of imaging biomarkers is disclosed assess effectiveness of pharmacotherapy and dosing strategies thereof. Finally, manufacturing of a combination pill with day-to-day variations of drug quantities is disclosed.