An ultrasound imaging system including an ultrasound probe having an array of ultrasonic transducers configured to emit generated ultrasound signals into a patient, receive reflected ultrasound signals from the patient, and convert the reflected ultrasound signals into corresponding electrical signals of the ultrasound signals for processing into ultrasound images. The system includes a console having a processor to execute logic that, when executed, causes operations including capturing first and second ultrasound images of a target insertion area of a patient at a first time, generating and causing rendering of a notification indicating results of a comparison of the first ultrasound image and the second ultrasound image. The operations can also include determining, via a machine learning model, whether the second ultrasound image corresponds to the second ultrasound image by at least a threshold amount, and providing a visual indication of a result of applying the trained machine learning model.

Systems, methods, and apparatus are provided for generating an atlas image of a branched structure and predicting a likelihood of success of certain treatments based on the atlas image. In one example, a method includes registering a plurality of images of instances of a branched structure to generate an aligned image for a cohort, wherein the branched structure comprises a central structure and at least one primary branch connected to the central structure; for each primary branch of the branched structure, iteratively registering respective portions of a plurality of images containing the primary branch to generate an aligned image portion of the primary branch; and applying a control grid of the aligned image portion of the primary branch to respective image portions containing the central structure and the other primary branches prior to iteratively registering a next primary branch; and generating an atlas image for the cohort based on the aligned image portions.

Aspects of the subject disclosure may include, for example, obtaining pre-treatment images for candidates for a clinical trial; analyzing the pre-treatment images according to an imaging model that is a machine learning model; predicting, according to the analyzing the pre-treatment images, one or more clinical variables; randomizing, based at least on the predicted variables, each candidate to one of an investigational trial arm or a control trial arm of the clinical trial; obtaining on-treatment images for the candidates; analyzing the on-treatment images according to the imaging model; predicting, based on the analyzing the on-treatment images, the one or more clinical variables for the on-treatment images; generating event estimation curves based on the predicted on-treatment variables for the investigational trial arm and the control trial arm of the clinical trial; and presenting the event estimation curves in the graphical user interface. Other embodiments are disclosed.

A neural network architecture and method for analysis of time series images from an image source employs a 3D-UNet convolutional neural network (CNN) configured to receive the time series images and generate spatiotemporal feature maps therefrom. Multiple sub-convolutional neural network output prongs based on an SRNet architecture receive the feature maps and simultaneously generate inferences for image segmentation, regression of values, and multi-landmark localization.

A computer-implemented method includes generating, via a processor, synthetic vessels. The method also includes performing, via the processor, three-dimensional (3D) computational fluid dynamics (CFD) on the synthetic vessels for different flow rates to generate 3D CFD data. The method further includes extracting, via the processor, 3D image patches from the synthetic vessels. The method even further includes obtaining, via the processor, pressure drops across the 3D image patches from the 3D CFD data. The method yet further includes training, via the processor, a deep neural network utilizing the 3D image patches, the pressure drops, and associated flow rates to generate a trained deep neural network.

An analysis device configured to analyze a correlation between feature values in a cell in response to a stimulus includes: a cell-image acquiring unit configured to acquire a plurality of cell images in which the cell that is stimulated is captured; a feature value calculating unit configured to calculate a feature value for constituent elements that form the cell, based on the plurality of cell images acquired by the cell-image acquiring unit; a correlation calculating unit configured to use the feature value calculated by the feature value calculating unit and to calculate correlations between the constituent elements; a correlation selecting unit configured to select a first correlation from the correlations calculated by the correlation calculating unit; and an image selecting unit configured to select a first cell image from the plurality of cell images that are captured, based on the first correlation that is selected.

There is provided a radiographic image processing apparatus including: an acquirer that acquires a dynamic image including a plurality of frame images captured by a radiographic imaging apparatus; a hardware processor that determines whether or not there is an abnormality in the dynamic image by using some of the frame images of the acquired dynamic image; and a notifier that notifies of a result of the determination by the hardware processor.

Aspects of the subject disclosure may include, for example, obtaining pre-treatment images; analyzing the pre-treatment images according to an imaging model that includes a machine learning model; predicting, according to the analyzing the pre-treatment images, one or more clinical variables; obtaining on-treatment images; analyzing the on-treatment images according to the imaging model; predicting, based on the analyzing the on-treatment images, the one or more clinical variables for the on-treatment images; and presenting event estimation information in a graphical user interface. Other embodiments are disclosed.

The present disclosure provides a method for treating clinical or pre-clinical skin damage in a skin field of a subject, wherein the skin field has been allocated a skin cancerization field index (SCR) score of at least 1 as determined by a process comprising the steps of: (i) assessing the number of keratoses in the skin field; (ii) assessing the thickness of the thickest keratosis in the skin field; and (iii) assessing the proportion of the field affected by clinical or subclinical skin damage. Based on the assessments made in (i), (ii) and (iii) the subject is optionally treated by at least one of (a) freezing one or more lesions, (b) shaving, curetting or surgically removing one or more lesions, (c) applying a topical treatment for actinic keratosis, basal cell carcinoma or squamous cell carcinoma, and (d) radiation therapy.

Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.