Abstract: A method of training a text model using a plurality of text passage combinations, each text passage combination comprising a respective first text passage and a respective second text passage describing a same matter as the respective first text passage but being differently worded than the respective first text passage. The training comprises minimizing a measure of statistical difference between a respective value of a first text embedding and the corresponding value of a second text embedding over the plurality of text passage combinations. The method then comprises jointly training the text model and an image model based on plurality of image-text combinations, each comprising a respective image and a respective textual report describing the respective image. The joint training comprises minimizing a measure of statistical difference between the value of an image embedding and the corresponding value of a third text embedding over the plurality of image-text combinations.

Abstract: A computer-implemented method comprising: receiving a 3D image including an object depicted in the image, the 3D image comprising an ordered set of 2D images; determining a contour around the object in a first of said 2D images; and determining a contour around the object in a second of said 2D images, the second 2D image being non-contiguous with the first in said ordered set, having an intermediate region comprising one or more intermediate ones of said 2D images between the first and second 2D images within said ordered set. In each of the first and second 2D images, inside of the contour is classified as foreground and outside of the contour is classified as background. The method further comprises performing a 3D geodesic distance computation to classify points in the intermediate region as foreground of background.

Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.

Abstract: Example solutions for zero-shot domain transfer with a text-to-text model train a text-to-text model for a target domain using unlabeled in-domain text training data, and concurrently train the model using labeled general-domain task training data. The in-domain training comprises masked language modeling (MLM) training, and the task training comprises both natural language generation (NLG) training and natural language understanding (NLU) training. The NLG training comprises natural language inference (NLI) training and the NLU training comprises summarization training. The trained model acquires domain-specific task competency, sufficient to perform a language task within the target domain. Suitable target domains include radiology, biomedical, and other medical, legal, and scientific domains.

Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.

Abstract: A computer-implemented method comprising: receiving a 3D image including an object depicted in the image, the 3D image comprising an ordered set of 2D images; determining a contour around the object in a first of said 2D images; and determining a contour around the object in a second of said 2D images, the second 2D image being non-contiguous with the first in said ordered set, having an intermediate region comprising one or more intermediate ones of said 2D images between the first and second 2D images within said ordered set. In each of the first and second 2D images, inside of the contour is classified as foreground and outside of the contour is classified as background. The method further comprises performing a 3D geodesic distance computation to classify points in the intermediate region as foreground of background.