Abstract: Systems and methods are disclosed for training and deployment of machine learning-based models that dynamically translate natural language to database query language, and include automation of training data generation, query representation language, and adaptive model training. A method for generating datasets for a natural language interface to a database includes a database query builder, which receives insights regarding the database, and based at least in part on the database insights builds a plurality of database queries. The method further includes generating a data distribution of natural language queries paired with corresponding database queries by, for each one of the plurality of database queries, pairing the database query to a natural language query and one or more paraphrases of the natural language query, and projecting the data distribution onto a plurality of segmented text distributions and applying one or more control signals to generate an optimal training data distribution.

Abstract: A method to determine myocardial wall dynamics and tissue characteristics using a method provided to determine myocardial wall dynamics and tissue characteristics using a 3D model of the myocardium. The method comprises generating an epicardial surface and an endocardial surface from a plurality of SAX and LAX slices; identifying a plurality of nodes on the epicardial and endocardial surfaces or in between these surfaces within the myocardium in a reference frame; defining a set of coefficients, each coefficient being associated with the respective location of the corresponding node in a phase; determining the coefficients and in this way determining the model; determining the myocardial wall dynamics in terms of strain values and displacements.

Abstract: A method of delineating a region of interest in a medical image and a system for carrying out the method. An initial point, corresponding to a pixel having an initial pixel intensity is selected on a desired region of interest in an image. A preliminary region of interest is delineated that includes the initial pixel and all connected pixels having a signal intensity in an initial range is delineated and displayed on the image. The initial range of signal intensities is adjusted based on user feedback. An adjusted region of interest is displayed. Also disclosed is a method of quantitatively analyzing a desired parameter in a region of interest of a medical image in real time and a system for carrying out this method.