Abstract: A method for image segmentation includes receiving an input image. The method further includes obtaining a deep learning model having a triad of predictors. Furthermore, the method includes processing the input image by a shape model in the triad of predictors to generate a segmented shape image. Moreover, the method includes presenting the segmented shape image via a display unit.

Abstract: Techniques are provided for generating enhanced image representations from original X-ray images using deep learning techniques. In one embodiment, a system is provided that includes a memory storing computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a reception component, an analysis component, and an artificial intelligence component. The analysis component analyzes the original X-ray image using an AI-based model with respect to a set of features of interest. The AI component generates a plurality of enhanced image representations. Each enhanced image representation highlights a subset of the features of interest and suppresses remaining features of interest in the set that are external to the subset.

Abstract: The present approach relates to a system capable of life-long learning in a deep learning context. The system includes a deep learning network configured to process an input dataset and perform one or more tasks from among a first set of tasks. As an example, the deep learning network may be part of an imaging system, such as a medical imaging system, or may be used in industrial applications. The system further includes a learning unit communicatively coupled to the deep learning network 102 and configured to modify the deep learning network so as to enable it to perform one or more tasks in a second task list without losing the ability to perform the tasks from the first list.

Abstract: Techniques are provided for generating enhanced image representations from original X-ray images using deep learning techniques. In one embodiment, a system is provided that includes a memory storing computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a reception component, an analysis component, and an artificial intelligence component. The analysis component analyzes the original X-ray image using an AI-based model with respect to a set of features of interest. The AI component generates a plurality of enhanced image representations. Each enhanced image representation highlights a subset of the features of interest and suppresses remaining features of interest in the set that are external to the subset.

Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.

Abstract: A method for image segmentation includes receiving an input image. The method further includes obtaining a deep learning model having a triad of predictors. Furthermore, the method includes processing the input image by a shape model in the triad of predictors to generate a segmented shape image. Moreover, the method includes presenting the segmented shape image via a display unit.

Abstract: A method for determining optimized deep learning architecture includes receiving a plurality of training images and a plurality of real time images corresponding to a subject. The method further includes receiving, by a medical practitioner, a plurality of learning parameters comprising a plurality of filter classes and a plurality of architecture parameters. The method also includes determining a deep learning model based on the plurality of learning parameters and the plurality of training images, wherein the deep learning model comprises a plurality of reusable filters. The method further includes determining a health condition of the subject based on the plurality of real time images and the deep learning model. The method also includes providing the health condition of the subject to the medical practitioner.

Abstract: A method for image segmentation includes receiving an input image (102). The method further includes obtaining a deep learning model (104) having a triad of predictors (116, 118, 120). Furthermore, the method includes processing the input image by a shape model in the triad of predictors (116, 118, 120) to generate a segmented shape image (110). Moreover, the method includes presenting the segmented shape image via a display unit (128).

Abstract: A system and method for generating a patient-specific organ model is provided. The method may include receiving ultrasound images of an organ and probe position data corresponding with each of the ultrasound images. The method may include receiving identification of landmarks in the ultrasound images corresponding with pre-defined landmarks of a generic geometric organ model. The method may include automatically identifying surface points of the organ in the ultrasound images. The method may include generating a patient-specific ultrasound point cloud of the organ based on the received identification of the landmarks, the automatically identified surface points of the organ, and the probe position data. The method may include registering a point cloud of the generic geometric model to the patient-specific ultrasound point cloud to create a patient-specific organ model. The method may include presenting the patient-specific organ model at a display system.

Abstract: The present approach relates to a system capable of life-long learning in a deep learning context. The system includes a deep learning network configured to process an input dataset and perform one or more tasks from among a first set of tasks. As an example, the deep learning network may be part of an imaging system, such as a medical imaging system, or may be used in industrial applications. The system further includes a learning unit communicatively coupled to the deep learning network 102 and configured to modify the deep learning network so as to enable it to perform one or more tasks in a second task list without losing the ability to perform the tasks from the first list.

Abstract: A method for ultrasound imaging is presented. The method includes acquiring at least one image of a subject, determining a current position of an ultrasound probe on a body surface of the subject based on the image, identifying anatomical regions of interest in the image, quantifying the image to determine suitability of the image to one or more scan planes corresponding to a clinical protocol, generating a personalized anatomical model of the subject based on a current position of the ultrasound probe, the identified anatomical regions of interest, and the quantification of the image, computing a desired trajectory of the ultrasound probe from the current location to a target location based on the clinical protocol, communicating a desired movement of the ultrasound probe based on the computed trajectory, moving the ultrasound probe along the computed trajectory based on the communicated desired movement to acquire images of the subject.

Abstract: A method for image segmentation includes receiving an input image (102). The method further includes obtaining a deep learning model (104) having a triad of predictors (116, 118, 120). Furthermore, the method includes processing the input image by a shape model in the triad of predictors (116, 118, 120) to generate a segmented shape image (110). Moreover, the method includes presenting the segmented shape image via a display unit (128).

Abstract: A method for determining optimized deep learning architecture includes receiving a plurality of training images and a plurality of real time images corresponding to a subject. The method further includes receiving, by a medical practitioner, a plurality of learning parameters comprising a plurality of filter classes and a plurality of architecture parameters. The method also includes determining a deep learning model based on the plurality of learning parameters and the plurality of training images, wherein the deep learning model comprises a plurality of reusable filters. The method further includes determining a health condition of the subject based on the plurality of real time images and the deep learning model. The method also includes providing the health condition of the subject to the medical practitioner.

Abstract: A system and method for generating a patient-specific organ model is provided. The method may include receiving ultrasound images of an organ and probe position data corresponding with each of the ultrasound images. The method may include receiving identification of landmarks in the ultrasound images corresponding with pre-defined landmarks of a generic geometric organ model. The method may include automatically identifying surface points of the organ in the ultrasound images. The method may include generating a patient-specific ultrasound point cloud of the organ based on the received identification of the landmarks, the automatically identified surface points of the organ, and the probe position data. The method may include registering a point cloud of the generic geometric model to the patient-specific ultrasound point cloud to create a patient-specific organ model. The method may include presenting the patient-specific organ model at a display system.

Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.