Abstract: A method for generating an image of a subject with a magnetic resonance imaging (MRI) system is presented. The method includes first performing a localizer scan of the subject to acquire localizer scan data. A machine learning (ML) module is then used to detect the presence of metal regions in the localizer scan data based on magnitude and phase information of the localizer scan data. Based on the detected metal regions in the localizer scan data, the MRI workflow is adjusted for diagnostic scan of the subject. The image of the subject is then generated using the adjusted workflow.

Abstract: Systems and methods are provided for an image processing system. In an example, a method includes acquiring a pathology dataset, acquiring a reference dataset, generating a deformation field by mapping points of a reference case of the reference dataset to points of a patient image of the pathology dataset, manipulating the deformation field, applying the deformation field to the reference case to generate a simulated pathology image including a simulated deformation pathology, and outputting the simulated pathology image.

Abstract: Systems/techniques that facilitate improved uncertainty scoring for neural networks via stochastic weight perturbations are provided. In various embodiments, a system can access a trained neural network and/or a data candidate on which the trained neural network is to be executed. In various aspects, the system can generate an uncertainty indicator representing how confidently executable or how unconfidently executable the trained neural network is with respect to the data candidate, based on a set of perturbed instantiations of the trained neural network.

Abstract: Various methods and systems are provided for bicuspid valve detection with ultrasound imaging. In one embodiment, a method comprises acquiring ultrasound video of a heart over at least one cardiac cycle, identifying frames in the ultrasound video corresponding to at least one cardiac phase, and classifying a cardiac structure in the identified frames as a bicuspid valve or a tricuspid valve. A generative model such as a variational autoencoder trained on ultrasound image frames at the at least one cardiac phase may be used to classify the cardiac structure. In this way, relatively rare occurrences of bicuspid aortic valves may be automatically detected during regular cardiac ultrasound screenings.

Abstract: Techniques are described for generating high quality training data collections for training artificial intelligence (AI) models in the medical imaging domain. A method embodiment comprises receiving, by a system comprising processor, input indicating a clinical context associated with usage of a medical image dataset, and selecting, by the system, one or more data scrutiny metrics for filtering the medical image dataset based on the clinical context. The method further comprises applying, by the system, one or more image processing functions to the medical image dataset to generate metric values of the one or more data scrutiny metrics for respective medical images included in the medical image dataset, filtering, by the system, the medical image dataset into one or more subsets based on one or more acceptability criteria for the metric values.

Abstract: Systems/techniques that facilitate deep learning multi-planar reformatting of medical images are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can localize, via execution of a machine learning model, a set of landmarks depicted in the three-dimensional medical image, a set of principal anatomical planes depicted in the three-dimensional medical image, and a set of organs depicted in the three-dimensional medical image. In various instances, the system can determine an anatomical orientation exhibited by the three-dimensional medical image, based on the set of landmarks, the set of principal anatomical planes, or the set of organs. In various cases, the system can rotate the three-dimensional medical image, such that the anatomical orientation now matches a predetermined anatomical orientation.

Abstract: Techniques are described for learning feature representations of medical images using a self-supervised learning paradigm and employing those feature representations for automating downstream tasks such as image retrieval, image classification and other medical image processing tasks. According to an embodiment, computer-implemented method comprises generating alternate view images for respective medical images included in set of training images using one or more image augmentation techniques or one or more image selection techniques tailored based on domain knowledge associated with the respective medical images. The method further comprises training a transformer network to learn reference feature representations for the respective medical images using their alternate view images and a self-supervised training process.

Abstract: Systems and methods for self-supervised representation learning as a means to generate context-specific pretrained models include selecting data from a set of available data sets; selecting a pretext task from domain specific pretext tasks; selecting a target problem specific network architecture based on a user selection from available choices or any customized model as per user preference; and generating a pretrained model for the selected network architecture using the selected data obtained from the set of available data sets and a pretext task as obtained from domain specific pretext tasks.

Abstract: A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

Abstract: Systems and techniques that facilitate data diversity visualization and/or quantification for machine learning models are provided. In various embodiments, a processor can access a first dataset and a second dataset, where a machine learning (ML) model is trained on the first dataset. In various instances, the processor can obtain a first set of latent activations generated by the ML model based on the first dataset, and a second set of latent activations generated by the ML model based on the second dataset. In various aspects, the processor can generate a first set of compressed data points based on the first set of latent activations, and a second set of compressed data points based on the second set of latent activations, via dimensionality reduction. In various instances, a diversity component can compute a diversity score based on the first set of compressed data points and second set of compressed data points.

Abstract: Systems and methods for workflow management for labeling the subject anatomy are provided. The method comprises obtaining at least one localizer image of a subject anatomy using a low-resolution medical imaging device. The method further comprises labeling at least one anatomical point within the at least one localizer image. The method further comprises extracting using a machine learning module a mask of the at least one localizer image comprising the at least one anatomical point label. The method further comprises using the mask to label at least one anatomical point on a high-resolution image of the subject anatomy based on the at least one anatomical point within the localizer image.

Abstract: Various methods and systems are provided for bicuspid valve detection with ultrasound imaging. In one embodiment, a method comprises acquiring ultrasound video of a heart over at least one cardiac cycle, identifying frames in the ultrasound video corresponding to at least one cardiac phase, and classifying a cardiac structure in the identified frames as a bicuspid valve or a tricuspid valve. A generative model such as a variational autoencoder trained on ultrasound image frames at the at least one cardiac phase may be used to classify the cardiac structure. In this way, relatively rare occurrences of bicuspid aortic valves may be automatically detected during regular cardiac ultrasound screenings.

Abstract: Systems and method for domain adaptation using pseudo-labelling and model certainty quantification for video data are provided. The method includes obtaining a source data and a target data each comprising a plurality of frames for processing by a machine learning module. The method comprises testing the target data to identify if a minimum number of frames exhibit a frame confidence score based on the source data and identifying salient region within the target data and measuring a degree of spatial consistency of the salient region over time.

Abstract: A medical imaging system includes at least one medical imaging device providing image data of a subject and a processing system programmed to generate a plurality of training images having simulated medical conditions by blending a pathology region from a plurality of template source images to a plurality of target images. The processing system is further programmed to train a deep learning network model using the plurality of training images and input the image data of the subject to the deep learning network model. The processing system is further programmed to generate a medical image of the subject based on the output of the deep learning network model.