Abstract: Techniques are provided for evaluating and defining the scope of data-driven deep learning models. In one embodiment, a machine-readable storage medium is provided comprising executable instructions that, when executed by a processor, facilitate performance of operations comprising employing a machine learning model to extract first training data features included in a training data set and first target data features included in a target data set. The operations further comprise determining whether the target data set is within a defined data scope of the training data set based on analysis of correspondences between the first training data features and the first target data feature, and determining whether application of the target data set to a target neural network model developed using the training data set will generate results with an acceptable level of accuracy based on whether the target data set is within the defined data scope.

Abstract: Systems and techniques for providing concurrent image and corresponding multi-channel auxiliary data generation for a generative model are presented. In one example, a system generates synthetic multi-channel data associated with a synthetic version of imaging data. The system also predicts multi-channel imaging data and the synthetic multi-channel data with a first predicted class set or a second predicted class set. Furthermore, the system employs the first predicted class set or the second predicted class set for the synthetic multi-channel data to train a generative adversarial network model.

Abstract: Techniques are provided for enhancing the efficiency and accuracy of annotating data samples for supervised machine learning algorithms using an advanced annotation pipeline. According to an embodiment, a method can comprise collecting, by a system comprising a processor, unannotated data samples for input to a machine learning model and storing the unannotated data samples in an annotation queue. The method further comprises determining, by the system, annotation priority levels for respective unannotated data samples of the unannotated data samples, selecting, by the system from amongst different annotation techniques, one or more of the different annotation techniques for annotating the respective unannotated data samples based the annotation priority levels associated with the respective unannotated data samples.

Abstract: A computer-implemented system is provided that includes a learning network component that determines respective weights assigned to respective node inputs of the learning network in accordance with a learning phase of the learning network and trains a variable separator component to differentially change learning rates of the learning network component. A differential rate component applies at least one update learning rate to adjust at least one weight assigned to at least one of the respective node inputs and applies at least one other update learning rate to adjust the respective weight assigned to at least one other of the respective node inputs in accordance with the variable separator component during the learning phase of the learning network.

Abstract: Techniques are described for generating mono-modality training image data from multi-modality image data and using the mono-modality training image data to train and develop mono-modality image inferencing models. A method embodiment comprises generating, by a system comprising a processor, a synthetic 2D image from a 3D image of a first capture modality, wherein the synthetic 2D image corresponds to a 2D version of the 3D image in a second capture modality, and wherein the 3D image and the synthetic 2D image depict a same anatomical region of a same patient. The method further comprises transferring, by the system, ground truth data for the 3D image to the synthetic 2D image. In some embodiments, the method further comprises employing the synthetic 2D image to facilitate transfer of the ground truth data to a native 2D image captured of the same anatomical region of the same patient using the second capture modality.

Abstract: Systems and techniques that facilitate synthetic training data generation for improved machine learning generalizability are provided. In various embodiments, an element augmentation component can generate a set of preliminary annotated training images based on an annotated source image. In various aspects, a preliminary annotated training image can be formed by inserting at least one element of interest or at least one background element into the annotated source image. In various instances, a modality augmentation component can generate a set of intermediate annotated training images based on the set of preliminary annotated training images. In various cases, an intermediate annotated training image can be formed by varying at least one modality-based characteristic of a preliminary annotated training image. In various aspects, a geometry augmentation component can generate a set of deployable annotated training images based on the set of intermediate annotated training images.

Abstract: A computer-implemented system is provided that includes a learning network component that determines respective weights assigned to respective node inputs of the learning network in accordance with a learning phase of the learning network and trains a variable separator component to differentially change learning rates of the learning network component. A differential rate component applies at least one update learning rate to adjust at least one weight assigned to at least one of the respective node inputs and applies at least one other update learning rate to adjust the respective weight assigned to at least one other of the respective node inputs in accordance with the variable separator component during the learning phase of the learning network.

Abstract: Techniques are described for optimizing deep learning model performance using image harmonization as a pre-processing step. According to an embodiment, a method comprises decomposing, by a system operatively coupled to a processor, an input image into sub-images. The method further comprises harmonizing the sub-images with corresponding reference sub-images of at least one reference image based on two or more different statistical values respectively calculated for the sub-images and the corresponding reference-sub images, resulting in transformation of the sub-images into modified sub-images images. In some implementations, the modified sub-images can be combined into a harmonized image having a more similar appearance to the at least one reference image relative to the input image.

Abstract: Techniques are provided for deep neural network (DNN) identification of realistic synthetic images generated using a generative adversarial network (GAN). According to an embodiment, a system is described that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise, a first extraction component that extracts a subset of synthetic images classified as non-real like as opposed to real-like, wherein the subset of synthetic images were generated using a GAN model.

Abstract: Systems and techniques for providing concurrent image and corresponding multi-channel auxiliary data generation for a generative model are presented. In one example, a system generates synthetic multi-channel data associated with a synthetic version of imaging data. The system also predicts multi-channel imaging data and the synthetic multi-channel data with a first predicted class set or a second predicted class set. Furthermore, the system employs the first predicted class set or the second predicted class set for the synthetic multi-channel data to train a generative adversarial network model.

Abstract: Techniques are provided for deep neural network (DNN) identification of realistic synthetic images generated using a generative adversarial network (GAN). According to an embodiment, a system is described that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise, a first extraction component that extracts a subset of synthetic images classified as non-real like as opposed to real-like, wherein the subset of synthetic images were generated using a GAN model. The computer executable components can further comprise a training component that employs the subset of synthetic images and real images to train a DNN network model to classify synthetic images generated using the GAN model as either real-like or non-real like.

Abstract: An x-ray image orientation detection and correction system including a detection and correction computing device is provided. The processor of the computing device is programmed to execute a neural network model that is trained with training x-ray images as inputs and observed x-ray images as outputs. The observed x-ray images are the training x-ray images adjusted to have a reference orientation. The processor is further programmed to receive an unclassified x-ray image, analyze the unclassified x-ray image using the neural network model, and assign an orientation class to the unclassified x-ray image. If the assigned orientation class is not the reference orientation, the processor is programmed to adjust an orientation of the unclassified x-ray image using the neural network model, and output a corrected x-ray image. If the assigned orientation class is the reference orientation, the processor is programmed to output the unclassified x-ray image.

Abstract: Systems and techniques for providing concurrent image and corresponding multi-channel auxiliary data generation for a generative model are presented. In one example, a system generates synthetic multi-channel data associated with a synthetic version of imaging data. The system also predicts multi-channel imaging data and the synthetic multi-channel data with a first predicted class set or a second predicted class set. Furthermore, the system employs the first predicted class set or the second predicted class set for the synthetic multi-channel data to train a generative adversarial network model.

Abstract: Techniques are described for performing active surveillance and learning for machine learning (ML) model authoring and deployment workflows. In an embodiment, a method comprises applying, by a system comprising a processor, a primary ML model trained on a training dataset to data samples excluded from the training dataset to generate inferences based on the data samples. The method further comprises employing, by the system, one or more active surveillance techniques to regulate performance of the primary ML model in association with the applying, wherein the one or more active surveillance techniques comprise at least one of, performing a model scope evaluation of the primary ML model relative to the data samples or using a domain adapted version of the primary ML model to generate the inferences.

Abstract: Techniques are provided for enhancing the efficiency and accuracy of annotating data samples for supervised machine learning algorithms using an advanced annotation pipeline. According to an embodiment, a method can comprise collecting, by a system comprising a processor, unannotated data samples for input to a machine learning model and storing the unannotated data samples in an annotation queue. The method further comprises determining, by the system, annotation priority levels for respective unannotated data samples of the unannotated data samples, selecting, by the system from amongst different annotation techniques, one or more of the different annotation techniques for annotating the respective unannotated data samples based the annotation priority levels associated with the respective unannotated data samples.

Abstract: Techniques are provided for enhancing the efficiency and accuracy of annotating data samples for supervised machine learning algorithms using an advanced annotation pipeline. According to an embodiment, a method can comprise collecting, by a system comprising a processor, unannotated data samples for input to a machine learning model and storing the unannotated data samples in an annotation queue. The method further comprises determining, by the system, annotation priority levels for respective unannotated data samples of the unannotated data samples, selecting, by the system from amongst different annotation techniques, one or more of the different annotation techniques for annotating the respective unannotated data samples based the annotation priority levels associated with the respective unannotated data samples.

Abstract: Techniques are provided for determining confident data samples for machine learning (ML) models on unseen data. In one embodiment, a method is provided that comprises extracting, by a system comprising a processor, a feature vector for a data sample based on projection of the data sample onto a standard feature space. The method further comprises processing, by the system, the feature vector using an outlier detection model to determine whether the data sample is within a scope of a training dataset used to train a machine learning model, wherein the outlier detection model was trained using features extracted from the training dataset based on projection of data samples included in the training dataset onto the standard feature space.

Abstract: Systems, apparatus, instructions, and methods for medical machine time-series event data processing are disclosed. An example apparatus includes a data processor to process one-dimensional data captured over time with respect to patient(s). The example apparatus includes a visualization processor to transform the processed data into graphical representations and to cluster the graphical representations including the first graphical representation into at least first and second blocks arranged with respect to an indicator of a criterion to provide a visual comparison of the first block and the second block with respect to the criterion. The example apparatus includes an interaction processor to facilitate interaction, via the graphical user interface, with the first and second blocks of graphical representations to extract a data set for processing from at least a subset of the first and second blocks.

Abstract: Systems, apparatus, instructions, and methods for medical machine time-series event data generation are disclosed. An example synthetic time series data generation apparatus is to generate a synthetic data set including multi-channel time-series data and associated annotation using a first artificial intelligence network model. The example apparatus is to analyze the synthetic data set with respect to a real data set using a second artificial intelligence network model. When the second artificial intelligence network model classifies the synthetic data set as a first classification, the example apparatus is to adjust the first artificial intelligence network model using feedback from the second artificial intelligence network model. When the second artificial intelligence network model classifies the synthetic data set as a second classification, the example apparatus is to output the synthetic data set.

Abstract: An artificial intelligence platform and associated methods of training and use are disclosed. An example apparatus includes a data pipeline to: preprocess data using one or more preprocessing operations applied to features associated with the data; and enable debugging to visualize the preprocessed data. The example apparatus includes a network to: instantiate one or more differentiable operations in a training configuration to train an artificial intelligence model; capture feedback including optimization and loss information to adjust the training configuration; and store one or more metrics to evaluate performance of the artificial intelligence model.