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: Systems/techniques that facilitate AI-based region-of-interest masks for improved data reconstructions are provided. In various embodiments, a system can access a set of two-dimensional medical scan projections. In various aspects, the system can generate a set of two-dimensional region-of-interest masks respectively corresponding to the set of two-dimensional medical scan projections. In various instances, the system can generate a region-of-interest visualization based on the set of two-dimensional region-of-interest masks and the set of two-dimensional medical scan projections. In various cases, the system can generate the set of two-dimensional region-of-interest masks by executing a machine learning segmentation model on the set of two-dimensional medical scan projections.

Abstract: A dual energy x-ray imaging system and method of operation includes an artificial intelligence-based motion correction system to minimize the effects of motion artifacts in images produced by the imaging system. The motion correction system is trained to apply simulated motion to various objects of interest within the LE and HE projections in the training dataset to improve registration of the LE and HE projections. The motion correction system is also trained to enhance the correction of small motion artifacts using noise attenuation and subtraction image-based edge detection on the training dataset images reduce noise from the LE projection, consequently improving small motion artifact correction. The motion correction system additionally employs separate motion corrections for soft and bone tissue in forming subtraction soft tissue and bone tissue images, and includes a motion alarm to indicate when motion between LE and HE projections requires a retake of the projections.

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: Various methods and systems are provided for denoising images. In one example, a method includes obtaining an input image and a noise map representing noise in the input image, generating, from the noise map and based on a calibration factor, a strength map, entering the input image and the strength map as input to a denoising model trained to output a denoised image based on the input image and the strength map, and displaying and/or saving the denoised image output by the denoising model.

Abstract: Systems/techniques that facilitate improved neural network inferencing efficiency with fewer parameters are provided. In various embodiments, a system can access a medical image on which an artificial intelligence task is to be performed. In various aspects, the system can facilitate the artificial intelligence task by executing a neural network pipeline on the medical image, thereby yielding an artificial intelligence task output that corresponds to the medical image. In various instances, the neural network pipeline can include respective skip connections from the medical image, prior to any convolutions, to each convolutional layer in the neural network pipeline.

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: A tomosynthesis machine allows for faster image acquisition and improved signal-to-noise by acquiring a projection attenuation data and using machine learning to identify a subset of the projection attenuation data for the production of thinner slices and/or higher resolution slices using machine learning.

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: 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: 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: 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: 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: An artificial intelligence (AI) measurement system for an X-ray image is employed either as a component of the X-ray imaging system or separately from the X-ray imaging system to automatically scan post-exposure X-ray images to detect and locate various landmarks of the anatomy presented within the X-ray image. A set of key image features approximating the locations of the landmarks having known distance relationships to one another is overlaid onto the X-ray image. The positions of the key image features are then adjusted to correspond to the landmarks within the X-ray image. These adjustments are made relative to the prior known distance relationships between the key features, which enables the measurement system to readily calculate desired angular and length measurements between landmarks as a result.

Abstract: Various methods and systems are provided for automatically registering and stitching images. In one example, a method includes entering a first image of a subject and a second image of the subject to a model trained to output a transformation matrix based on the first image and the second image, where the model is trained with a plurality of training data sets, each training data set including a pair of images, a mask indicating a region of interest (ROI), and associated ground truth, automatically stitching together the first image and the second image based on the transformation matrix to form a stitched image, and outputting the stitched image for display on a display device and/or storing the stitched image in memory.

Abstract: An artificial intelligence (AI) X-ray image information detection and correction system is employed either as a component of the X-ray imaging system or separately from the X-ray imaging system to automatically scan post-exposure X-ray images to detect various types of information or characteristics of the X-ray image, including, but not limited to, anatomy, view, orientation and laterality of the X-ray image, along with an anatomical landmark segmentation. The information detected about the X-ray image can then be stored by the AI system in association with the X-ray image for use in various downstream X-ray system workflow automations and/or reviews of the X-ray image.

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/techniques that facilitate AI-based region-of-interest masks for improved data reconstructions are provided. In various embodiments, a system can access a set of two-dimensional medical scan projections. In various aspects, the system can generate a set of two-dimensional region-of-interest masks respectively corresponding to the set of two-dimensional medical scan projections. In various instances, the system can generate a region-of-interest visualization based on the set of two-dimensional region-of-interest masks and the set of two-dimensional medical scan projections. In various cases, the system can generate the set of two-dimensional region-of-interest masks by executing a machine learning segmentation model on the set of two-dimensional medical scan projections.

Abstract: Systems/techniques that facilitate learning-based clean data selection are provided. In various embodiments, a system can access a raw dataset. In various aspects, the system can select, via execution of a data selection machine learning model, a clean dataset from the raw dataset. In various instances, the system can train a target machine learning model to perform a target task based on the clean dataset. In various aspects, the clean dataset can include candidate-annotation groupings that are in the raw dataset and that are determined by the data selection machine learning model to be suitable for training of the target machine learning model, and the clean dataset can exclude candidate-annotation groupings that are in the raw dataset and that are determined by the data selection machine learning model to not be suitable for training of the target machine learning model.