Abstract: A system for analyzing medical images to detect and classify a medical condition, the system includes an input for receiving a medical image, a convolutional neural network coupled to the input and configured to analyze the medical image to generate a prediction including a probability of the presence of the medical condition in the medical image and an atlas creation module coupled to the convolutional neural network and configured to generate an atlas comprising a set of image features and a set of training images. Each image feature is assigned with at least one training image associated with the medical condition. The system further includes a prediction basis selection module coupled to the convolutional neural network and the atlas and configured to create a prediction basis for the prediction generated by the convolutional neural network.

Abstract: An ischemic stroke mimic is detected, or otherwise predicted, based on medical images acquired from a subject. Medical image data, which include medical images acquired from a head of the subject, are accessed with a computer system. A machine learning model (e.g., one or more deep convolutional neural networks) is trained on training data to estimate a probability of an acute intracranial abnormality being depicted in a medical image. Intracranial abnormality prediction data are generated by inputting the medical image data to the machine learning model. The intracranial abnormality prediction data include an intracranial abnormality probability score for each of the medical images in the medical image data. An ischemic stroke mimic classification for the medical image data is generated based on the intracranial abnormality prediction data, and may be displayed to a user with the computer system.

Abstract: Supervised and unsupervised learning schemes may be used to automatically label medical images for use in deep learning applications. Large labeled datasets may be generated from a small initial training set using an iterative snowball sampling scheme. A machine learning powered automatic organ classifier for imaging datasets, such as CT datasets, with a deep convolutional neural network (CNN) followed by an organ dose calculation is also provided. This technique can be used for patient-specific organ dose estimation since the locations and sizes of organs for each patient can be calculated independently.

Abstract: Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

Abstract: A system and method for determining patient risk stratification is provided based on body composition derived from computed tomography images using segmentation with machine learning. The system may enable real-time segmentation for facilitating clinical application of body morphological analysis sets. A fully-automated deep learning system may be used for the segmentation of skeletal muscle cross sectional area (CSA). Whole-body volumetric analysis may also be performed. The fully-automated deep segmentation model may be derived from an extended implementation of a Fully Convolutional Network with weight initialization of a pre-trained model, followed by post processing to eliminate intramuscular fat for a more accurate analysis.

Abstract: A system for analyzing medical images to detect and classify a medical condition, the system includes an input for receiving a medical image, a convolutional neural network coupled to the input and configured to analyze the medical image to generate a prediction including a probability of the presence of the medical condition in the medical image and an atlas creation module coupled to the convolutional neural network and configured to generate an atlas comprising a set of image features and a set of training images. Each image feature is assigned with at least one training image associated with the medical condition. The system further includes a prediction basis selection module coupled to the convolutional neural network and the atlas and configured to create a prediction basis for the prediction generated by the convolutional neural network.

Abstract: In accordance with some embodiments, systems, methods and media for generating a bone age assessment. In some embodiments, a method comprises: receiving an x-ray image of a subject's left hand and wrist; converting the image to a predetermined size; identifying, without user intervention, a first portion of the image corresponding to the hand and wrist; processing the first portion of the image to increase contrast between bones and non-bones to generate a processed image; causing a trained convolution neural network to determine a bone age based on the processed image; receiving an indication of the bone age; causing the bone age to be presented to a user as the result of a bone age assessment; and causing the bone age and the image to be stored in an electronic medical record associated with the subject.

Abstract: Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

Abstract: Described her are systems and methods for reconstructing images from x-ray attenuation data (e.g., sinogram data) in which metal artifacts are reduced. The algorithms described in the present disclosure take advantage of accurate forward system modeling and one or more iterative reconstruction techniques (IRTs) (e.g., those using compressed sensing) to reconstruct images from incomplete data sets. Rather than replace measurements that are identified as corrupted with inaccurate ones, the systems and methods described in the present disclosure exclude those corrupted measurements in the fidelity term of the energy functional. As a result, the corrupted measurements are not included in the image formation process. In doing so, the reconstruction problem is changed from being about inaccurate data correction to sparse data image reconstruction.

Abstract: Supervised and unsupervised learning schemes may be used to automatically label medical images for use in deep learning applications. Large labeled datasets may be generated from a small initial training set using an iterative snowball sampling scheme. A machine learning powered automatic organ classifier for imaging datasets, such as CT datasets, with a deep convolutional neural network (CNN) followed by an organ dose calculation is also provided. This technique can be used for patient-specific organ dose estimation since the locations and sizes of organs for each patient can be calculated independently.

Abstract: Supervised and unsupervised learning schemes may be used to automatically label medical images for use in deep learning applications. Large labeled datasets may be generated from a small initial training set using an iterative snowball sampling scheme. A machine learning powered automatic organ classifier for imaging datasets, such as CT datasets, with a deep convolutional neural network (CNN) followed by an organ dose calculation is also provided. This technique can be used for patient-specific organ dose estimation since the locations and sizes of organs for each patient can be calculated independently.

Abstract: Systems and methods for translating medical imaging data for processing using a general processing graphic processing unit (GPGPU) architecture are provided. Medical imaging data acquired from a patient and having data characteristics incompatible with processing on the GPGPU architecture, including at least one of bit-resolution, memory capacity requirements for processing, or bandwidth requirements for processing is translated for processing by the GPGPU architecture. The translation process is performed by determining a plurality of window level settings using a machine learning network to increase conspicuity of an object in an image generated from the medical imaging data or generate at least two channel image datasets from the medical imaging data. Translated medical image data is crated using at least one of the window level settings or at least two channel image datasets and then processed using the GPGPU architecture to generate medical images of the patient.

Abstract: A system and method for determining patient risk stratification is provided based on body composition derived from computed tomography images using segmentation with machine learning. The system may enable real-time segmentation for facilitating clinical application of body morphological analysis sets. A fully-automated deep learning system may be used for the segmentation of skeletal muscle cross sectional area (CSA). Whole-body volumetric analysis may also be performed. The fully-automated deep segmentation model may be derived from an extended implementation of a Fully Convolutional Network with weight initialization of a pre-trained model, followed by post processing to eliminate intra-muscular fat for a more accurate analysis.

Abstract: A method and systems for analyzing medical imaging using machine learning are provided. In some aspects, the method includes using an input on the computing device to receive image data acquired from a subject, wherein the image data is in a raw data domain, applying, using the computing device, a trained machine learning algorithm to the image data, wherein the trained machine learning algorithm is configured to perform a predetermined analysis on the image data. The method also includes generating a report indicative of the predetermined analysis using the computing device.

Abstract: In accordance with some embodiments, systems, methods and media for generating a bone age assessment. In some embodiments, a method comprises: receiving an x-ray image of a subject's left hand and wrist; converting the image to a predetermined size; identifying, without user intervention, a first portion of the image corresponding to the hand and wrist; processing the first portion of the image to increase contrast between bones and non-bones to generate a processed image; causing a trained convolution neural network to determine a bone age based on the processed image; receiving an indication of the bone age; causing the bone age to be presented to a user as the result of a bone age assessment; and causing the bone age and the image to be stored in an electronic medical record associated with the subject.

Abstract: A system may identify the location of objects of interest in a captured image by processing image data associated with the captured image using neural networks. The image data may be generated by an image sensor, which may be part of an imaging system. A cascade segmentation artificial intelligence that includes multiple neural networks may be used to process the image data in order to determine the locations objects of interest in the captured image. Post-processing may be performed on outputs of the cascade segmentation artificial intelligence to generate a mask corresponding to the locations of the objects of interest. The mask may be superimposed over the captured image to produce an output image, which may then be presented on a display.

Abstract: A system and method for producing an image of a subject with a tomographic imaging system are provided. A tomographic imaging system is operated to rotate a radiation detector, radiation source, or both through a plurality of angular positions around a subject while acquiring data. As the radiation detector or source is rotated, the radiation detector or source is shifted at each angular position by a different shift value. An image of the subject is reconstructed from the acquired data using a reconstruction technique that incorporates the shifts applied to the detector, source, or both into a system matrix.

Abstract: A system and method for producing an image of a subject with a tomographic imaging system are provided. A tomographic imaging system is operated to rotate a radiation detector, radiation source, or both through a plurality of angular positions around a subject while acquiring data. As the radiation detector or source is rotated, the radiation detector or source is shifted at each angular position by a different shift value. An image of the subject is reconstructed from the acquired data using a reconstruction technique that incorporates the shifts applied to the detector, source, or both into a system matrix.

Abstract: Technologies are generally described for employing ultra-short pulsed X-rays in X-ray computer tomography. Timing parameters of binary modulation applied to the X-rays at the source may be adjusted based on detector characteristics, industry standards, and/or user input. The timing for minimum X-ray intensity during each pulse may be selected to minimize afterglow effect. The timing for the maximum X-ray intensity may then be determined based on one or more of the minimum X-ray intensity timing, desired X-ray dosage, and/or other similar parameters.

Abstract: Technologies are generally described for employing ultra-short pulsed X-rays in X-ray computer tomography. Timing parameters of binary modulation applied to the X-rays at the source may be adjusted based on detector characteristics, industry standards, and/or user input. The timing for minimum X-ray intensity during each pulse may be selected to minimize afterglow effect. The timing for the maximum X-ray intensity may then be determined based on one or more of the minimum X-ray intensity timing, desired X-ray dosage, and/or other similar parameters.