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: Systems/techniques that facilitate deep learning image analysis with increased modularity and reduced footprint are provided. In various embodiments, a system can access medical imaging data. In various aspects, the system can perform, via execution of a deep learning neural network, a plurality of inferencing tasks on the medical imaging data. In various instances, the deep learning neural network can comprise a common backbone in parallel with a plurality of task-specific backbones. In various cases, the plurality of task-specific backbones can respectively correspond to the plurality of inferencing tasks.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: Certain examples provide an image data processing system including an anatomy detector to detect an anatomy in an image and to remove items not included in the anatomy from the image. The example system includes a bounding box generator to generate a bounding box around a region of interest in the anatomy. The example system includes a voxel-level segmenter to classify image data within the bounding box at the voxel level to identify an object in the region of interest. The example system includes an output imager to output an indication of the object identified in the region of interest segmented in the 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: Systems/techniques that facilitate multi-layer image registration are provided. In various embodiments, a system can access a first image and a second image. In various aspects, the system can generate, via execution of a machine learning model on the first image and the second image, a plurality of registration fields and a plurality of weight matrices that respectively correspond to the plurality of registration fields. In various instances, the system can register the first image with the second image based on the plurality of registration fields and the plurality of weight matrices.

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 freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run.

Abstract: An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line, and displaying the combined image on the display.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line, and displaying the combined image on the display.

Abstract: An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line, and displaying the combined image on the display.

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: Methods and systems are provided for tuning a static model with multiple operating points to adjust model performance without retraining the model or triggering a new regulatory clearance. In one embodiment, a method comprises, responsive to a request to tune a model, obtaining a tuning dataset including a set of medical images, executing the model using the set of medical images as input to generate model tuning output, and determining, for each operating point of a set of operating points, a set of tuning metric values based on the tuning dataset and the model tuning output relative to each operating point. An operating point from the set of operating points may be selected based on each set of tuning metric values and, upon a request to analyze a subsequent medical image, a representation of a finding output from the static model executed at the selected operating point.

Abstract: Systems and techniques that facilitate freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run.

Abstract: Certain examples provide an image data processing system including an anatomy detector to detect an anatomy in an image and to remove items not included in the anatomy from the image. The example system includes a bounding box generator to generate a bounding box around a region of interest in the anatomy. The example system includes a voxel-level segmenter to classify image data within the bounding box at the voxel level to identify an object in the region of interest. The example system includes an output imager to output an indication of the object identified in the region of interest segmented in the image.

Abstract: Certain examples provide an image data processing system including an anatomy detector to detect an anatomy in an image and to remove items not included in the anatomy from the image. The example system includes a bounding box generator to generate a bounding box around a region of interest in the anatomy. The example system includes a voxel-level segmenter to classify image data within the bounding box at the voxel level to identify an object in the region of interest. The example system includes an output imager to output an indication of the object identified in the region of interest segmented in the image.

Abstract: Certain examples provide an image data processing system including an anatomy detector to detect an anatomy in an image and to remove items not included in the anatomy from the image. The example system includes a bounding box generator to generate a bounding box around a region of interest in the anatomy. The example system includes a voxel-level segmenter to classify image data within the bounding box at the voxel level to identify an object in the region of interest. The example system includes an output imager to output an indication of the object identified in the region of interest segmented in the image.

Abstract: A method, as well as a system and a computer readable medium based on the method, for reducing perceived noise. The method comprises the steps of determining an area of interest in the image, the area of interest being determined in dependence of a foveal vision of a user, and applying a stronger noise filtering in a peripheral area of the image than in the area of interest, the peripheral area being outside the area of interest and corresponding to a peripheral vision of the user.