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: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object.

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: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object.

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, a system and a computer readable medium for automatic segmentation of a 3D medical image, the 3D medical image comprising an object to be segmented, the method characterized by comprising: carrying out, by using a machine learning model, in at least two of a first, a second and a third orthogonal orientation, 2D segmentations for the object in slices of the 3D medical image to derive 2D segmentation data; determining a location of a bounding box (10) within the 3D medical image based on the 2D segmentation data, the bounding box (10) having predetermined dimensions; and carrying out a 3D segmentation for the object in the part of the 3D medical image corresponding to the bounding box (10).

Abstract: A method, a system and a computer readable medium for automatic segmentation of a 3D medical image, the 3D medical image comprising an object to be segmented, the method characterized by comprising: carrying out, by using a machine learning model, in at least two of a first, a second and a third orthogonal orientation, 2D segmentations for the object in slices of the 3D medical image to derive 2D segmentation data; determining a location of a bounding box (10) within the 3D medical image based on the 2D segmentation data, the bounding box (10) having predetermined dimensions; and carrying out a 3D segmentation for the object in the part of the 3D medical image corresponding to the bounding box (10).

Abstract: An image quality control system is disclosed. The example system includes an artificial intelligence modeler to process image data and metadata from patient data to generate first feature(s) from the image data and to parse the metadata to identify study information. The example system includes a computer vision processor to identify second feature(s) in the image data. The example system includes a results evaluator to compare the first feature(s) and second feature(s) to generate a comparison and to evaluate the comparison, first feature(s), and second feature(s) with respect to the study information to generate an evaluation. The example system includes a quality controller to compare the evaluation to quality criterion(-ia) to produce an approval or rejection of the patient data, the approval to trigger release of the patient data and the rejection to deny release of the patient data.

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: An image quality control system is disclosed. The example system includes an artificial intelligence modeler to process image data and metadata from patient data to generate first feature(s) from the image data and to parse the metadata to identify study information. The example system includes a computer vision processor to identify second feature(s) in the image data. The example system includes a results evaluator to compare the first feature(s) and second feature(s) to generate a comparison and to evaluate the comparison, first feature(s), and second feature(s) with respect to the study information to generate an evaluation. The example system includes a quality controller to compare the evaluation to quality criterion(-ia) to produce an approval or rejection of the patient data, the approval to trigger release of the patient data and the rejection to deny release of the patient data.

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 for visualizing an object of interest includes obtaining an image of an object of interest, automatically separating the image into tissue clusters, automatically selecting foreground clusters from the tissue clusters, automatically generating a contour based on the selected foreground clusters, and displaying an image of the object of interest including the foreground clusters and the contour. A system and non-transitory computer readable medium are also described herein.

Abstract: An apparatus for multi-energy tissue quantification includes an x-ray imaging system comprises an x-ray source configured to emit a beam of x-rays toward an object to be imaged, a detector configured to receive the x-rays attenuated by the object, and a data acquisition system (DAS) operably coupled to the detector. A computer operably connected to the x-ray source and the DAS is programmed to cause the x-ray source to emit x-rays at each of a first kVp and a second kVp toward the detector, acquire x-ray data from x-rays emitted at the first and second kVp through a region of interest (ROI), and perform a first multi-material decomposition based on the acquired x-ray data. The computer is also programmed to quantify a volume fraction of a first material in the ROI based on the first multi-material decomposition and display the volume fraction of the first material to a user.

Abstract: A method for generating an image includes obtaining a first image and a second image of an object of interest, generating a joint histogram using the first and second images, transforming the information in the histogram from histogram space to image space using a look-up table, and generating a color image using the information output from the look-up table. A system and non-transitory computer readable medium are also described herein.

Abstract: A method for generating an image includes obtaining a first image and a second image of an object of interest, generating a joint histogram using the first and second images, transforming the information in the histogram from histogram space to image space using a look-up table, and generating a color image using the information output from the look-up table. A system and non-transitory computer readable medium are also described herein.

Abstract: A method for visualizing an object of interest includes obtaining an image of an object of interest, automatically separating the image into tissue clusters, automatically selecting foreground clusters from the tissue clusters, automatically generating a contour based on the selected foreground clusters, and displaying an image of the object of interest including the foreground clusters and the contour. A system and non-transitory computer readable medium are also described herein.

Abstract: An apparatus for multi-energy tissue quantification includes an x-ray imaging system comprises an x-ray source configured to emit a beam of x-rays toward an object to be imaged, a detector configured to receive the x-rays attenuated by the object, and a data acquisition system (DAS) operably coupled to the detector. A computer operably connected to the x-ray source and the DAS is programmed to cause the x-ray source to emit x-rays at each of a first kVp and a second kVp toward the detector, acquire x-ray data from x-rays emitted at the first and second kVp through a region of interest (ROI), and perform a first multi-material decomposition based on the acquired x-ray data. The computer is also programmed to quantify a volume fraction of a first material in the ROI based on the first multi-material decomposition and display the volume fraction of the first material to a user.

Abstract: A system and process for analyzing multidimensional data characterizing a least a portion of a subject is described. An input module accepts at least one multidimensional dataset which is derived from any of several types of data sources. A registration module accepts the dataset from the input module and registers the dataset from the input module to a selected anatomical model to provide a registered dataset. A processing module is coupled to the registration module and uses this in determining a core region and associated core region information, and computes threshold characteristics of the registered dataset. A segmentation module accepts the registered dataset and the core region information from the processing module, and segments the registered dataset to provide a segmented description of an organ from the registered dataset and core region information, where the segmented, registered dataset describes characteristics of the organ of the subject.

Abstract: Systems, method and apparatus in which some embodiments of automatic segmentation of a liver parenchyma from multiphase contrast-enhanced computed-tomography images includes analyzing an intensity change in the images belonging to the different phases in order to determine the region-of-interest of the liver, thereafter segmenting starting from the region-of-interest and incorporating anatomical information to prevent oversegmentation, and thereafter combining the information of all available images.