Abstract: Systems and methods for automated patient anatomy and orientation identification using an artificial intelligence (AI) based deep learning module are provided. The method comprises positioning a subject over a table of a magnetic resonance imaging (MRI) system and wrapping at least one radiofrequency (RF) imaging coil over the subject. The method comprises obtaining a plurality of depth images, color images and infrared images of the subject using a three-dimensional (3D) depth camera and identifying the table boundary of the MRI system using the images obtained by the 3D camera. The method further comprises identifying a location of the subject over the table to determine if the subject is positioned within the table boundary of the MRI system and identifying a plurality of key anatomical points or regions corresponding to a plurality of organs of the subject body.

Abstract: The current disclosure provides methods and systems for rapidly and consistently determining medical image quality metrics following acquisition of a diagnostic medical image. In one embodiment, the current disclosure teaches a method for determining an image quality metric by, acquiring a medical image of an anatomical region, mapping the medical image to a positional attribute of an anatomical feature using a trained deep neural network, determining an image quality metric based on the positional attribute of the anatomical feature, determining if the image quality metric satisfies an image quality criterion, and displaying the medical image, the image quality metric, and a status of the image quality criterion via a display device. In this way, a diagnostic scanning procedure may be expedited by providing technicians with real-time insight into quantitative image quality metrics.

Abstract: Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, determining at least one spine label seed point on a non-functional image volume, automatically labeling the non-functional image volume with a plurality of spine labels based on the at least one spine label seed point, automatically correcting the geometric misalignments and registering the functional image volume, adjusting the plurality of spine labels and propagating the adjusted spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Abstract: Systems and methods for automated patient anatomy and orientation identification using an artificial intelligence (AI) based deep learning module are provided. The method comprises positioning a subject over a table of a magnetic resonance imaging (MRI) system and wrapping at least one radiofrequency (RF) imaging coil over the subject. The method comprises obtaining a plurality of depth images, color images and infrared images of the subject using a three-dimensional (3D) depth camera and identifying the table boundary of the MRI system using the images obtained by the 3D camera. The method further comprises identifying a location of the subject over the table to determine if the subject is positioned within the table boundary of the MRI system and identifying a plurality of key anatomical points or regions corresponding to a plurality of organs of the subject body.

Abstract: Methods and systems are provided for estimating patient structure prior to a scan by a medical imaging system. As one example, a method may include acquiring depth images of a patient positioned on a table of the medical imaging system, correcting the depth images based on histogram data from the depth images, and extracting a three-dimensional structure of the patient based on the corrected depth images.

Abstract: Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, determining at least one spine label seed point on a non-functional image volume, automatically labeling the non-functional image volume with a plurality of spine labels based on the at least one spine label seed point, automatically correcting the geometric misalignments and registering the functional image volume, adjusting the plurality of spine labels and propagating the adjusted spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Abstract: Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold.

Abstract: Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, automatically labeling the non-functional image volume with spine labels, automatically correcting the geometric misalignments and registering the functional image volume, and propagating the spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Abstract: Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold.

Abstract: Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold.

Abstract: Methods and systems are provided for estimating patient structure prior to a scan by a medical imaging system. As one example, a method may include acquiring depth images of a patient positioned on a table of the medical imaging system, correcting the depth images based on histogram data from the depth images, and extracting a three-dimensional structure of the patient based on the corrected depth images.

Abstract: Examples of systems and methods are described for selecting firmware versions of multiple components for a distributed computing system (e.g., a cluster). Multiple selection interfaces may be presented to a user who may select at least one firmware version of at least one component. Based on the user selection(s), a service manager may evaluate firmware component dependencies and identify compatible firmware versions of other components for installation. In this manner, a set of firmware versions may be installed and/or upgraded which may be different than a current set of versions and/or a set of versions recommended in a wholly automated manner.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a set of video frames associated with a video. A determination can be made that a threshold number of video frames of the set of video frames depict two or more reaction icons of a set of reaction icons. The video can be identified as a poll video based on the determining that the threshold number of video frames of the set of video frames depict two or more reaction icons of the set of reaction icons.

Abstract: A method for generating an object 3D point cloud in a medical imaging system comprising a machine table and a scanning device comprises: extracting a valid 3D point cloud in a valid region where the machine table is located from a global 3D point cloud based on a current height of the machine table and boundary information of the machine table, wherein the global 3D point cloud comprises 3D point clouds of an object and a surrounding environment thereof, and the object 3D point cloud is comprised in the valid 3D point cloud; and removing an environment 3D point cloud of the surrounding environment from the valid 3D point cloud to obtain the object 3D point cloud, wherein the surrounding environment comprises at least part of the machine table. In some embodiments, a moving path of the machine table in the medical imaging system is planned using the object 3D point cloud. In some embodiments, collision prediction of the object is performed in the medical imaging system using the object 3D point cloud.

Abstract: Examples described herein provide for hardware interface services in virtualized systems. The hardware interface services may receive a vendor-agnostic command to control a particular hardware component. The particular hardware component may be identified, for example, by its location (e.g., physical and/or logical location or other identification) in the virtualized system. The hardware interface services described herein may identify a hardware component type (e.g., vendor, serial number, model number, etc.) based on the location provided. The hardware interface services may translate the vendor-agnostic command to a command specific for the identified hardware component.

Abstract: Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, automatically labeling the non-functional image volume with spine labels, automatically correcting the geometric misalignments and registering the functional image volume, and propagating the spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Abstract: A system and method include creating a bootable virtual machine (VM) image for a container image. The method includes a controller machine creating a single partition within an output VM disk file where the single partition comprises a master boot record and a partition table, forming a valid file system in a main partition of the output VM disk file, arranging an input set of container image definitions as a list where a base image forms a head of the list and subsequent images follow in the list, sequentially processing the list for each image by adding the input set of container image definitions to the output VM file; and applying a final networking configuration over the output VM file.

Abstract: A system and method include receiving, by a migration tool of a virtual computing system, an indication for hypervisor conversion for converting a hypervisor on nodes in a cluster of the virtual computing system from a first hypervisor type to a second hypervisor type. The system and method also include converting, one at a time, the hypervisor on each of the nodes from the first hypervisor type to the second hypervisor type in response to the indication, including converting virtual machines on each of the nodes for running on the second hypervisor type. The hypervisor and the virtual machines are converted on one node before starting conversion of the hypervisor and the virtual machines on another node, and the virtual machines of the one node are migrated from the one node before conversion and the migrated virtual machines remain operational during conversion of the hypervisor on the one node.

Abstract: A system and method include assigning, by an identifier management system of a virtual computing system, a hypervisor agnostic identifier to a virtual machine. The system and method also include creating a mapping of the hypervisor agnostic identifier to a first hypervisor specific identifier of the virtual machine, including storing the mapping in a database, and updating the mapping in response to a second hypervisor specific identifier being associated with the virtual machine. The updated mapping maps the hypervisor agnostic identifier to the second hypervisor specific identifier. The system and method further include making available the hypervisor agnostic identifier for use by other elements of the virtual computing system instead of the first hypervisor specific identifier and the second hypervisor specific identifier. The first hypervisor specific identifier and the second hypervisor specific identifier are hypervisor specific, while the hypervisor agnostic identifier is not hypervisor specific.

Abstract: Examples of systems and methods are described for selecting firmware versions of multiple components for a distributed computing system (e.g., a cluster). Multiple selection interfaces may be presented to a user who may select at least one firmware version of at least one component. Based on the user selection(s), a service manager may evaluate firmware component dependencies and identify compatible firmware versions of other components for installation. In this manner, a set of firmware versions may be installed and/or upgraded which may be different than a current set of versions and/or a set of versions recommended in a wholly automated manner.