Abstract: A method comprises inputting a treatment planning image of a target subject into a machine learning system. The method further comprises determining, by the machine learning system, a first target-subject-specific model of the treatment planning image. The method further comprises applying, by a processing device, the first target-subject-specific model to the treatment planning image to generate a transformed treatment planning image corresponding to a first position of a plurality of positions of the target subject. The method further comprises comparing the transformed treatment planning image to a reference image. The method further comprises, based on the comparing, modifying one or more parameters of the first target-subject-specific model to generate a second target-subject-specific model corresponding to a second position of the plurality of positions.

Abstract: A multimodal imaging apparatus, comprising a rotatable gantry system positioned at least partially around a patient support, a first source of radiation coupled to the rotatable gantry system, the first source of radiation configured for imaging radiation, a second source of radiation coupled to the rotatable gantry system, the second source of radiation configured for at least one of imaging radiation or therapeutic radiation, wherein the second source of radiation has an energy level more than the first source of radiation, and a second radiation detector coupled to the rotatable gantry system and positioned to receive radiation from the second source of radiation, and a processor configured to combine first measured projection data based on the radiation detected by the first detector with second measured projection data based on the radiation detected by the second detector, and reconstruct an image based on the combined data, wherein the reconstructing comprises at least one of correcting the second meas

Abstract: A method is described including online selecting of at least one of a plurality of optimal imaging times or a plurality of imaging angles and optimizing a parameter of an imaging system based on the online selecting.

Abstract: A system and method of performing prospective and retrospective on-line adaptive radiotherapy. The method includes performing, during a treatment delivery session, delivery of a dose of radiation to an anatomical volume. The method includes detecting, during the treatment delivery session, a current state of the anatomical volume. The method includes predicting a future change in the current state of the anatomical volume during the treatment delivery session. The method includes adjusting, while the anatomical volume is in the current state, the treatment delivery to anticipate the future change in the anatomical volume.

Abstract: A radiation treatment session is initiated to deliver a therapeutic radiation beam from a therapeutic radiation source to a target. One or more X-ray radiation sources are caused to deliver an imaging radiation beam from the one or more X-ray radiation sources through the target to one or more X-ray detectors to acquire imaging data associated with the target during therapeutic radiation beam delivery. One or more volumetric images are constructed using the acquired imaging data.

Abstract: A system and method of performing prospective and retrospective on-line adaptive radiotherapy. The method includes performing, during a treatment delivery session, delivery of a dose of radiation to an anatomical volume. The method includes detecting, during the treatment delivery session, a current state of the anatomical volume. The method includes predicting a future change in the current state of the anatomical volume during the treatment delivery session. The method includes adjusting, while the anatomical volume is in the current state, the treatment delivery to anticipate the future change in the anatomical volume.

Abstract: Techniques for hybrid videoconferencing are described. A method of hybrid videoconferencing may comprise receiving, by a call routing service, a request to initiate a call with a provider from a user device, providing, by the call routing service, first endpoint data associated with a first connection between the user device and an agent device associated with the provider, establishing the first connection between the agent device and the user device via the call routing service, providing, by the call routing service, second endpoint data associated with a second connection between the user device and the agent device, and establishing, by a peer-to-peer (P2P) contact service, the second connection between the agent device and the user device.

Abstract: A radiation treatment session is initiated to deliver a therapeutic radiation beam from a therapeutic radiation source to a target. One or more X-ray radiation sources are caused to deliver an imaging radiation beam from the one or more X-ray radiation sources through the target to one or more X-ray detectors to acquire imaging data associated with the target during therapeutic radiation beam delivery. One or more volumetric images are constructed using the acquired imaging data.

Abstract: A method including applying a first target-subject-specific model associated with a target subject to a treatment planning image to generate a transformed treatment planning image corresponding to a first position of a plurality of positions. The method also includes modifying one or more hyper-parameters of the first target-subject-specific model to generate a second target-subject-specific model corresponding to a second position of the plurality of positions. The method further includes controlling a radiation treatment delivery device based on the second target-subject-specific model to deliver a radiation treatment to the target subject.

Abstract: A method comprises identifying a treatment planning image of a target subject, the treatment planning image comprising information associated with an arrangement of structures within the target subject. The method further comprises generating, based on the information, a set of reference data associated with the target subject, the reference data indicating a plurality of positions of the target subject. The method further comprises generating target-subject-specific models based on the reference data and modifying one or more hyper-parameters of the target-subject-specific mode to generate second target-subject-specific models corresponding to a second position of the plurality of positions. The method further comprises controlling a radiation treatment delivery device based on the second target-subject-specific model to deliver a radiation treatment to the target subject.

Abstract: A radiation treatment session is initiated to deliver a therapeutic radiation beam from a therapeutic radiation source to a target. One or more X-ray radiation sources are caused to deliver an imaging radiation beam from the one or more X-ray radiation sources through the target to one or more X-ray detectors to acquire imaging data associated with the target during therapeutic radiation beam delivery. One or more volumetric images are constructed using the acquired imaging data.

Abstract: A method is described including online selecting of at least one of a plurality of optimal imaging times or a plurality of imaging angles and optimizing a parameter of an imaging system based on the online selecting.

Abstract: An image of a region of interest (ROI) is identified from a first perspective, the image having an uncertainty value associated with the ROI. A model is generated comprising one or more parameters associated with the ROI based on the image. A plurality of tracking quality metrics for a plurality of perspectives that a subsequent image may be captured from by an imaging system of the ROI are determined using the model, the tracking quality metrics indicating a reduction of the uncertainty value associated with the ROI by the subsequent image. A second perspective of the plurality of perspectives for the subsequent image is selected based on a corresponding tracking quality metric of the plurality of tracking quality metrics for the second perspective indicating a reduction of the uncertainty value.

Abstract: An image of a region of interest (ROI) is identified from a first perspective, the image having an uncertainty value associated with the ROI. A model is generated comprising one or more parameters associated with the ROI based on the image. A plurality of tracking quality metrics for a plurality of perspectives that a subsequent image may be captured from by an imaging system of the ROI are determined using the model, the tracking quality metrics indicating a reduction of the uncertainty value associated with the ROI by the subsequent image. A second perspective of the plurality of perspectives for the subsequent image is selected based on a corresponding tracking quality metric of the plurality of tracking quality metrics for the second perspective indicating a reduction of the uncertainty value.

Abstract: A multimodal imaging apparatus, comprising a rotatable gantry system positioned at least partially around a patient support, a first source of radiation coupled to the rotatable gantry system, the first source of radiation configured for imaging radiation, a second source of radiation coupled to the rotatable gantry system, the second source of radiation configured for at least one of imaging radiation or therapeutic radiation, wherein the second source of radiation has an energy level more than the first source of radiation, and a second radiation detector coupled to the rotatable gantry system and positioned to receive radiation from the second source of radiation, and a processor configured to combine first measured projection data based on the radiation detected by the first detector with second measured projection data based on the radiation detected by the second detector, and reconstruct an image based on the combined data, wherein the reconstructing comprises at least one of correcting the second meas

Abstract: Multimodal imaging apparatus and methods include a rotatable gantry system with multiple sources of radiation comprising different energy levels (for example, kV and MV). Fast slip-ring technology and helical scans allow data from multiple sources of radiation to be combined or utilized to generate improved images and workflows, including for IGRT. Features include increasing the precision of spatial registrations between respective image sets to allow more precise radiation treatment delivery, reducing image artifacts (e.g., scatter, metal and beam hardening, image blur, motion, etc.), and utilization of dual energy imaging (e.g., for material separation and quantitative imaging, patient setup, online adaptive IGRT, etc.).

Abstract: A method of hybrid videoconferencing may comprise receiving, by a call routing service, a request to initiate a call with a provider from a user device, providing, by the call routing service, first endpoint data associated with a first connection between the user device and an agent device associated with the provider, establishing the first connection between the agent device and the user device via the call routing service, providing, by the call routing service, second endpoint data associated with a second connection between the user device and the agent device, and establishing, by a peer-to-peer (P2P) contact service, the second connection between the agent device and the user device.

Abstract: A method comprises inputting a treatment planning image of a target subject into a machine learning system. The method further comprises determining, by the machine learning system, a first target-subject-specific model of the treatment planning image. The method further comprises applying, by a processing device, the first target-subject-specific model to the treatment planning image to generate a transformed treatment planning image corresponding to a first position of a plurality of positions of the target subject. The method further comprises comparing the transformed treatment planning image to a reference image. The method further comprises, based on the comparing, modifying one or more parameters of the first target-subject-specific model to generate a second target-subject-specific model corresponding to a second position of the plurality of positions.

Abstract: A method comprises identifying a treatment planning image of a target subject, the treatment planning image comprising information associated with an arrangement of structures within the target subject. The method further comprises generating, based on the information, a set of reference data associated with the target subject, the reference data indicating a plurality of positions of the target subject. The method further comprises generating target-subject-specific models based on the reference data and modifying one or more hyper-parameters of the target-subject-specific mode to generate second target-subject-specific models corresponding to a second position of the plurality of positions. The method further comprises controlling a radiation treatment delivery device based on the second target-subject-specific model to deliver a radiation treatment to the target subject.

Abstract: Multimodal imaging apparatus and methods include a rotatable gantry system with multiple sources of radiation comprising different energy levels (for example, kV and MV). Fast slip-ring technology and helical scans allow data from multiple sources of radiation to be combined or utilized to generate improved images and workflows, including for IGRT. Features include increasing the precision of spatial registrations between respective image sets to allow more precise radiation treatment delivery, reducing image artifacts (e.g., scatter, metal and beam hardening, image blur, motion, etc.), and utilization of dual energy imaging (e.g., for material separation and quantitative imaging, patient setup, online adaptive IGRT, etc.).