Abstract: An example client device includes processing circuitry and a memory including instructions that, when executed by the processing circuitry, cause the client device to undertake certain actions. Certain instructions cause the device to periodically measure active network performance data for a network, calculate expected rewards for the plurality of entry points, select an expected best entry point based on the expected rewards, route data to the selected entry point, measure passive network performance data for the selected entry point, and update a reinforcement learning algorithm, based in part on the measured passive network performance data.

Abstract: Systems and methods for mapping a patient to one or more clinical trials are provided. Patient data of a patient is received and encoded into a patient model of the patient. Synthetic patients are generated for each clinical trial in a set of clinical trials based on characteristics of participants in that clinical trial. The patient model of the patient is compared to each of the synthetic patients to identify synthetic patients matching the patient model. The patient is mapped to one or more clinical trials in the set of clinical trials based on the matching synthetic patients.

Abstract: Systems and methods for predicting risk for a medical event associated with evaluating or treating a patient for a disease are provided. Input medical imaging data and patient data of a patient are received. The input medical imaging data includes abnormality patterns associated with a disease. Imaging features are extracted from the input medical imaging data using a trained machine learning based feature extraction network. One or more of the extracted imaging features are normalized. The one or more normalized extracted imaging features and the patient data are encoded into features using a trained machine learning based encoder network. Risk for a medical event associated with evaluating or treating the patient for the disease is predicted based on the encoded features.

Abstract: Described herein are methods, network devices, systems, and computer-readable media that provide a technical solution for runtime monitoring and visualization of intent-based network policies in a manner that bridges the gap between high-level insights from runtime and low-level network device configurations. A network topology and a plurality of network configurations can be received in an intent-based network and a number of monitoring spots available within the network topology for runtime monitoring of an intent-based network policy among a plurality of intent-based policies can be determined. A plurality of runtime constraints including one or more of time, resource capacity, and bandwidth demand can then be determined based on the network topology and the plurality of network configurations.

Abstract: Techniques and architectures for measuring available bandwidth. A train of probe packets is received from a remote electronic device. A per-packet one-way delay (OWD) is calculated for at least two packets from the train of probe packets. An OWD threshold value is calculated based on the calculated OWD for the at least two packets from the train of probe packets. A packet pair is selected from the train of probe packets based on the per-packet OWD for each packet in the packet pair exceeding the OWD threshold value. An estimated available bandwidth is computed based on one or more transmission characteristics of the selected packet pair.

Abstract: Systems and methods for assessing cardiovascular disease of a patient are provided. Patient data of the patient is received. The patient data may include one or more input medical images of a chest of the patient, results of an assessment of a lung disease performed based on the one or more input medical images, demographic and clinical data of the patient, and cardiovascular imaging exams of the patient. One or more risk scores are computed for the patient based on the patient data using a trained machine learning based network.

Abstract: Systems and methods are provided for assessing collateral circulation of a patient. Patient data of a patient is received. A collateral circulation score is computed based on the patient data using a trained machine learning network. The collateral circulation score represents functioning of collateral circulation of the patient. The collateral circulation score is output.

Abstract: Systems and methods are provided for evaluating an aorta of a patient. A medical image of an aorta of a patient is received. The aorta is segmented from the medical image. One or more measurement planes are identified on the segmented aorta. At least one measurement is calculated at each of the one or more measurement planes. The aorta of the patient is evaluated based on the at least one measurement calculated at each of the one or more measurement planes.

Abstract: Techniques and architectures for measuring available bandwidth. A train of probe packets is received from a remote electronic device. A per-packet one-way delay (OWD) is calculated for at least two packets from the train of probe packets. An OWD threshold value is calculated based on the calculated OWD for the at least two packets from the train of probe packets. A packet pair is selected from the train of probe packets based on the per-packet OWD for each packet in the packet pair exceeding the OWD threshold value. An estimated available bandwidth is computed based on one or more transmission characteristics of the selected packet pair.

Abstract: Systems and methods for generating a segmentation mask of an anatomical structure, along with a measure of uncertainty of the segmentation mask, are provided. In accordance with one or more embodiments, a plurality of candidate segmentation masks of an anatomical structure is generated from an input medical image using one or more trained machine learning networks. A final segmentation mask of the anatomical structure is determined based on the plurality of candidate segmentation masks. A measure of uncertainty associated with the final segmentation mask is determined based on the plurality of candidate segmentation masks. The final segmentation mask and/or the measure of uncertainty are output.

Abstract: Machine-based risk prediction or assistance is provided for peri-procedural complication, such as peri-procedural myocardial infarction (PMI). A machine-learned model is used to predict risk of PMI and/or recommend courses of action to avoid PMI in PCI. Various combinations of types or modes of information are used in the prediction, such as both imaging and non-imaging data. The prediction may be made prior to, during, and/or after PCI using the machine-learned model to more quickly reduce the chance of PMI. The workflows for prior, during, and/or post PCI incorporate the risk prediction and/or risk-based recommendations to reduce PMI for patients.

Abstract: Example implementations relate to determining whether network invariants are violated by flow rules to be implemented by the data plane of a network. In an example, a verification module implemented on a device receives a flow rule transmitted from an SDN controller to a switch, the flow rule relating to an event. The module determines whether the flow rule matches any of a plurality of network invariants cached in the device. If determined that the flow rule matches one of the plurality of network invariants, the verification module determines whether the flow rule violates the matched network invariant. If determined that the flow rule does not match any of the plurality of network invariants, the verification module (1) reports the event associated with the flow rule to a policy management module, (2) receives a new network invariant related to the event from the policy management module, and (3) determines whether the flow rule violates the new network invariant.

Abstract: Techniques and architectures for measuring available bandwidth. A train of probe packets is received from a remote electronic device. A network transmission delay for at least two packets from the train of probe packets is measured. Network congestion is estimated utilizing the at least two packets from the train of probe packets. An estimated available bandwidth is computed based on the network transmission and estimated network congestion. One or more network transmission characteristics are modified based on the estimated available bandwidth.

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.

Abstract: An embodiment of a method includes providing a first result list indicating a plurality of first anatomic structures and indicating, for each respective first anatomic structure of the plurality of first anatomic structures, a corresponding first severity indicator; providing a second result list indicating, for each respective second anatomic structure of the plurality of the second anatomic structures, a corresponding second severity indicator; providing a relationship matrix indicating a level of interrelatedness between the first anatomic structures and the second anatomic structures; and generating, based on the first result list provided, on the second result list and on the relationship matrix provided, a concordance visualization indicating a respective level of concordance between at least one of the first anatomic structures and the corresponding first severity indicator, and indicating a respective level of concordance between at least one of the second anatomic structures and the corresponding sec

Abstract: A first sequence of cardiac image frames are received by a first neural network of the neural network system. The first neural network outputs a first set of feature values. The first set of feature values includes a plurality of data subsets, each corresponding to a respective image frame and relating to spatial features of the respective image frame. The first set of feature values are received at a second neural network of the neural network system. The second neural network outputs a second set of feature values relating to temporal features of the spatial features. Based on the second set of feature values, a cardiac phase value relating to a cardiac phase associated with a first image frame is determined.

Abstract: Example implementations relate to a proactive auto-scaling approach. According to an example, a machine-learning prediction model is trained to forecast future serverless workloads during a window of time for an application running in a public cloud based on past serverless workload information associated with the application by performing a training process. During the window of time, serverless workload information associated with the application is monitored. A future serverless workload is predicted for the application at a future time within the window, based on the machine learning prediction model. Prior to the future time, containers within the public cloud executing the application are pre-warmed to accommodate the predicted future serverless workload by issuing fake requests to the application to trigger auto-scaling functionality implemented by the public cloud.

Abstract: Example implementations relate to a proactive auto-scaling approach. According to an example, a target performance metric for an application running in a serverless framework of a private cloud is received. A machine-learning prediction model is trained to forecast future serverless workloads during a window of time for the application based on historical serverless workload information. The serverless framework is monitored to obtain serverless workload observations for the application. A future serverless workload for the application at a future time is predicted by the trained machine learning prediction model based on workload observations. A feedback control system is then used to output a new number of replicas based on a current value of the performance metric, the target performance metric and the predicted future serverless workload. Finally, the serverless framework is caused to scale and pre-warm a number of replicas supporting the application to the new number.

Abstract: An example system may comprise a set of network devices in a network topology, the network topology having a plurality of external links that connect to other networks, wherein the system comprises a processing resource to: assign multiple Internet Protocol (IP) addresses to one of the network interfaces of a client device; communicate the multiple IP addresses to a network interface of the client device; receive a packet from the one of the network interfaces, wherein the packet includes a source address that is one of the multiple IP addresses; select an external link of the plurality of external links based on the source address of the packet; and forward the packet via the external link of the plurality of external links.

Abstract: Systems and methods for retraining a trained machine learning model are provided. One or more input medical images are received. Measures of interest for a primary task and a secondary task are predicted from the one or more input medical images using a trained machine learning model. The predicted measures of interest for the primary task and the secondary task are output. User feedback on the predicted measure of interest for the secondary task is received. The trained machine learning model is retrained for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.