Abstract: Techniques for detecting certain acoustic events from audio data are described. A system may perform event aggregation for certain types of events before sending an output to a device representing the event is detected. The system may bypass the event aggregation process for certain types of events that the system may detect with a high level of confidence. In such cases, the system may send an output to the device when the event is detected. The system may be used to detect acoustic events representing presence of a person or other harmful circumstances (such as, fire, smoke, etc.) in a home, an office, a store, or other types of indoor settings.

Abstract: A method for determining peripheral nerve stimulation during MR imaging of a patient in a MR scan unit for a MR pulse sequence is described. In the method, a plurality of model-based candidate stimulations are determined dependent on a unit vector potential of the gradient magnet field generated during MR imaging and dependent on candidate data models for different object parameter values. A model-based candidate data stimulation is selected as a stimulation model for the patient dependent on an individual patient model. A distribution of a vector potential of a gradient magnetic field acting on the patient is determined as a function of a unit gradient current for a determined position of the patient in the MR scanning unit. The nerve stimulation of the patient is determined for the determined position based on the selected candidate stimulation and a gradient current of a gradient pulse of the MR pulse sequence.

Abstract: A system and method is provided for assessing Peripheral Nerve Stimulation (PNS). The system receives an imaging pulse sequence to be applied to a region of interest (ROI) of a subject arranged in the imaging system, where the imaging pulse sequence identifies coil parameters related to at least one coil. The system obtains a first model including a plurality of tissue types and corresponding electromagnetic properties in the ROI. The system then obtains a second model indicating location, orientation, and/or physiological properties of one or more nerve tracks in the ROI. The system estimates a plurality of PNS thresholds in the ROI caused by the imaging pulse sequence applied in the imaging system using the first model, the second model, a nerve membrane model, and the coil parameters.

Abstract: A method for determining peripheral nerve stimulation during MR imaging of a patient in a MR scan unit for a MR pulse sequence is described. In the method, a plurality of model-based candidate stimulations are determined dependent on a unit vector potential of the gradient magnet field generated during MR imaging and dependent on candidate data models for different object parameter values. A model-based candidate data stimulation is selected as a stimulation model for the patient dependent on an individual patient model. A distribution of a vector potential of a gradient magnetic field acting on the patient is determined as a function of a unit gradient current for a determined position of the patient in the MR scanning unit. The nerve stimulation of the patient is determined for the determined position based on the selected candidate stimulation and a gradient current of a gradient pulse of the MR pulse sequence.

Abstract: Systems and methods for designing and manufacturing electromagnetic coils for use with a magnetic resonance imaging (“MRI”) system are described. More particularly, described here are methods for designing and manufacturing gradient coils for producing magnetic field gradients with greater peripheral nerve stimulation (“PNS”) thresholds relative to conventional gradient coils. The gradient coil design is constrained using an oracle penalty that is computed to account for a PNS requirement for the coil. In other applications, the oracle penalty can be used to optimize driving patterns for an electromagnetic stimulation system, such that a target PNS requirement is achieved.

Abstract: A method for assessing peripheral nerve stimulation (PNS) for a coil geometry includes retrieving a PNS Huygens' P-matrix for a body model. The PNS Huygens' P-matrix is defined on a Huygens' surface enclosing the body model. The method further includes generating a coil specific PNS P-matrix for the coil geometry based on at least the PNS Huygens' P-matrix for the body model, determining at least one PNS threshold for the coil geometry based on the coil specific PNS P-matrix, and storing the at least one PNS threshold in a storage device.

Abstract: A system and method for assessing Peripheral Nerve Stimulation (PNS). The system receives an imaging pulse sequence to be applied to at least a region of interest (ROI) of a subject arranged in the imaging system, the imaging pulse sequence identifying coil parameters related to at least one coil. The system obtains a first model including a plurality of tissue types and corresponding electromagnetic properties in the ROI. The system then obtains a second model indicating at least one of location, orientation, and physiological properties of one or more nerve tracks in the ROI. The system estimates a plurality of PNS thresholds in the ROI caused by the imaging pulse sequence applied in the imaging system using the first model, the second model, a nerve membrane model, and the coil parameters.