Abstract: A weakly supervised intracranial hemorrhage (ICH) detection workflow includes training a deep learning (DL) model including a coupled convolutional neural network and recurrent neural network on a large dataset of CT scans with expert-labeled slices indicating presence or absence of ICH. Transfer learning (TL) is used to further train the DL model using a second large dataset of CT scans with only scan labels extracted from radiology reports using natural language processing (NLP). The DL model weights each slice of the scan against the final ICH diagnosis using an attention-based bi-directional long-short term memory network, where the attention weights represent slice-level ICH predictions. Model-generated heatmaps highlight significant regions of the CT scans that lead to the provided ICH predictions.

Abstract: A system is described, which provides a realtime, thermal-based intraoperative brain mapping system. In general, the system integrates a thermal camera that provides a map of temperature changes, while simultaneously providing stimuli and recording behavioral responses. The system can implement real-time processing of data to produce functional maps. The present disclosure also provides methods for characterizing the spatial and temporal properties of the thermodynamic response, which can be used to optimize an infrared mapping procedure.

Abstract: A weakly supervised intracranial hemorrhage (ICH) detection workflow includes training a deep learning (DL) model including a coupled convolutional neural network and recurrent neural network on a large dataset of CT scans with expert-labeled slices indicating presence or absence of ICH. Transfer learning (TL) is used to further train the DL model using a second large dataset of CT scans with only scan labels extracted from radiology reports using natural language processing (NLP). The DL model weights each slice of the scan against the final ICH diagnosis using an attention-based bi-directional long-short term memory network, where the attention weights represent slice-level ICH predictions. Model-generated heatmaps highlight significant regions of the CT scans that lead to the provided ICH predictions.

Abstract: Intraoperative functional mapping using an intraoperative thermal imaging system is described. The system enables higher resolution images, faster acquisition speeds, and is non-invasive. The high resolution functional maps can provide physiologic information, prognostic information, and functional network structures to a neurosurgeon in a time efficient manner.

Abstract: Described here are systems and methods for obtaining measurements of both tissue perfusion and permeability with a magnetic resonance imaging (“MRI”) system after the administration of a single dose of contrast agent. To this end, the MRI system is directed to acquire T2*-weighted data, during which the acquired signal values are monitored for a trigger event. When the trigger event occurs, the MRI system is directed to switch from acquiring the T2*-weighted data to acquiring T1-weighted data. The systems and methods of the present invention can thus be used for a fully automated, single acquisition of perfusion and permeability measurements using only a single dose of contrast agent.

Abstract: Described here are systems and methods for obtaining measurements of both tissue perfusion and permeability with a magnetic resonance imaging (“MRI”) system after the administration of a single dose of contrast agent. To this end, the MRI system is directed to acquire T2-weighted or T2*-weighted data, during which the acquired signal values are monitored for a trigger event. When the trigger event occurs, the MRI system is directed to switch from acquiring the T2-weighted or T2*-weighted data to acquiring T1-weighted data. The systems and methods described here can thus be used for a fully automated, single acquisition of perfusion and permeability measurements using only a single dose of contrast agent.

Abstract: Described here are systems and methods for obtaining measurements of both tissue perfusion and permeability with a magnetic resonance imaging (“MRI”) system after the administration of a single dose of contrast agent. To this end, the MRI system is directed to acquire T2-weighted or T2*-weighted data, during which the acquired signal values are monitored for a trigger event. When the trigger event occurs, the MRI system is directed to switch from acquiring the T2-weighted or T2*-weighted data to acquiring T1-weighted data. The systems and methods described here can thus be used for a fully automated, single acquisition of perfusion and permeability measurements using only a single dose of contrast agent.

Abstract: Described here are systems and methods for obtaining measurements of both tissue perfusion and permeability with a magnetic resonance imaging (“MRI”) system after the administration of a single dose of contrast agent. To this end, the MRI system is directed to acquire T2*-weighted data, during which the acquired signal values are monitored for a trigger event. When the trigger event occurs, the MRI system is directed to switch from acquiring the T2*-weighted data to acquiring T1-weighted data. The systems and methods of the present invention can thus be used for a fully automated, single acquisition of perfusion and permeability measurements using only a single dose of contrast agent.

Abstract: A method for operating an automated functional Magnetic Resonance Imaging (fMRI) system includes controlling, by a control computer, a Magnetic Resonance Imaging (MRI) device to apply one or more pulse sequences to a portion of a brain of a patient and controlling, by the control computer, one or more stimulation devices to provide a stimulation of the patient. The method also includes acquiring, by the control computer, functional images of said portion of said brain of the patient in response to the applying of the one or more pulse sequences and during stimulation and receiving, by the control computer, one or more patient responses during the stimulating of the patient. The method further includes synchronizing, by the control computer, the stimulation of the patient, the acquiring of the functional images and the receiving of the one or more patient responses using at least one synchronization signal.

Abstract: We present a method for informed optimization of sampling vectors in multi-directional diffusion-weighted magnetic resonance imaging. The advantage of this optimization is that it is informed rather than being a naïve optimization of sampling vectors. Typically, sampling vectors are set relatively uniformly along a spherical surface. In this case, a scan at high imaging resolutions utilizes sampling vectors that are chosen based on the knowledge of the overall orientation distribution for the entire sample or region of interest. This overall orientation distribution is obtained by performing multi-directional diffusion-weighted scans at high angular resolution, but low or minimal voxel resolution. A subset of the vectors used in this high-angular-resolution scan is chosen to minimize the error in the final results. This optimal subset is not necessarily uniform in space.