The General Hospital Corporation

Massachusetts Institute of Technology

Boston University

Bo Zhu

Matthew Scot Rosen

Bruce R Rosen

Wojciech Matusik

Lawrence Leroy Wald

Desai Chen

Ouri Cohen

Neha Koonjoo

Melina Skouras

Danyal Fareed Bhutto

Systems, methods, and media for complex input data configurations for imaging applications. Complex data optimization can be provided to improve accuracy of models (e.g., neural networks) used to reconstruct medical images from raw sensor data, for example. Complex data optimization can include applying raw sensor data to an input layer of a neural network to generate an input vector ordered such that real components and imaginary components of samples in the raw sensor data are adjacent. The input vector can then be applied to convolutional layer of the neural network.

System and method for complex input data configurations for imaging applications

A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

System and method for automated transform by manifold approximation

System and method for optimizing a three-dimensional model representing a shape of an object to be fabricated from a plurality of materials having known physical properties. The object is designed to exhibit one or more target properties and the three-dimensional model includes a plurality of cells. The system includes at least one processor programmed to receive a data structure including information for a material property gamut of microstructures for the plurality of materials and two or more of the known physical properties of the plurality of materials, and perform a topology optimization process on the three-dimensional model to generate an optimized model, wherein the topology optimization process is constrained based, at least in part, on the information in the received data structure and the one or more target properties.

Topology optimization with microstructures

Disclosed is a system and method for estimating quantitative parameters of a subject using a magnetic resonance ('MR') system using a dictionary. The dictionary may include a plurality of signal templates that sparsely sample acquisition parameters used when acquiring data. The acquired data is compared with the dictionary using a neural network. Thus, systems and methods are provided that are more computationally efficient, and have reduced data storage requirements than traditional MRF reconstruction systems and methods.

System and method for magnetic resonance fingerprinting using neural networks trained with sparsely sampled dictionaries

A system and method for producing an image of a subject with a magnetic resonance imaging system, in which the image depicts an image contrast indicative of rotary saturation produced in response to magnetic particles administered to the subject, are provided. An agent that includes magnetic particles is administered to the subject. An electromagnetic drive field is applied to the subject at a drive frequency so that the magnetic particles produce magnetic fields that oscillate at the drive frequency and harmonics thereof. A spin-lock field is then established at a spin-lock frequency that is a harmonic of the drive frequency in order to produce rotary saturation of nuclear spins affected by the magnetic fields produced by the magnetic particles. Image data is then acquired from the subject using the MRI system, from which an image of the subject that depicts an image contrast indicative of the produced rotary saturation is reconstructed.

Growing community of inventors

Cambridge, MA, United States of America

Bo Zhu