University of California

At+t Corp.

At&t Intellectual Property I, L.p.

California Institute of Technology

Technische Unversität Berlin

Other

Broadcom Corporation

Csub Auxillary for Sponsored Programs Administration

Hamid Jafarkhani

Vahid Tarokh

Yao Rong Wang

Amy Ruth Reibman

Michael Orchard

Nambirajan Seshadri

Arash Kheradvar

Babak Hassibi

Peter Jung

Philipp Walk

Li Liu

Ayman Fawzy Naguib

Arthur Robert Calderbank

Bedri A Cetiner

Homayoun Yousefi'zadeh

Michael Rashidi Avendi

Zhiying Wang

Mahdi Hajiaghayi

Weiqi Li

Sanaz Barghi

Behzad Shahraray

Hani Mehrpouyan

Vida Vakilian

Erdem Koyuncu

Elliott Groves

Feng Li

Arghavan Arafati

Saeed Karimi-Bidhendi

Processes and device configurations are provided for generating and using flexible storage codes. Methods and configurations described herein can reconstruct and recover data from a distributed network in the event of one or more failures or erasures. According to embodiments, a method includes determining the number of nodes and number of symbols of a flexible storage code, and reconstructing the information using the flexible storage code and determined numbers of nodes and symbols. The flexible storage code may be configured for a flexible number of nodes and symbols for information to use a subarray of symbols and nodes of a storage code array for information. Flexible storage codes may provide a framework for a reconstruction configuration using one or more of a flexible locally recoverable code (LRC), flexible partial maximum distance separable code (PMDSC), and flexible minimum storage regenerating code (MSRC).

Systems and methods for distributed storage using storage codes with flexible number of nodes

Methods, devices, and systems that are related to facilitating an automated, fast and accurate model for cardiac image segmentation, particularly for image data of children with complex congenital heart disease are disclosed. In one example aspect, a generative adversarial network is disclosed. The generative adversarial network includes a generator configured to generate synthetic imaging samples associated with a cardiovascular system, and a discriminator configured to receive the synthetic imaging samples from the generator and determine probabilities indicating likelihood of the synthetic imaging samples corresponding to real cardiovascular imaging sample. The discriminator is further configured to provide the probabilities determined by the discriminator to the generator and the discriminator to allow the parameters of the generator and the parameters of the discriminator to be adjusted iteratively until an equilibrium between the generator and the discriminator is established.

Synthetically generating medical images using deep convolutional generative adversarial networks

Communication systems and methods in accordance with various embodiments of the invention utilize modulation on zeros. Carrier frequency offsets (CFO) can result in an unknown rotation of all zeros of a received signal's z-transform. Therefore, a binary MOCZ scheme (BMOCZ) can be utilized in which the modulated binary data is encoded using a cycling register code (e.g. CPC or ACPC), enabling receivers to determine cyclic shifts in the BMOCZ symbol resulting from a CFO. Receivers in accordance with several embodiments of the invention include decoders capable of decoding information bits from received discrete-time baseband signals by: estimating a timing offset for the received signal; determining a plurality of zeros of a z-transform of the received symbol; identifying zeros from the plurality of zeros that encode received bits by correcting fractional rotations resulting from the CFO; and decoding information bits based upon the received bits using a cycling register code.

Systems and methods for communicating by modulating data on zeros in the presence of channel impairments

Devices, systems and methods related to techniques for performing four-chamber segmentation of echocardiograms are disclosed. In one example aspect, a method for generating segmented image data based on an input echocardiogram includes receiving an input echocardiogram that includes information associated with four chambers of a heart, performing segmentation on the information associated with the four chambers using an adversarial model that comprises a first artificial neural network with multiple layers, and combining data from selected layers of the first artificial neural network to generate an output image that includes the segmented four chambers of the heart.

Fully automated four-chamber segmentation of echocardiograms

Methods and devices are provided for error correction of distributed data in distributed systems using Reed-Solomon codes. In one embodiment, processes are provided for error correction that include receiving a first correction code for data fragments stored in storage nodes, constructing a second correction code responsive to an unavailable storage node of the storage nodes, performing erasure repair of the unavailable storage node, and outputting a corrected data fragment. The first correction code is a Reed-Solomon code represented as a polynomial and the second correction code is represented as a second polynomial with an increased subpacketization size. Processes are configured to account for repair bandwidth and sub-packetization size. Code constructions and repair schemes accommodate different sizes of evaluation points and provide a flexible tradeoff between the subpacketization size repair bandwidth of codes. In addition, schemes are provided to manage a single node failure and multiple node failures.

Method and system for repairing Reed-Solomon codes

A method of detecting whether or not a body chamber has an abnormal structure or function including: (a) providing a stack of images as input to a system comprising one or more hardware processors configured to obtain a stack of medical images comprising at least a representation of the body chamber inside the patient; to obtain a region of interest using a convolutional network trained to locate the body chamber, wherein the region of interest corresponds to the body chamber from each of the medical images; and to infer a shape of the body chamber using a stacked auto-encoder (AE) network trained to delineate the body chamber, wherein the AE network segments the body chamber; (b) operating the system to detect the body chamber in the images using deep convolutional networks trained to locate the body chamber, to infer a shape of the body chamber using a stacked auto-encoder trained to delineate the body chamber, and to incorporate the inferred shape into a deformable model for segmentation; and (c) detecting whether or not the body chamber has an abnormal structure, wherein an abnormal structure is indicated by a body chamber clinical indicia that is different from a corresponding known standard clinical indicia for the body chamber.

Automated segmentation of organ chambers using deep learning methods from medical imaging

Systems and methods are disclosed for automatically segmenting a heart chamber from medical images of a patient. The system may include one or more hardware processors configured to: obtain image data including at least a representation of the patient's heart; obtain a region of interest from the image data; organize the region of interest into an input vector; apply the input vector through a trained graph; obtain an output vector representing a refined region of interest corresponding to the heart based on the application of the input vector through the trained graph; apply a deformable model on the obtained output vector representing the refined region of interest; and identify a segment of a heart chamber from the application of the deformable model on the obtained output vector.

A wireless system, and particularly, a multiple-input multiple-output (MIMO) wireless communication system is disclosed. The wireless system includes a plurality of (re)configurable antennas and a rate-two space coding design for a MIMO system. The MIMO wireless communication system generally includes M (re)configurable antennas configured to independently transmit or broadcast wireless electromagnetic signals having a frequency in the microwave and/or optical ranges, a controller configured to control the (re)configurable antennas, and an encoder configured to encode information onto the wireless electromagnetic signals. The information comprises codewords having N symbols, and the codewords are expressed in an N&#xd7;M matrix having a non-zero determinant and in which at least one symbol is associated with a coefficient configured to maximize diversity, maximize coding gain and/or reduce channel fading in the MIMO wireless communication system. M and N are each independently an integer of at least 2.

System for resolving channel sparsity in multiple-input multiple-output systems using (re)configurable antennas, and methods of making and using the same

An apparatus or method for minimizing the total accessing cost, such as minimizing repair bandwidth, delay or the number of hops including the steps of minimizing the number of nodes to be engaged for the recovery process using a polynomial-time solution that determines the optimal number of participating nodes and the optimal set of nodes to be engaged for recovering lost data, where in a distributed database storage system, for example a dynamic system, where the accessing cost or even the number of available nodes are subject to change results in different values for the optimal number of participating nodes. An MDS code is included which can be reused when the number of participating nodes varies without having to change the entire code structure and the content of the nodes.

Cost-efficient repair for storage systems using progressive engagement

A method includes the step of interleaving training and feedback stages in a transmitter and a multiplicity of antennas, wherein the transmitter trains the corresponding ones of the multiplicity of antennas one by one and receives feedback information after training each one of the corresponding ones of the multiplicity of antennas. An apparatus operating using the method includes a multiple-input single-output system with t transmitter antennas, a short-term power constraint P, and target data rate &#x3c1; where for any t, the same outage probability as a system with perfect transmitter and receiver channel state information is achieved with a feedback rate of Rbits per channel state and via training Rtransmitter antennas on average, where Rand Rare independent of t, and depend only on &#x3c1; and P.

Interleaved training and limited feedback for multiple-antenna systems

The disclosure relates to a method of automatically producing a three-dimensional (3D) segmentation of a heart chamber, the method comprising: obtaining data sets from cardiac magnetic resonance imaging (MRI) or ultrasound, generating a 3D segmentation of the heart chamber from the data sets using an active contour method, modifying the 3D segmentation by adding a plurality of intra-chamber structures; and identifying an enclosing myocardium using the 3D segmentation generated by the method.

Automated 3D reconstruction of the cardiac chambers from MRI or ultrasound

An encoder includes a controller to determine whether macroblocks of a frame of video content are to be processed by intra-frame encoding or by predictive coding. The encoder includes a switch coupled to the controller. The encoder includes an intra-frame unit to receive the macroblocks via the switch when the controller determines to process the macroblocks by intra-frame encoding. The encoder includes a predictive unit to receive the macroblocks via the switch when the controller determines to process the macroblocks by predictive encoding. The encoder also includes a redundancy allocation unit coupled to the controller. The controller determines whether to process the macroblocks by intra-frame encoding or predictive frame encoding based on information received from the redundancy allocation unit.

Growing community of inventors

Irvine, CA, United States of America

Hamid Jafarkhani