Arterys Inc.

John Axerio-Cilies

Torin Arni Taerum

Darryl Bidulock

Hussein Patni

Kyle Dormer

Daniel Irving Golden

Jesse Lieman-Sifry

Matthieu Le

Hok Kan Lau

Sean Patrick Sall

Matthew Joseph Didonato

Shek Bun Law

Fabien Rafael David Beckers

Albert Hsiao

Robert George Newton

Carla Leibowitz

Angélique Sophie Calmon

Giovanni De Francesco

Fabien Beckers

Daniel Marc Raymond Beauchamp

Anitha Priya Krishnan

Berk Dell Norman

Maud Josee Caroline Benaddi

Patrick Ross Corless

Justin Reid

Derek John Scherger

Kendall Wu

Tristan Jugdev

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are commonly used to assess patients with known or suspected pathologies of the lungs and liver. In particular, identification and quantification of possibly malignant regions identified in these high-resolution images is essential for accurate and timely diagnosis. However, careful quantitative assessment of lung and liver lesions is tedious and time consuming. This disclosure describes an automated end-to-end pipeline for accurate lesion detection and segmentation.

Content based image retrieval for lesion analysis

An MRI image processing and analysis system may identify instances of structure in MRI flow data, e.g., coherency, derive contours and/or clinical markers based on the identified structures. The system may be remotely located from one or more MRI acquisition systems, and perform: error detection and/or correction on MRI data sets (e.g., phase error correction, phase aliasing, signal unwrapping, and/or on other artifacts); segmentation; visualization of flow (e.g., velocity, arterial versus venous flow, shunts) superimposed on anatomical structure, quantification; verification; and/or generation of patient specific 4-D flow protocols. A protected health information (PHI) service is provided which de-identifies medical study data and allows medical providers to control PHI data, and uploads the de-identified data to an analytics service provider (ASP) system. A web application is provided which merges the PHI data with the de-identified data while keeping control of the PHI data with the medical provider.

Medical imaging and efficient sharing of medical imaging information

This disclosure relates to a medical image viewer for incorporating multi-user collaboration features, such as in-image commenting and workspace sharing. An example method includes receiving a comment location including image coordinates and comment information associated with the comment from a user device. The comment information includes a text body, identify identity information related to the user, and a comment creation date. The example method further includes determining world coordinates based on the image coordinates, and storing the world coordinates and the comment information as a subset of header attributes of the DICOM image file.

Cloud-based radiology commenting and workspace sharing

Systems and methods for providing a novel framework to simulate the appearance of pathology on patients who otherwise lack that pathology. The systems and methods include a 'simulator' that is a generative adversarial network (GAN). Rather than generating images from scratch, the systems and methods discussed herein simulate the addition of diseases-like appearance on existing scans of healthy patients. Focusing on simulating added abnormalities, as opposed to simulating an entire image, significantly reduces the difficulty of training GANs and produces results that more closely resemble actual, unmodified images. In at least some implementations, multiple GANs are used to simulate pathological tissues on scans of healthy patients to artificially increase the amount of available scans with abnormalities to address the issue of data imbalance with rare pathologies.

Simulating abnormalities in medical images with generative adversarial networks

Systems and methods for automated segmentation of anatomical structures, such as the human heart. The systems and methods employ convolutional neural networks (CNNs) to autonomously segment various parts of an anatomical structure represented by image data, such as 3D MRI data. The convolutional neural network utilizes two paths, a contracting path which includes convolution/pooling layers, and an expanding path which includes upsampling/convolution layers. The loss function used to validate the CNN model may specifically account for missing data, which allows for use of a larger training set. The CNN model may utilize multi-dimensional kernels (e.g., 2D, 3D, 4D, 6D), and may include various channels which encode spatial data, time data, flow data, etc. The systems and methods of the present disclosure also utilize CNNs to provide automated detection and display of landmarks in images of anatomical structures.

Automated cardiac volume segmentation

An MRI image processing and analysis system may identify instances of structure in MRI flow data, e.g., coherency, derive contours and/or clinical markers based on the identified structures. The system may be remotely located from one or more MRI acquisition systems, and perform: perform error detection and/or correction on MRI data sets (e.g., phase error correction, phase aliasing, signal unwrapping, and/or on other artifacts); segmentation; visualization of flow (e.g., velocity, arterial versus venous flow, shunts) superimposed on anatomical structure, quantification; verification; and/or generation of patient specific 4-D flow protocols. An asynchronous command and imaging pipeline allows remote image processing and analysis in a timely and secure manner even with complicated or large 4-D flow MRI data sets.

Apparatus, methods and articles for four dimensional (4D) flow magnetic resonance imaging

Apparatus, methods and articles for four dimensional (4D) flow magnetic resonance imaging using coherency identification for magnetic resonance imaging flow data

Growing community of inventors

San Francisco, CA, United States of America

John Axerio-Cilies