University of California

Jonathan Goldin

Matthew S Brown

Hyun J Kim

Bharath Ramakrishna

Pechin Lo

Dieter R Enzmann

Yu Shi

Weng Kee Wong

Xiaoyong Wang

Eva Marjolein Van Rikxoort

A method for training a machine learning algorithm that classifies predictive regions-of interest ('ROI') of progression of idiopathic pulmonary fibrosis. The method includes acquiring a set of computed tomography (CT) images of a plurality of patients and selecting a plurality of ROIs within the set of images. Each of the ROIs designates a label that indicates progression of pulmonary fibrosis and training a machine learning algorithm by inputting the plurality of ROIs and the associated labels into the algorithm. The algorithm identifies the ROIs in the set of images as indicating regions of pulmonary fibrosis within the set of images based on the features.

System and method for prediction of disease progression of pulmonary fibrosis using medical images

A method for using machine learning to perform classification of anatomical coverage of images includes acquiring a series of medical images of a subject. The method also includes automatically, with a computer system, analyzing each image in the series of medical images using a machine-learning technique to classify each image in the series of medical images based on anatomical structures reflected in each image in the series of medical images.

System and method for improved medical images

Automated image analysis systems and methods are disclosed to quantify change in fibrosis and interstitial lung disease. The system generates scoring changes in Quantitative Interstitial Lung Disease (QILD) by filtering the uploaded images to minimize cross-site variability within images, sampling from a grid of pixels or voxels within the CT images, classifying individual pixels or voxels within downloaded images based on one or more selected texture features, generating a QILD score for each image based on selected features within the image, and calculating a transition between QILD scores within the plurality of CT images.

Automated image system for scoring changes in quantitative interstitial lung disease

A computer aided detection (CAD) method and system is configured to input chest radiographs and generate overlay layer for labeling and tracing tubes detected within the image. The input image is first preprocessed and then segmented according to anatomy. Seeds are generated from the segmented image and then used to grow the region. Tubes are selected from the grown region and data is overlayed on the image based on the grown seed path.

Methods and apparatus for computer-aided radiological detection and imaging

An automated or semi-automated system and methods are disclosed that provide a rapid and repeatable method for identifying lung, lobe, and fissure voxels in CT images, and allowing for quantitative lung assessment and fissure integrity analysis. An automated or semi-automated segmentation and editing system and methods are also disclosed for lung segmentation and identification of lung fissures.

Growing community of inventors

Los Angeles, CA, United States of America

Jonathan Goldin