Brian Wang

US Patent:

7450687, Nov 11, 2008

Filed:

Sep 29, 2006

Appl. No.:

11/529906

Inventors:

Inhwan Yeo - Voorhees NJ, US
Brian Wang - Merchantville NJ, US

Assignee:

University of Medicine and Dentistry of New Jersey - New Brunswick NJ

International Classification:

A61N 5/10

US Classification:

378 65

Abstract:

An accurate method for inversely verifying a therapeutic radiation dose delivered to a patient via an x-ray delivery system without involving any computational iteration was developed. The usage of it includes detecting the transmitted radiation dose image after passage through the patient, imaging the patient during treatment to anatomically record information of the patient, followed by inversely verifying through use of both the detected radiation image and the imaging data, the actual radiation dose delivered to the patient, and comparing the level of the dose delivered to a previously planned dose to determine whether the planned dose was delivered, or whether an overdose or underdose occurred.

US Patent:

20120201428, Aug 9, 2012

Filed:

Jun 30, 2010

Appl. No.:

13/381206

Inventors:

Sarang Joshi - Salt Lake City UT, US
Jacob Hinkle - Salt lake city UT, US
Bill Salter - Salt lake City UT, US
Tom Fletcher - Salt lake City UT, US
Brian Wang - Salt lake City UT, US

Assignee:

University of Utah Research Foundation - Salt Lake City UT

International Classification:

G06K 9/00

US Classification:

382107

Abstract:

Systems and methods which implement an image reconstruction framework to incorporate complex motion of structure, such as complex deformation of an object or objects being imaged, in image reconstruction techniques are shown. For example, techniques are provided for tracking organ motion which uses raw time-stamped data provided by any of a number of imaging modalities and simultaneously reconstructs images and estimates deformations in anatomy. Operation according to embodiments reduces artifacts, increase the signal-to-noise ratio (SNR), and facilitates reduced image modality energy dosing to patients. The technology also facilitates the incorporation of physical properties of organ motion, such as the conservation of local tissue volume. This approach is accurate and robust against noise and irregular breathing for tracking organ motion.

US Patent:

20180070905, Mar 15, 2018

Filed:

Sep 14, 2017

Appl. No.:

15/704719

Inventors:

- Louisville KY, US
Ahmed Soliman - Louisville KY, US
Fahmi Khalifa - Louisville KY, US
Ahmed Shaffie - Louisville KY, US
Neal Dunlap - Louisville KY, US
Brian Wang - Louisville KY, US

International Classification:

A61B 6/00
A61B 6/03
A61N 5/10
G06T 7/33
G06T 7/149
G06T 7/143
G06T 7/174
G06T 7/38
G06T 7/246

Abstract:

A system and computation method is disclosed that identifies radiation-induced lung injury after radiation therapy using 4D computed tomography (CT) scans. After deformable image registration, the method segments lung fields, extracts functional and textural features, and classifies lung tissues. The deformable registration locally aligns consecutive phases of the respiratory cycle using gradient descent minimization of the conventional dissimilarity metric. Then an adaptive shape prior, a first-order intensity model, and a second-order lung tissues homogeneity descriptor are integrated to segment the lung fields. In addition to common lung functionality features, such as ventilation and elasticity, specific regional textural features are estimated by modeling the segmented images as samples of a novel 7-order contrast-offset-invariant Markov-Gibbs random field (MGRF). Finally, a tissue classifier is applied to distinguish between the injured and normal lung tissues.