Washington University

University of California

Varian Medical Systems, Inc.

Washing University

Sasa Mutic

Todd Pawlicki

Sridhar Yaddanapudi

Sreekrishna M Goddu

Hua Li

Michael Altman

James Kavanaugh

Corey Zankowski

Ryan Scott Brame

Hsin-Chen Chen

Jun Tan

Kevin L Moore

Lindsey Appenzoller

Olga Green

Mark Anastasio

Tiezhi Zhang

Chunjoo Park

Hasani Wooten

Chunjoo (Justin) Park

Hao Zhang

Bin Cai

Tianyu Zhao

Disclosed herein is a method for deforming patient images obtained with a couch of one set of physical properties (e.g. curvature) based on the physical properties (e.g. curvature) of a couch where radiation therapy treatment will be performed. Also disclosed herein is a radiotherapy delivery system which includes a non-flat couch top, on-couch planning, and optional deformable image registration. The methods and systems use images from scanners of various couch top shapes for treatment of radiotherapy patients without a need for specialized treatment planning imaging. In such methods and systems, treatment delivery can be performed based on only diagnostic images and setup images acquired at the time of treatment on the treatment machine. The radiotherapy delivery systems can include any combination of volumetric imaging with radiotherapy treatments with photon, proton, electron, and\or other particle radiation.

Image deformation methods and curved couch for radiotherapy treatment planning

An apparatus includes a first multileaf collimator comprising a plurality of pairs of beam-blocking leaves each comprising an end portion. The end portions of beam-blocking leaves of two adjacent pairs are configured to collectively form an aperture when the two adjacent pairs of beam-blocking leaves are closed. The aperture may be sized and shaped to allow a radiation beam to pass through for radiosurgery.

Multileaf collimator cone enabling stereotactic radiosurgery

A computer-implemented method for correcting artifacts within CT images of a subject includes providing iteratively correcting a CT volumetric image with a high-contrast mask by overpainting the high-contrast mask within CT volumetric image set by evaluating a model function and updating the CT projections to reflect the overpainting using a gradient descent based on previous overpainted CT projections, back-projecting the corrected CT projections to produce a corrected volumetric image set, and comparing the corrected CT volumetric image set against a previous corrected CT volumetric image set until convergence. The original voxels overpainted by the high-contrast mask are re-inserted into the converged CT volumetric image to produce the final CT volumetric image set.

Methods of image reconstruction to reduce artifacts in rapid CBCT scans

The present invention is a method or system for acceptance testing and commissioning of a LINAC and treatment planning system (TPS). For a LINAC commissioning, the present invention collects reference data from a fully calibrated LINAC and compares the reference data with machine performance data collected from LINAC. The compared results are analyzed to assess accuracy of the testing LINAC. For a TPS commissioning, the present invention collects standard reference data from standard treatment plans and standard input data and compares the standard reference data with results from standard tests that are performed by a testing treatment plan system. The compares results are analyzed to assess accuracy of the testing treatment plan system.

Acceptance, commissioning, and ongoing benchmarking of a linear accelerator (LINAC) using an electronic portal imaging device (EPID)

The present disclosure describes a computer-implemented method of transforming a low-resolution MR image to a high-resolution MR image using a deep CNN-based MRI SR network and a computer-implemented method of transforming an MR image to a pseudo-CT (sCT) image using a deep CNN-based sCT network. The present disclosure further describes a MR image-guided radiation treatment system that includes a computing device to implement the MRI SR and CT networks and to produce a radiation plan based in the resulting high resolution MR images and sCT images.

ML-based methods for pseudo-CT and HR MR image estimation

The present invention is a method or system for acceptance testing and commissioning of a LINAC and treatment planning system (TPS). For a LINAC commissioning, the present invention collects reference data from a fully calibrated LINAC and compares the reference data with machine performance data collected from a testing LINAC. The compared results are analyzed to assess accuracy of the testing LINAC. For a TPS commissioning, the present invention collects standard reference data from standard treatment plans and standard input data and compares the standard reference data with results from standard tests that are performed by a testing treatment plan system. The compares results are analyzed to assess accuracy of the testing treatment plan system.

A system and method for validating the accuracy of delineated contours in computerized imaging using statistical data for generating assessment criterion that define acceptable tolerances for delineated contours, with the statistical data being conditionally updated and/or refined between individual processes for validating delineated contours to thereby adjust the tolerances defined by the assessment criterion in the stored statistical data, such that the stored statistical data is more closely representative of a target population. In an alternative embodiment, a system and method for validating the accuracy of delineated contours in computerized imaging using machine learning for assessing delineated contours, with the machine learning training data being used to generate geometric attributes, and the geometric attributes used to construct intra- and interstructural geometric attribute distribution models to automatically detect contouring errors. The present invention may be used to facilitate, as one example, radiation therapy.

System and method for the validation and quality assurance of computerized contours of human anatomy

Embodiments develop a predictive dose-volume relationships for a radiation therapy treatment is provided. A system includes a memory area for storing data corresponding to a plurality of patients, wherein the data comprises a three-dimensional representation of the planning target volume and one or more organs-at-risk. The data further comprises an amount of radiation delivered to the planning target volume and the one or more organs-at-risk. The system further includes one or more processors programmed to access, from the memory area, the data and to develop a model that predicts dose-volume relationships using the three-dimensional representations of the planning target volume and the one or more organs-at-risk. The model is being derived from correlations between dose-volume relationships and calculated minimum distance vectors between discrete volume elements of the one or more organs-at-risk and a boundary surface of the planning target volume.

Developing predictive dose-volume relationships for a radiotherapy treatment

A system or method for radiation treatment optimized for non-coplanar delivery, which includes a first collimator affixed to a gantry and a second collimator movably attached to the gantry to provide the second collimator a translation movement out of a gantry rotation plane. The system or method also includes a third collimator configured to collimate the beam in a direction of a target in the patient's body. The beam collimated by the third collimator is configured to follow the target during treatment. A method of performing rotation setup correction by rotating the treatment beam, without rotating the patient.

System and method for radiation treatment optimized for non-coplanar delivery

A method for optimizing a CT simulation protocol for different size patients for contouring and segmentation of organs and tumors. The method scanning different size phantoms, cadavers, or patients with a CT scanning x-ray tube to create a set of images and to create data sets for each different size phantoms, cadavers, or patients and then calculating an image quality index (IQI) as a benchmark for contouring accuracy. Finding an optimal IQI that characterizes patients of different sizes and using the optimal IQI to determine the accuracy of the contouring and segmentation of A CT simulation protocol for a patient.

Growing community of inventors

St. Louis, MO, United States of America

Sasa Mutic