The University of Texas System

Steve B Jiang

Weiguo Lu

Robert Timmerman

Mingli Chen

Dan Nguyen

Hak Choy

Xuejun Gu

Arnold Pompos

Troy Long

Xun Jia

Vasant Kearney

Kenneth Dale Westover

Azar Sadeghnejad Barkousaraie

Jun Tan

Tsuicheng D Chiu

Bo Zhao

Ko-ay Timmy Siauw

Tobin Strom

A method and system for generating a treatment plan are disclosed herein. A computing system receives a plurality of dose volume histograms for a plurality of patients and a plurality of volumetric dose distributions corresponding to the plurality of dose volume histograms. The computing system generates a volumetric dose prediction model using a neural network by learning, by the neural network, a relationship between a plurality of dose volume histograms for the plurality of patients and the corresponding plurality of volumetric dose distributions. The computing system receives a candidate dose volume histogram for a target patient. The computing system infers, via the volumetric dose prediction module, a volumetric dose prediction distribution matching the candidate dose volume histogram. The computing system generates a recommendation based on the inferred volumetric dose prediction distribution.

Deep learning based dosed prediction for treatment planning and quality assurance in radiation therapy

The present disclosure is directed towards a treatment planning system for use in a stereotactic radiotherapy system. In particular, the disclosed systems and methods may be used for generating a treatment plan and/or verifying an existing treatment plan. Moreover, the disclosed systems and methods may be suitable for use in a clinical setting. A method for verifying a treatment plan of a stereotactic radiotherapy device may include the steps of receiving a treatment plan, generating a second treatment plan by applying a modified monte-carlo method to regions of interest in the treatment plan, and identifying discrepancies between the received treatment plan and the generated second treatment plan.

Independent stereotactic radiotherapy dose calculation and treatment plan verification

A method for determining a radiotherapy treatment plan can include: receiving anatomical data for a patient; generating, via a neural network analyzing the anatomical data, a plurality of fitness values for a plurality of candidate beam orientations; determining a selected beam orientation based on the plurality of fitness values; performing a fluence map optimization (FMO) process on the selected beam orientation; and determining a dose distribution for the patient based on the FMO process.

Beam selection for radiotherapy

A method and system for generating a voxel-based quadratic penalty model for automatic intensity modulated radiation therapy (IMRT) treatment planning are disclosed herein. A computing system generates an initial assignment of threshold values to a penalty function for IMRT treatment planning. The computing system receives an update to a dose value associated with the IMRT treatment planning. The computing system dynamically updates the threshold values based on the updated dose value. The computing system continues to iterate the threshold values based on further updated dose values.

Dose volume histogram and dose distribution based autoplanning

Systems, methods, and computer-readable storage media providing techniques for probing in-vivo beam ranges directly using therapeutic beams for particle therapy treatment are disclosed. In an embodiment, a configuration is determined for one or more probing spots, each spot corresponding to a planned location within an interior region of a tumor volume where a dose of radiation is to be delivered. At least one therapeutic beam is provided to the tumor volume, and one or more images may be captured to provide an indication of the range/depth of the probing spots. Providing the probing spots to the interior of the tumor volume reduces the risk that the dose is provided to sensitive tissue (e.g., because even if the dose is delivered to a location other than the planned location, the dose is likely to remain contained within the tumor volume).

Mid-plane range-probing techniques for particle therapy

A cloud-based radiation therapy treatment planning system (TPS). The TPS changes the clinical workflow of the radiotherapy treatment planning process, by increasing the mobility and computational power of the treatment planning software and hardware architecture. The system is divided into computational components. A user device includes a light and flexible user interface, while the server side entails a hospital relay server, and/or a graphics processing unit cluster server. The TPS computational architecture enables the computational power of a GPU-cluster server on a tablet, laptop, or smartphone.

Systems and methods for cloud-based radiation therapy treatment planning

Methods, apparatuses, systems, and implementations for creating a patient-specific soft bolus for radiotherapy treatment are disclosed. 2D and/or 3D images of a desired radiotherapy treatment site may be acquired, such as the head, neck, skin, breast, anus, and/or vulva. A user may interact with one or more representations of the images via an interactive user interface such as a graphical user interface (GUI). The images may include target/avoidance structures and radiation beam arrangement. The user may interact with the images to create a visualization of a patient-specific bolus. The visualization and properties of the bolus may be modified as the user manipulates aspects of the image. Data corresponding to the bolus models may be used to create 3D printed negative molds of the bolus model using 3D printing technology. A soft patient-specific bolus may be cast using the 3D printed model.

Methods, apparatuses, and systems for creating a patient-specific soft bolus for radiotherapy treatment

Radiation therapy systems and their components, including secondary radiation shields. At least some versions of the disclosed systems combine a radiation delivery device, a primary radiation shielding device, and a secondary shielding layer into an integrated, modular unit. This is accomplished by using a small direct beam shield capable of blocking a primary beam from a radiation delivery device. In turn, a thinner shielding layer can be used to surround the radiation delivery device and primary shielding device, enabling a single modular unit to be delivered to an installation site. In some embodiments, a bed may be disposed within the secondary shielding layer. In some embodiments, the system is configured to provide up to 4-pi (4&#x3c0;) steradians of radiation coverage to the bed from the radiation delivery device.

Growing community of inventors

Dallas, TX, United States of America

Steve B Jiang