Technology | Treatment Planning | December 27, 2018

RayStation 8B Released With Machine Learning Applications for Treatment Planning

New features allow automated treatment planning and organ segmentation

RayStation 8B Released With Machine Learning Applications for Treatment Planning

December 27, 2018 — RaySearch Laboratories released RayStation 8B, the latest version of the radiation therapy treatment planning system (TPS), with new advances including some automation applications using machine learning and deep learning. Other major news in RayStation 8B include a new module for evaluation of robustness of treatment plans and photon Monte Carlo dose.

Machine learning means that the algorithms in these features learn from the data they are trained on, and they learn in a way that resembles human logic. The applications for automated treatment planning and automated organ segmentation will help improve efficiency and consistency in the clinic. The machine learning framework delivered with RayStation 8B allows for models to be trained on the clinic’s available data, and it is also possible to use pre-trained models provided by RaySearch.

The new features have been developed by RaySearch’s in-house machine learning department in collaboration with Princess Margaret Cancer Centre in Toronto, Canada, and are the first machine learning applications in a TPS on the radiation oncology market today, according to the company.

Robust evaluation is a new module in Plan Evaluation, which enables efficient evaluation of robustness of treatment plans with respect to uncertainties in patient setup and density interpretation of computed tomography (CT). Multiple scenarios with different uncertainty settings are easily created and the scenarios can be evaluated simultaneously for quick decision support. This is achieved through display of different robustness metrics connected to the clinical goals of the treatment.

Improvements for photon planning include a Monte Carlo dose engine. The Monte Carlo dose algorithm brings improved accuracy and it is utilizing the graphics processing unit (GPU) to enable fast dose computation. The dose for a dual arc volumetric modulated arc therapy (VMAT) plan can be computed in less than 60 seconds, which is at least one order of magnitude faster than any other system on the market, according to RaySearch. The Monte Carlo dose engine can be used also during optimization.

Boron neutron capture therapy (BNCT) planning has been under development since 2017 and is now available in RayStation 8B. BNCT is a type of radiation therapy that enables targeting of cancer at the cellular level. BNCT planning in RayStation is developed together with Sumitomo Heavy Industries Ltd and Neutron Therapeutics Inc.

RayStation 8B also adds various improvements and enhancements, including support for directly deliverable multicriteria optimization (MCO) for VMAT, collimation of individual energy layers with the Adaptive Aperture of the Mevion S250i Hyperscan proton therapy system, and handling of relative biological effectiveness for proton dose.

For more information: www.raysearchlabs.com

Related Content

Black Men Less Likely to Adopt Active Surveillance for Low-Risk Prostate Cancer
News | Prostate Cancer | June 17, 2019
A new study reveals black men are less likely than white men to adopt an active surveillance strategy for their...
University Medical Center Groningen Performs First Automatic Log-based Proton Therapy Patient QA
News | Proton Therapy | June 14, 2019
IBA announced the physics team of University Medical Center Groningen (UMCG) in the Netherlands has developed and...
M*Modal and Community Health Network Partner on AI-powered Clinical Documentation
News | PACS Accessories | June 13, 2019
M*Modal announced that the company and Community Health Network (CHNw) are collaborating to transform the patient-...
iCAD Introduces ProFound AI for 2D Mammography in Europe
News | Artificial Intelligence | June 13, 2019
iCAD Inc. announced the launch of ProFound AI for 2D Mammography in Europe. This software is the latest addition to...
The Current Direction of Healthcare Reform Explained by CMS Administrator Seema Verma
News | Radiology Business | June 11, 2019
June 11, 2019 — Centers for Medicare and Medicaid Services (CMS) Administrator Seema Verma addressed the American Med
Aidoc Earns FDA Approval for AI for C-spine Fractures
Technology | Artificial Intelligence | June 11, 2019
Radiology artificial intelligence (AI) provider Aidoc announced the U.S. Food and Drug Administration (FDA) has cleared...
Medivis SurgicalAR Gets FDA Clearance
Technology | Virtual and Augmented Reality | June 10, 2019
Medivis announced that its augmented reality (AR) technology platform for surgical applications, SurgicalAR, has...
Glassbeam Announces New Clinsights Application Suite for Healthcare Provider Market
Technology | Analytics Software | June 10, 2019
Glassbeam launched Clinsights, a new revitalized application suite powered by artificial intelligence/machine learning...
The DeepAAA algorithm, developed at the MGH & BWH Center for Clinical Data Science, accurately detected and measured an abdominal aortic aneurysm (AAA) in a CT image even though appearance of the AAA was complicated by a blood clot

The DeepAAA algorithm, developed at the MGH & BWH Center for Clinical Data Science, accurately detected and measured an abdominal aortic aneurysm (AAA) in a CT image even though appearance of the AAA was complicated by a blood clot. (The algorithm drew a green circle around the aneurysm.) Image courtesy of Varun Buch, MGH & BWH Center for Clinical Data Science

Feature | Artificial Intelligence | June 10, 2019 | By Greg Freiherr
Editor’s note: This article is the second in a content series by Greg Freiherr covering the ...
ASTRO Applauds New Prior Authorization Legislation
News | Radiation Therapy | June 07, 2019
The American Society for Radiation Oncology (ASTRO) released a statement applauding Congress’s introduction of...