Varian Medical Systems International Ag

Varian Medical Systems, Inc.

Siemens Healthineers International Ag

Joakim Pyyry

Janne Iimari Nord

Esa Kuusela

Jarkko Yriana Peltola

Benjamin M Haas

Perttu Niemela

Pascal Paysan

Sami Petri Perttu

Dieter Marc Seghers

Martin Sabel

Adam Scott Harrington

Dominique Gasser

Corey Zankowski

Reto W Filiberti

Charles Adelsheim

Sylvie Spiessens

Joseph Schumm

Roland Meier

Sean Herries

Kari Jyrkkälä

Juha Kauppinen

Hannu Laaksonen

Stefan J Thieme-Marti

Andres Graf

Ramin Baghaie

Perttu Niemelä

Agam Sharda

Jukka Suominen

Mika Miettinen

Wayne Keranen

Jeff Everett

William Kearns

Aleksi Nurmi

Janne Sauvala

Seppo Tuomaala

Perttu Niemelae

A method of generating a treatment plan for treating a patient with radiotherapy, the method includes obtaining a plurality of sample plans, which are generated by use of a knowledge base comprising historical treatment plans and patient data. The method also includes performing a multi-criteria optimization based on the plurality of sample plans to construct a Pareto frontier, where the plurality of sample plans are evaluated with at least two objectives measuring qualities of the plurality of sample plans such that treatment plans on the constructed Pareto frontier are Pareto optimal with respect to the objectives. The method further includes identifying a treatment plan by use of the constructed Pareto frontier.

Knowledge based multi-criteria optimization for radiotherapy treatment planning

An apparatus for treatment planning and/or treatment setup includes: a simulator configured to obtain a first model representing a first component of a medical system, and virtually move the first model to simulate a movement of the first component of the medical system; an analyzer configured to determine imaging waypoints during a treatment process based on the virtual movement of the first model; and a graphic generator configured to generate a graphic based on the determined imaging waypoints.

Imaging waypoints for radiation treatment

Example methods and systems for tomographic data analysis are provided. One example method may comprise: obtaining first three-dimensional (3D) feature volume data and processing the first 3D feature volume data using an AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers, transforming the second 3D volume data into 2D feature data using the forward-projection module and generating analysis output data by processing the 2D feature data using the multiple second processing layers.

Tomographic image analysis using artificial intelligence (AI) engines

Solutions are provided herein that specifically accounts for biological effects of tissue during radiation planning (such as treatment planning). In one or more embodiments, the biological effects may be calculated by accessing a knowledge base to determine reference data comprising at least one biological characteristic corresponding to the at least one organ, predicting a biological effect for the plurality of identified structures based on the biological characteristic corresponding to the at least one organ, and generating or modifying a radiation plan based on the biological effect. By incorporating biological data and fraction dose information, dose-estimation models can be created and trained to more accurately estimate dose absorption and effectiveness. Moreover, existing estimation models may be adapted to create dose estimations that account for the biological efficiency of target structures.

Knowledge based treatment planning corrected for biological effects

Example methods and systems for tomographic image reconstruction are provided. One example method may comprise: obtaining two-dimensional (2D) projection data and processing the 2D projection data using the AI engine that includes multiple first processing layers, an interposing back-projection module and multiple second processing layers. Example processing using the AI engine may involve: generating 2D feature data by processing the 2D projection data using the multiple first processing layers, reconstructing first three-dimensional (3D) feature volume data from the 2D feature data using the back-projection module; and generating second 3D feature volume data by processing the first 3D feature volume data using the multiple second processing layers.

Tomographic image reconstruction using artificial intelligence (AI) engines

An apparatus for creating a radiation treatment plan for execution by a radiation treatment machine, includes: a waypoint module configured to obtain imaging waypoint data representing imaging waypoints, the imaging waypoints at least partially defining one or more positions for obtaining images of a patient during a treatment session; a treatment trajectory module configured to obtain treatment data at least partially defining a beam-on direction; a treatment plan generator configured to create the radiation treatment plan based at least in part on the imaging waypoint data and the treatment data.

Systems and methods for planning and executing automated multi-axis motion in treatment

Example methods and systems for radiotherapy treatment planning are provided. One example method may comprise obtaining image data associated with a patient; and processing the image data to generate a treatment plan for the patient using an inferential chain that includes multiple AI engines that are trained separately to perform respective multiple treatment planning steps. A first treatment planning step may be performed using a first AI engine to generate first output data based on at least one of: (i) the image data, and (ii) first input data generated based on the image data. A second treatment planning step may be performed using a second AI engine to generate the treatment plan based on at least one of: (i) the first output data, and (ii) second input data generated based on the first output data.

Radiotherapy treatment planning using artificial intelligence (AI) engines

A clinical goal for radiation treatment of a patient is set. A dose prediction model is selected from a number of dose prediction models based on the clinical goal. A radiation treatment plan is then generated for the patient using the dose prediction model that was selected based on the clinical goal.

Selecting a dose prediction model based on clinical goals

Example methods and systems for generating an aggregated artificial intelligence (AI) engine for radiotherapy treatment planning are provided. One example method may include obtaining multiple AI engines associated with respective multiple treatment planners; generating multiple sets of output data using the multiple AI engines associated with the respective multiple treatment planners: comparing the multiple AI engines associated with the respective multiple treatment planners based on the multiple sets of output data; and based on the comparison, aggregating at least some of the multiple AI engines to generate the aggregated AI engine for performing the particular treatment planning step. The multiple AI engines may be trained to perform a particular treatment planning step, and each of the multiple AI engines is trained to emulate one of the multiple treatment planners performing the particular treatment planning step.

Aggregation of artificial intelligence (AI) engines

A radiation-treatment plan to treat a treatment target in a given patient takes into account imaging-based dosing of that patient by, for example, automatically accounting for radiation dosing of the given patient that results from imaging to determine at least one physical position of the given patient when forming the radiation-treatment plan. These teachings are particularly beneficial when applied in application settings where the aforementioned imaging comprises obtaining images using megavoltage-sourced radiation. By one approach these teachings provide for automatically accounting for radiation dosing of the given patient that results from imaging by, at least in part, automatically adjusting therapeutic dosing of the given patient as a function of the radiation dosing of the given patient that results from such imaging.

Accounting for imaging-based radiation doses

A control circuit uses a (possibly self-generated) seed radiation treatment plan to identify a portion (possibly only a point) of a multi-criteria optimization (MCO)-based Pareto surface. The control circuit then selects a sampling plan set for MCO planning by enlarging that portion of the Pareto surface region to thereby facilitate developing an optimized radiation treatment plan. A radiation treatment platform then uses that optimized radiation treatment plan to treat a patient by administering the radiation in accordance with the plan.

Therapeutic radiation treatment

Collision free regions are predetermined for one or more class solutions. Each class solution has defined limits for allowed field geometry variations. Collision free regions in planning can be defined as a set of allowed isocenter positions relative to a fixation device. The collision free regions may be visualized by a user to plan for field geometry and isocenter position tradeoffs. Collision free regions in delivery can be defined as a set of allowed couch support coordinates. The treatment fields in a radiation treatment plan can be checked against the collision free regions in delivery to determine whether they will pose any collision risks.

Radiation treatment planning and delivery using collision free regions

A system generally includes at least one computing device having a user interface and a display interface. The computing device is configured to generate at least one desktop that can be viewed by a user via the display interface and to access a plurality of functionality modules that are each configured to receive at least one radiotherapy parameter. The computing device is configured to enable the user, via the user interface, to place the functionality modules onto the desktop. The computing device is configured to enable the user, via the user interface, to connect one of the placed functionality modules to at least another one to commence the generation of at least one workflow output. The computing device is also configured to enable the user, via the user interface, to connect a plurality of input components to the placed functionality modules to finalize the generation of the workflow output.

Systems and methods for generating workflow outputs

Growing community of inventors

Helsinki, Finland

Joakim Pyyry