Mathisen & Macara LLP

A cryoprobe (300) includes a needle (304) defining an internal cavity, a cryogen conduit (308) positioned in the internal cavity, and a multi-filar heater (314) positioned radially outward of the cryogen conduit in the internal cavity configured to heat the needle to a predetermined temperature.

A linear accelerator for a radiation therapy system includes a plurality of cavities aligned along a length of the linac and a channel extending between adjacent cavities of the plurality of cavities. The plurality of cavities include a first material and the channel includes a second material different from the first material.

A cryoablation probe (200) includes a needle (202) forming an inner cavity. The needle includes at least one flow disruptor (206) positioned in the inner cavity. The cryoablation probe also includes a cryogen lumen (310) configured to deliver cryogen toward a distal end of the needle (204), wherein the at least one flow disruptor induces a turbulent flow of the cryogen in the inner cavity.

A method used for planning radiation treatment is disclosed. The method comprises, by a processor, accessing information comprising calculated dose and calculated linear energy transfer for a plurality of sub-volumes in a volume in a treatment target, and displaying, on a display device, an image of the treatment target overlayed with a rendering that is based on the calculated doses and the calculated linear energy transfer for the plurality of sub-volumes in the treatment target.

A cryoprobe (100) includes a shell (102) extending in an axial direction (120) and forming a needle for positioning at a target tissue and a tube (108) extending in the axial direction positioned radially inward of the shell (102). An inner surface of the shell (102) and the outer surface of the tube (108) define an insulating cavity (304) therebetween.

Disclosed herein are methods (200) and systems (100) for optimizing radiation therapy plans through a dual-model system, enhancing operational efficiency, effectiveness, and safety of machine learning models (111, 112) configured to generate radiotherapy treatment plans. Embodiments utilize a utility function to guide the optimization of treatment parameters, while an independent validation model (111) evaluates each iteration of the plan. The validation model (111) ensures that the treatment remains clinically viable by halting the optimization process (200) once the validation score ceases to improve, thereby preventing over-optimization. This approach allows for optimized treatment plans to be predicted by existing machine learning in a manner that is both theoretically ideal but also practically applicable and safe for patient treatment, addressing the critical need for reliability in radiation therapy planning.

Example methods and systems for image reconstruction using multiple image reconstruction chains for radiation therapy are described. In one example, a computer system may obtain projection image data 110 associated with a target structure within a patient. The computer system may generate, using a first image reconstruction chain 121, 122, 122N, first volume image data 131, 132, 132N based on the projection image data. The computer system may generate and display, on a display device, a first user interface (UI) 141 view for a user to interact with the first volume image data. The computer system may also generate, using a second image reconstruction chain, second volume image data based on at least one of the following: the projection image data and the first volume image data. The computer system may generate and display, on the display device, a second UI 142 view for the user to interact with the second volume image data.

A server (110a) monitors (202) a sequence of screen captures from a radiotherapy treatment planning platform's user interface, operated by medical professionals. The server (110a) generates (204) a training dataset comprising a time series of the screen captures and trains (206) a machine learning model using this dataset. The trained model is configured to predict (208) visual attributes of the user interface, determining the next screen's attributes based on prior interactions. When executed, the model predicts future visual attributes of the interface as a user interacts with the current screen, offering real-time guidance for navigating the treatment planning platform.

Provided herein are systems (200) for configuring a proton beam system to deliver energy to a patient. In some examples, systems (200) can include one or more processors that are configured to receive (302) scan data associated with a three-dimensional scan of a patient, determine (304) a treatment plan involving delivery of energy from a plurality of gantry positions relative to the patient, and provide (308) control data associated with the treatment plan to a proton beam system, the control data configured to control the proton beam system when executing the treatment plan. In some examples, each field specified by the treatment plan can be associated with a beam configuration that targets the planning target volume such that each spot path (420) of the beam configuration is separated from at least one other spot path (420) of the beam configuration by a distance that satisfies a threshold distance.

An ion chamber (116) comprises a first ion chamber window assembly (200) and an ion chamber housing (1000) having a first opening. The first ion chamber window assembly includes a first ion chamber window (2000) and a first metal plating (200) arranged at a peripheral edge of the first ion chamber window, wherein the first ion chamber window is formed of at least a first metal and has a first surface exposed through the first opening. The first metal plating is formed of a second metal. The first metal is different from the second metal, and the first ion chamber window assembly is fixed, via the first metal plating, on an inner side of the ion chamber housing (1000) at a periphery of the first opening.