Koninklijke Philips Corporation N.v.

The University of Texas System

Siemens Medical Solutions Usa, Inc.

Ruby Hall Clinic

Vaitheeswaran Ranganathan

Prashant Kumar

Gipson Joe Anto

Karl Antonin Bzdusek

Matthew Palmer

Sivaramakrishnan Krishnaiyer Raman

Michael Kantor

Bojarajan Perumal

Deepak Pitambar Mahajan

Murali Balasubramanian

Reshmi Bhattacharjee

Saravanan Karunanithi

Ajesh Kumar

Rohinee Nuggehalli Ashwinee Kumar

Sathiya Narayanan Vatyam

Described are various embodiments of systems, devices, methods, and computer readable mediums related to image fusion of lower resolution (LR) images and higher resolution (HR) reference images of an object in a body. In an example embodiment of a method, the method comprises determining specific image scanning geometries used for acquiring LR images based on an ML algorithm that uses at least one feature in at least one region of interest in the respective LR images as input. The method further comprises generating image scanning geometry matching oblique HR images based on HR reference images and the determined specific image scanning geometries used for acquiring the respective LR images and registering the oblique HR images with the LR images to generate registered HR images. Current feature information is extracted from the LR images and mapped on corresponding feature information in the registered HR images to generate fusion images.

Lower to higher resolution image fusion

In a continuous arc radiation therapy planning method for planning a radiation therapy session parameterized by a set parameters for control points (CPs) along at least one radiation source arc, a geometric optimization () is performed that does not include calculating radiation absorption profiles to generate optimized values for a sub-set of the parameters. After the geometric optimization, a main optimization () is performed that includes calculating radiation absorption profiles. The main optimization is performed with the sub-set of parameters initialized to the optimized values from the geometric optimization. The sub-set of parameters optimized by the geometric optimization may include collimator angle parameters for a multileaf collimator (MLC) (). The geometric optimization may optimize a cost function comprising a sum over the CPs of a per-CP cost function dependent on a target-only region () defined as a planning target volume excluding any portion overlapping an organ at risk.

Method of optimizing collimator trajectory in volumetric modulated Arc therapy

In order to assess the achievability of treatment goals for a radiation therapy treatment, an estimation unit generates a treatment plan for the radiation therapy treatment only on the basis of treatment goals relating to a target structure to obtain a first dose distribution, (i) segments the region of the patient's body into a plurality of concentric shells surrounding the target structure and determines a mean radiation dose assigned to each shell in accordance with the first dose distribution, and (iii) checks whether a further dose distribution can be determined, which fulfills the treatment goals relating to at least one structure at risk and, which is configured such that the mean radiation dose assigned to each shell in accordance with the further dose distribution corresponds to the mean radiation dose assigned to the same shell in accordance with the first dose distribution.

Estimation of the achievability of treatment goals in radiation therapy

A method includes generating a nominal dose distribution based on an image and clinical goals. The method further includes generating a setup error dose distribution based on range and setup uncertainties. The method further includes generating a dose distribution for a parameter of an internal organ. The method further includes optimizing a planned dose distribution of an intensity modulated proton therapy plan by minimizing a total objective value including the nominal dose distribution, the setup error dose distribution dose distribution, and the dose distribution for the internal organ. The method further includes generating a final dose distribution for the intensity modulated proton therapy plan based on beam parameters of the optimized planned dose distribution. The method further includes controlling a proton therapy apparatus configured to deliver proton therapy based on the intensity modulated proton therapy plan with the optimized planned dose distribution.

Intensity modulated proton therapy (IMPT) plan optimization based at least on internal organ anticipated movement and/or expected deformation

A radiation therapy system () includes a radiation therapy (RT) optimizer unit () and an interactive planning interface unit (). The RT optimizer unit () receives at least one target structure and at least one organ-at-risk (OAR) structure segmented from a volumetric image (), and generates an optimized RT plan () based on dose objectives (--), at least one dose objective of the dose objectives corresponding to each of the at least one target structure (-) and the at least one OAR structure (-). The optimized RT plan includes a planned radiation dose for each voxel of the volumetric image using external beam radiation therapy, wherein the RT optimizer unit operates iteratively. The interactive planning interface unit () interactively controls each of the dose objectives through controls () displayed on a single display () of a display device (), operates the RT optimizer unit to iteratively compute the planned radiation dose according to the controls, and provide visual feedback () on the single display according to progress of the RT optimizer unit after each trial.

Radiation therapy interactive planning

A robustness optimization is disclosed for a broad beam proton therapy plan. A nominal dose distribution () is computed, to be delivered to a volume by performing proton therapy on the volume according to a proton therapy plan () having parameters () defining a range compensator shape and a range band. The parameters of the proton therapy plan are adjusted to reduce a difference between the nominal dose distribution () and a perturbed dose distribution calculated to be delivered to the volume modified by an error scenario () by performing proton therapy on the volume modified by the error scenario in accordance with the proton therapy plan with the parameters adjusted by the adjusting operation. The adjusting may be repeated serially for each error scenario of a set of error scenarios () to produce a proton therapy plan that is robust for any of these error scenarios.

Robust broad beam optimization for proton therapy

An achievability estimate is computed for an intensity modulated radiation therapy (IMRT) geometry () including a target volume, an organ at risk (OAR), and at least one radiation beam. Namely, a geometric complexity (GC) metric is computed for the IMRT geometry that compares a number NT of beamlets of the at least one radiation beam available in the IMRT geometry for irradiating the target volume and a number n of these beamlets that also pass through the OAR. A GC metric ratio is computed of the GC metric for the IMRT geometry and the GC metric for a reference IMRT geometry for which an IMRT plan is achievable. If the clinician is satisfied with this estimate then optimization () of an IMRT plan for the IMRT geometry () is performed. Alternatively, a reference IMRT geometry is selected by comparing the GC metric with GC metrics of past IMRT plans.

Pre-optimization method for quick prediction of achievability of clinical goals in intensity modulated radiation therapy

A method and related system to adjust an existing treatment plan. A second optimization is run based on a dual objective function system that includes a first objective function used for the optimization in respect of the existing plan and a second, extended objective function that includes the said first objective function as a functional component.

Method to reduce local hot/cold spots in DMPO-based IMRT planning

A therapy planning system and method generate an optimal treatment plan accounting for changes in anatomy. Therapy is delivered to the subject according to a first auto-planned optimal treatment plan based on a first image of a subject. A second image of the subject is received after a period of time. The second image is registered with the first image to generate a deformation map accounting for physiological changes. The second image is segmented into regions of interest using the deformation map. A mapped delivered dose is computed for each region of interest using the dose delivery goals and the deformation map. The first treatment plan is merged with the segmented regions of the second image and the mapped delivered dose during optimization.

Automatic plan optimization for changing patient anatomy in the presence of mapped delivered dose from delivered fractions

A method for reviewing a treatment plan () for delivering radiation therapy to a patient. The treatment plan () includes geometric analysis data, dose distribution analysis data, dose volume histogram data, parametric analysis data or deliverability analysis data of a patient. First, for the treatment plan (), a plurality of clinical and delivery goals are identified (). Next, goal data points are extracted () from the treatment plan (). Then, data points are correlated () to identify deficiencies in the treatment plan (). A report is generated () to display on a display () the correlated data points using visual markings () to highlight identified deficiencies. Text and audio notations can be attached to the report to explain the correlations and warn a user of plan deficiencies.

Audio-visual summarization system for RT plan evaluation

A method for dose-gradient based optimization of an intensity modulated radiation therapy plan. First, an optimizer () performs a first optimization () of the plan to generate dose distributions corresponding to the plan. Next, the optimizer () generates a beam specific dose gradient map () for each beam of the plan. Then, new dose gradients are specified () for the plan. Last, the optimizer () performs a final optimization () using the new dose gradients. The final optimization is given the new dose gradients as soft constraints into an objective function. The optimizer () applies a limiting factor to the objective function such that a first dose gradient is limited by the optimizer only if the first dose gradient exceeds the new dose gradient for a specific beamlet.

Interactive dose gradient based optimization technique to control IMRT delivery complexity

A therapy planning system () and method generate an optimal treatment plan. A plurality of objectives are automatically formulated () based on a plurality of clinical goals including dose profiles and priorities. The dose profiles and the priorities correspond to a plurality of structures including a plurality of target and/or critical structures identified within a planning image. Further, a plurality of treatment plan parameters are optimized () based on the plurality of objectives to generate a treatment plan. The plurality of objectives are reformulated () and the plurality of treatment plan parameters are reoptimized () based on the reformulated plurality of objectives to generate a reoptimized treatment plan. The optimizing () is repeated based on the reformulated plurality of objectives to generate a reformulated treatment plan.

Growing community of inventors

Bengaluru, India

Vaitheeswaran Ranganathan