Elekta Ab (publ)

Elekta Ab

University Health Network

Jonas Anders Adler

Jens Olof Sjölund

Ozan Öktem

Markus Eriksson

David Anthony Jaffray

David Andreas Tilly

Peter Kimstrand

Marcus Hennix

Gregory Bootsma

Linn Öström

Frank Verhaegen

Bjorn Nutti

Hakan Nordstrom

Ozan Oktem

Much of the image processing that is applied to medical images is a form of 'inverse problem'. This is a class of mathematical problems in which a “forward” model by which a signal is converted into dataset is known, to at least some degree, but where the aim is to reconstruct the signal given the resulting dataset. Thus, an inverse problem is essentially seeking to discover x given knowledge of A(x)+noise by finding an appropriate reconstruction operator Asuch that A(A(x)+noise)≈x, thereby enabling us to obtain x (or a close approximation) given knowledge of an output dataset consisting of A(x)+noise. Generally, several such processes (or their equivalents) are applied to the image dataset. If the first process (for example, noise reduction) is expressed via a first reconstruction operator Acharacterised by a parameter set Θand the second process (for example, segmentation) is expressed via a second reconstruction operator Acharacterised by a parameter set Θ, then the result of the two steps applied consecutively is A(A(y)). This can be expressed as an overall reconstruction operator P, characterised by a parameter set Φ. If we then allow a machine learning process to optimise P, then the steps previously carried out separately can be combined into a single optimisation. This yields advantages in terms of computational load and in the accuracy of the end result.

Analysis of medical images

Techniques for solving a radiotherapy treatment plan optimization problem are provided. The techniques include receiving a radiotherapy treatment plan optimization problem; processing the radiotherapy treatment plan optimization problem with a machine learning model to estimate one or more optimization variables of the radiotherapy treatment plan optimization problem, wherein the machine learning model is trained to establish a relationship between the one or more optimization variables and parameters of a plurality of training radiotherapy treatment plan optimization problems; and generating a solution to the radiotherapy treatment plan optimization problem based on the estimated one or more optimization variables of the radiotherapy treatment plan optimization problem.

Radiotherapy treatment plan optimization using machine learning

Techniques for generating a radiotherapy treatment plan are provided. The techniques include receiving an input parameter related to a patient, the input parameter being of a given type; processing the input parameter with a machine learning technique to estimate a realizable plan parameter of a radiotherapy treatment plan, wherein the machine learning technique is trained to establish a relationship between the given type of input parameter and a set of realizable radiotherapy treatment plan parameters to achieve a target radiotherapy dose distribution; and generating the radiotherapy treatment plan based on the estimated realizable plan parameter.

Generation of realizable radiotherapy plans

Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.

Posterior image sampling to detect errors in medical imaging

Systems and methods for calculating radiotherapy dose distribution are provided. The systems and methods include operations for receiving data representing at least one of particle trajectories or a dose deposition pattern in a simulated delivery of a radiotherapy plan; applying a dose calculation process to the received data to generate a first radiotherapy dose distribution having a first level of detail; and processing the first radiotherapy dose distribution using a trained machine learning technique to generate a second radiotherapy dose distribution having a second level of detail that enhances the first level of detail.

Computing radiotherapy dose distribution

Techniques for the operation and use of a model that learns the general representation of multimodal images is disclosed. In various examples, methods from representation learning are used to find a common basis for representation of medical images. These include aspects of encoding, fusion, and downstream tasks, with use of the general representation and model. In an example, a method for generating a modality-agnostic model includes receiving imaging data, encoding the imaging data by mapping data to a latent representation, fusing the encoded data to conserve latent variables corresponding to the latent representation, and training a model using the latent representation. In an example, a method for processing imaging data using a trained modality-agnostic model includes receiving imaging data, encoding the data to the defined encoding, processing the encoded data with a trained model, and performing imaging processing operations based on output of the trained model.

Modality-agnostic method for medical image representation

Posterior image sampling using statistical learning model

Embodiments disclose a method performed by at least one processor for processing a plurality of x-ray projection images of a subject, the method comprising a plurality of operations including reconstructing the projection images to yield a volume reconstruction; segmenting the reconstructed volume by assigning a material type to each voxel; estimating a first set of scatter images corresponding to a subset of the projection images by calculating probabilistic predictions of interactions of x-rays with the subject and applying a low pass spatial filter to the scatter images; estimating a second set of scatter images corresponding to projection images not included in the subset, based on the first set of scatter images; and subtracting, for each projection image, the corresponding scatter image to yield a corrected projection image. Applying the plurality of operations of the method in an iterative process on graphics-processor-quality computational hardware enables real-time scatter correction and reconstruction of CT volume images.

Growing community of inventors

Stockholm, Sweden

Jonas Anders Adler