Mirada Medical Limited

Mark Gooding

Timor Kadir

Aymeric Larrue

Daniel Balfour

Devis Peressutti

David McCabe

Paul Aljabar

Ian Brown

Djamal Boukerroui

A method and system for generating synthetic images for use in a database is described. The database is used for delineation of features in real images, the method comprising the steps of: providing a delineated image acquired using a first scanner, defining a model related to the generation of synthetic images using a second scanner, processing the delineated image using the model to generate a synthetic image, mapping contours to the synthetic image to form a synthetic image-contour pair; repeating providing, defining and processing steps to generate a plurality of synthetic images and contour pairs for the database; using said database of synthetic images and contour pairs to optimise a contouring algorithm, where the optimised algorithm generates contours for the real images of the same type as the synthetic images; processing one or more further real images to contour and delineate features on the further real image using the algorithm.

System and method for automatic delineation of scanned images

A method () of generating an atlas for a universal atlas database () is provided. A new medical scan image () is provided. A universal auto-contouring operation () is performed on the medical scan image, to generate a set of universal contours () for the medical scan image. A local auto-contouring customisation operation () is performed on the medical scan image, to generate a set of local contours () for the medical scan image. The set of local contours is standardised () using a trained model to compensate for biases in the set of local contours, thereby creating a set of standardised global contours () for the medical scan image. The set of standardised global contours () and the medical scan image () can be added to the universal atlas database () as a new atlas, thereby expanding the set of atlases that are available in the universal atlas database.

Method and apparatus for generating a universal atlas database

A method and apparatus for assessing image registration. The method comprises obtaining image datasets for the first and second medical images and registration data representing the registration from the first medical image to the second medical image, collating use-case information for the image registration, deriving a set of at least one measurement and assessment criteria therefor based at least partly on the collated use-case information, performing the at least one measurement on at least one of the obtained image datasets and the obtained registration data to derive at least one measurement value, applying the assessment criteria for the at least one measurement to the at least one measurement value to derive at least one assessment result, and outputting an indication of the at least one assessment result.

Method and apparatus for assessing image registration

A method and apparatus for selecting a subset of atlases from a set of candidate atlases. The method comprises: for each candidate atlas n within the set of N candidate atlases, computing an auto-contouring performance measure in relation to each training atlas t within a subset of a set of T training atlases; for each pair combination of candidate atlas n and training atlas t for which an auto-contouring performance measure has been computed, deriving a score based on the computed auto-contouring performance measures; for each candidate atlas n within the set of N candidate atlases, aggregating the derived scores for each pair combination comprising that candidate atlas n; and selecting a subset of M candidate atlases from the set of N candidate atlases based on the aggregated scores therefor.

Selection of a subset of atlases from a set of candidate atlases

A method of generating image alignment data for medical images. The method comprises determining prospective image pair registration connections, determining registration weighting values for the determined prospective image pair registration connections based at least partly on intra-image attribute data, determining optimal registration paths for image pairs based at least partly on the registration weighting values for the prospective image pair registration connections, and generating image alignment data for the determined optimal registration paths.

Method and apparatus for generating image alignment data

A method and apparatus for delineating an object within a volumetric medical image. The method comprises obtaining auto-generated contour data for the object within the volumetric medical image, the auto-generated contour data defining a set of auto-generated contours forming a delineation structure for the object, selecting a subset of auto-generated contours for manual editing, and identifying the selected subset of auto-generated contours to a user. In some examples, the method further comprises presenting at least the selected subset of auto-generated contours to the user, receiving user feedback for at least one auto-generated contour, deriving a full set of contours forming a revised delineation structure for the object based at least partly on an interpolation of the auto-generated contour(s) for which user feedback was received, and storing contour data defining the derived full set of contours forming the revised delineation structure for the object within at least one data storage device.

Method and apparatus for delineating an object within a volumetric medical image

A method of measuring a parameter of a structure () on a medical image () comprises a measurement tool () displayed on a slice of the image. An automated point detection function identifies a point within at least one region () of the image that optimizes the placement of the respective end of the measurement tool (). The region may be 2-d or 3-d. The identified point(s) are then used to calculate the parameter, which may be distance, angle, area or volume. The measurement tool () may move to the identified points (). A system (), computer program and computer-readable medium are also provided. The invention may make the measurement of tumors, and measurements of the spacing within or between various structures on a medical image, more accurate and/or more consistent.

Growing community of inventors

Oxford, United Kingdom

Mark Gooding