Brainlab AG

Disclosed is a computer-implemented method for determining an orientation of an electrode using acquired two-dimensional rotational images taken while the two-dimensional imaging apparatus is rotated about the patient, and acquired three dimensional tomographic images of the anatomical structure. The electrode orientation is determined in the three-dimensional reference system of the tomographic imaging apparatus.

A method for calculating a 3D representation of a vascular malformation of a vascular structure is provided. The method comprises: providing 2D X-ray image data of a vascular structure containing a contrast agent and having a vascular malformation, providing 3D image data of the vascular structure and transforming the 3D image data into transformed 2D image data, overlaying the 2D X-ray image data and the transformed 2D image data; calculating a correspondence between the 2D X-ray image data and the transformed 2D image data to determine a co-registration between the 2D X-ray image data and the 3D image data, determining in the co-registered 2D X-ray image data the vascular malformation, and calculating the 3D representation of the vascular malformation based on the determined vascular malformation of the co-registered 2D X-ray image data.

Disclosed is a computer-implemented method for partitioning a medical image which encompasses acquiring a medical image of a surface of a patient and a surface of at least one object (embodied by image data), for example, by means of a 3D scanning device. Furthermore, a thermal image of the surface of the patient and the surface of the object is acquired (embodied by thermal data), for example, by means of a thermal camera. The medical image and the thermal image are fused (based on registration data), such that the image data is associated with the thermal data (embodied by association data). By analyzing the association data with regard to a specified condition (embodied by condition data), for example a condition related to a temperature threshold, a subset of the association data which fulfills the condition and describes a part of the medical image is determined (embodied by condition compliance data). For example, the object is colder than the skin of the patient, so by applying the temperature threshold, the part of the image representing the object may be identified. Accordingly, a part of the medical image showing a surface of the patient may be distinguished from a part of the medical image showing a surface of the object. Furthermore, and for example, one of those two parts may be defined to be a region of interest, and a positional shift of the region of interest (e.g. a face of the patient) may be determined by tracking the region of interest.

Disclosed is a computer-implemented method of determining an assignment of an object acquire patient image data of interest recognizable in a digital medical patient image such as a tumour or other medical anomaly such as an implant to an anatomical region. The medical patient image is registered with atlas data, The assignment is then determined by calculating a score value defining an amount of volume intersection between the object of interest and a digital object defining a specific anatomic region, for example a bounding box around a specific organ, which is defined in the atlas data.

Disclosed is a computer-implemented method of determining a correspondence between a region of interest as it appears in a first digital medical patient image and as it appears in a second digital medical image. The correspondence is determined by calculating the ratio of overlap of the region of interest with a data object defining an anatomical body part in the first image and the second image and determining whether the larger of the two ratios exceeds a threshold. If the threshold is exceeded, the method assumes that the appearances in the two images describe the same region of interest.

Disclosed is a computer-implemented method of determining one or more position and/or orientation parameters of an anatomical structure of a body portion. The anatomical structure has a longitudinal shape defining a longitudinal axis. The method includes generating and/or reading, by a data processing system, volumetric data of at least a portion of a subject. The method further includes generating and/or reading, by the data processing system, a deformable template which provides an estimate for a location of the longitudinal axis in the portion of the subject. The method further includes matching, by the data processing system, the deformable template to the volumetric data, thereby obtaining a matched template. The matching comprises using one or more internal energy functions and one or more external energy functions for optimizing an objective function. The method further includes determining, by the data processing system, the at least one position and/or orientation parameter based on the matched template.

Disclosed is a computer-implemented medical data processing method for determining an orientation of an electrode, the electrode being configured for electrically stimulating an anatomical structure of a patient and comprising a rotational orientation marker, the method comprising executing, on at least one processor of at least one computer, steps of: a) acquiring (S 1.1 ), at the at least one processor, rotational image data describing two-dimensional medical images of the anatomical structure and the electrode, the two-dimensional medical images having been taken with a two-dimensional medical imaging apparatus during rotation of the medical imaging apparatus relative to the anatomical structure, the rotational image data further describing, for each of the two-dimensional medical images, an imaging perspective relative to the anatomical structure associated with the respective two-dimensional medical image; b) determining (S 1.2 ), by the at least one processor and based on the rotational image data, rotational orientation data describing the rotational orientation of the electrode in the reference system of the two-dimensional medical images; c) acquiring (S 1.3 ), at the at least one processor, tomographic image data describing a set of tomographic medical images of the anatomical structure; d) determining (S 1.4 ), by the at least one processor and based on the rotational image data and the tomographic image data and the rotational orientation data, electrode orientation data describing a rotational orientation of the electrode in a reference system of the tomographic medical image data.

By using the Al module, the method of the present invention calculates, i.e. predicts, the dependency C i (p i ) of a radiotherapy (RT) quality criterion C, from an adjustment of such a radiotherapy planning parameter p i . In this way, the decision making process in RT treatment plan optimization is streamlined by prediction of promising settings of one or more radiotherapy planning parameters p, before the actual time intensive iterative optimization process is carried out. This is achieved by applying an Al module, which has been trained to predict the specific behaviour of the dose optimization algorithm, i.e. the optimizer, with respect to geometric patient data, dose prescription and treatment indication data. Thus, a computer-implemented medical method of predicting a dependency C i (p i ) of a radiotherapy (RT) quality criterion C i from an adjustment of a radiotherapy planning parameter p, is presented. The method comprises the following steps of providing geometric patient data geometrically describing an area of a patient, which is to be irradiated according to a radiotherapy treatment plan (step S 1 ), providing dose prescription data and treatment indication data for said patient (step S 2 ), and predicting with a trained Artificial Intelligence (Al) module the dependency C i (p i ) of the radiotherapy quality criterion C i from the radiotherapy planning parameter p, when adjusting said radiotherapy planning parameter p i , thereby using the geometric patient data, the dose prescription data and the treatment indication data as input for the Al module (step S 3 ).

Disclosed is a computer-implemented methods of determining distributions of corrections for correcting the segmentation of medical image data, determining corrections for correcting the segmentation of medical image data, training a learning algorithm for determining a segmentation of a digital medical image, and determining a relation between an image representation of the anatomical body part in an individual medical image and a label to be associated with the image representation of the anatomical body part in the individual medical image using the trained machine learning algorithm. The methods encompass reading a plurality of corrections to image segmentations, wherein the corrections themselves may have been manually generated, transforming these corrections into a reference system which is not patient-specific such as an atlas reference system, conducting a statistical analysis of the correction, and applying the re-transformed result of the statistical analysis to patient images. The result of the statistical analysis may also be used to appropriately train a machine learning algorithm for automatic segmentation of patient images. The application of such a trained machine learning algorithm is also part of this disclosure.

Disclosed is a computer-implemented method which encompasses registering a tracked imaging device such as a microscope having a known viewing direction and an atlas to a patient space so that a transformation can be established between the atlas space and the reference system for defining positions in images of an anatomical structure of the patient. Labels are associated with certain constituents of the images and are input into a learning algorithm such as a machine learning algorithm, for example a convolutional neural network, together with the medical images and an anatomical vector and for example also the atlas to train the learning algorithm for automatic segmentation of patient images generated with the tracked imaging device. The trained learning algorithm then allows for efficient segmentation and/or labelling of patient images without having to register the patient images to the atlas each time, thereby saving on computational effort.