Abstract: A method of object detection in a point cloud includes: determining first features associated with points of a point cloud representing one or more objects in at least a 3D space and defining geometrical information for each point of the point cloud, a first type of network being configured to receive points of the point cloud as input; determining second point cloud features based on the first features, the second features defining local geometrical information about the point cloud at positions of nodes of a uniform 3D grid; generating an object, an object proposal defining a 3D bounding box, the 3D bounding box that may define an object; and determining, by a third type of deep neural network, a score for a 3D anchor indicating a probability that the 3D anchor, the determining being based on second features that are located in the 3D anchor.

Abstract: A computer-implemented method for automated classification of 3D image data of teeth includes a computer receiving one or more of 3D image data sets where a set defines an image volume of voxels representing 3D tooth structures within the image volume associated with a 3D coordinate system. The computer pre-processes each of the data sets and provides each of the pre-processed data sets to the input of a trained deep neural network. The neural network classifies each of the voxels within a 3D image data set on the basis of a plurality of candidate tooth labels of the dentition. Classifying a 3D image data set includes generating for at least part of the voxels of the data set a candidate tooth label activation value associated with a candidate tooth label defining the likelihood that the labelled data point represents a tooth type as indicated by the candidate tooth label.

Abstract: A computer-implemented method for correction of a voxel representation of metal affected x-ray data. The method comprises a first 3D deep neural network receiving an initial voxel representation of x-ray data at its input and generating a voxel map at its output, the map identifying voxels of the initial voxel representation that belong to a region of voxels that are affected by metal. A second 3D deep neural network receives the initial voxel representation and the map generated by the first 3D deep neural network at its input and generating a corrected voxel representation, the corrected voxel representation including voxel estimations for voxels that are identified by the voxel map as being part of a metal affected region, the first 3D deep neural being trained on the basis of training data and reference data that include voxel representations of clinical x-ray data of a predetermined body part of a patient.

Abstract: A computer-implemented method for automated 3D root shape prediction comprising: receiving data defining at least one 3D representation of a tooth and processing the data including: transforming at least part of the data into a voxel representation of a crown; a pre-processor providing the representation of the crown to the input of the neural network trained on clinical representations of real teeth; the first neural network generating a representation of a root or a tooth from the crown, wherein the generation of the representation of the root or tooth includes: determining voxel activations in a voxel space of the output of the deep learning network, each activation representing a probability measure defining the probability that a voxel is part of the root or the tooth; and, determining whether a voxel activation is part of the root or the tooth by comparing the voxel activation with a voxel activation threshold value.

Abstract: A computer-implemented method for processing 3D image data of a dento-maxillofacial structure is described wherein the method may comprise the steps of: receiving 3D image data defining a volume of voxels, a voxel being associated with a radiodensity value and a position in the volume and the voxels providing a 3D representation of a dento-maxillofacial structure; using the voxels of the 3D image data to determine one or more 3D positional features for input to a first deep neural network, a 3D positional feature defining information aggregated from the entire received 3D data set; and, the first deep neural network receiving the 3D image data and the one or more positional features at its input and using the one or more 3D positional features to classify at least part of the voxels of the 3D image data into jaw, teeth and/or nerve voxels.

Abstract: A computer-implemented method for semantic segmentation of a point cloud comprises receiving a cloud having points representing a vector of an object, preferably part of a dento-maxillofacial structure having a dentition; determining subset(s) including a first number of points arranged around a selected point of the cloud and a second number of points arranged at spatial distances larger than a predetermined spatial distance of the first number of points, the first number of points representing fine feature(s) of the object around the selected point and the second number of points representing object global feature(s); providing each subset of points to a deep neural network, DNN, the DNN being trained to semantically segment points of each subset according to classes associated with the object; and, for each subset point, receiving a DNN output multi-element vector, wherein each element represents a probability that the point belongs to class(es) of the object.

Abstract: A method of the invention comprises obtaining training dental CT scans, identifying individual teeth and jaw bone in each of these CT scans, and training a deep neural network with training input data obtained from these CT scans and training target data. A further method of the invention comprises obtaining a patient dental CT scan, identifying individual teeth and jaw bone in this CT scan and using the trained deep learning network to determine a desired final position from input data obtained from this CT scan. The (training) input data represents all teeth and the entire alveolar process and identifies the individual teeth and the jaw bone. The determined desired final positions are used to determine a sequence of desired intermediate positions per tooth and the intermediate and final positions and attachment types are used to create three-dimensional representations of teeth and/or aligners.

Abstract: A method for automatically determining a canonical pose of a 3D object comprises: providing one or more blocks of voxels of a voxel representation of the 3D object to a first 3D deep neural network, the first 3D neural network being trained to generate canonical pose information; receiving canonical pose information from the first 3D deep neural network, the canonical pose information comprising for each voxel a prediction of a position of the voxel in the canonical coordinate system; using the canonical coordinates to determine an orientation and scale of the axes of the canonical coordinate system and a position of the origin of the canonical coordinate system relative to the axis and the origin of the first 3D coordinate system and using the orientation and the position to determine transformation parameters of the first coordinate system into canonical coordinates; and, determining a canonical representation of the 3D dental structure.

Abstract: A computer-implemented method for processing 3D image data of a dento-maxillofacial structure is described wherein the method may comprise the steps of: receiving 3D image data defining a volume of voxels, a voxel being associated with a radiodensity value and a position in the volume and the voxels providing a 3D representation of a dento-maxillofacial structure; using the voxels of the 3D image data to determine one or more 3D positional features for input to a first deep neural network, a 3D positional feature defining information aggregated from the entire received 3D data set; and, the first deep neural network receiving the 3D image data and the one or more positional features at its input and using the one or more 3D positional features to classify at least part of the voxels of the 3D image data into jaw, teeth and/or nerve voxels.

Abstract: A computer-implemented method for correction of a voxel representation of metal affected x-ray data. The method comprises a first 3D deep neural network receiving an initial voxel representation of x-ray data at its input and generating a voxel map at its output, the map identifying voxels of the initial voxel representation that belong to a region of voxels that are affected by metal. A second 3D deep neural network receives the initial voxel representation and the map generated by the first 3D deep neural network at its input and generating a corrected voxel representation, the corrected voxel representation including voxel estimations for voxels that are identified by the voxel map as being part of a metal affected region, the first 3D deep neural being trained on the basis of training data and reference data that include voxel representations of clinical x-ray data of a predetermined body part of a patient.

Abstract: A computer-implemented method for automated 3D root shape prediction comprising: receiving data defining at least one 3D representation of a tooth and processing the data including: transforming at least part of the data into a voxel representation of a crown; a pre-processor providing the representation of the crown to the input of the neural network trained on clinical representations of real teeth; the first neural network generating a representation of a root or a tooth from the crown, wherein the generation of the representation of the root or tooth includes: determining voxel activations in a voxel space of the output of the deep learning network, each activation representing a probability measure defining the probability that a voxel is part of the root or the tooth; and, determining whether a voxel activation is part of the root or the tooth by comparing the voxel activation with a voxel activation threshold value.

Abstract: A computer-implemented method for automated classification of 3D image data of teeth includes a computer receiving one or more of 3D image data sets where a set defines an image volume of voxels representing 3D tooth structures within the image volume associated with a 3D coordinate system. The computer pre-processes each of the data sets and provides each of the pre-processed data sets to the input of a trained deep neural network. The neural network classifies each of the voxels within a 3D image data set on the basis of a plurality of candidate tooth labels of the dentition. Classifying a 3D image data set includes generating for at least part of the voxels of the data set a candidate tooth label activation value associated with a candidate tooth label defining the likelihood that the labelled data point represents a tooth type as indicated by the candidate tooth label.