Automated determination of a canonical pose of a 3D objects and superimposition of 3D objects using deep learning

Abstract

A method for automatically determining a canonical pose of a 3D object represented by a 3D data set is described, wherein the method comprises: providing one or more blocks of voxels of a voxel representation of the3D object associated with a first coordinate system to the input of a first 3D deep neural network, the first 3D neural network being trained to generate canonical pose information associated with a canonical coordinate system defined relative to a position of part of the 3D dental structure; receiving canonical pose information from the output of thefirst3D deep neural network, the canonical pose information comprising for each voxel of the one or more blocks a prediction of a position of the voxel in the canonical coordinate system, the position being defined by canonical coordinates; 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 for transforming coordinates of the first coordinate system into canonical coordinates; and, determining a canonical representation of the 3D dental structure, the determining including applying the transformation parameters to coordinates of the voxels of the voxel representation or the 3D data set used for determining the voxel representation.

Description

technical field [0001] The present invention relates to automatically determining a canonical pose of a 3D object (e.g., a 3D dental structure) using deep learning and to automatically overlaying a 3D object; in particular, but not exclusively, to a method for automatically determining a canonical pose of a 3D object and Systems and methods and systems for automatically overlaying 3D objects and computer program products enabling computer systems to perform these methods. Background technique [0002] Accurate 3D models of the patient's dentition and jaws (maxilla and mandible) are essential for 3D computer-aided dental applications (orthodontic treatment planning, dental implant planning, orthognathic surgery planning (jaw surgery), etc.) . Formation of such a 3D model is based on 3D image data of the patient, typically 3D computed tomography (CT) data representing a 3D object such as a dento-maxillofacial complex or other body part. A CT scan typically produces a voxel r...

AI Technical Summary

Problems solved by technology

Additional difficulties may arise when datasets only partially overlap

State-of-the-art voxel-based overlay methods are often computationally expensive

[0008] The large size of 3D datasets and the fact that clinical implementation requires very stringent accuracy criteria make it difficult to utilize traditional image superposition methods on high-dimensional medical images

Known overlay systems cannot handle these problems in a reliable and robust manner

More generally, large variations in 3D datasets across different modalities pose problems for accurate processing by deep neural network systems

Images