A method is for providing a medical image of a patient, acquired via a computed tomography apparatus. An embodiment of the method includes acquiring first projection data of a first measurement region; acquiring second projection data of a second measurement region; registering a reference image to the at least one respiration-correlated image of the patient, wherein the reference image corresponds to the at least one functional image of the patient or is reconstructed under a second reconstruction rule from the second projection data, to produce a deformation model; applying the deformation model to the at least one functional image of the patient; combining the at least one functional image of the patient, deformed by the applying of the deformation model, with the at least one respiration-correlated image of the patient, to produce the medical image of the patient; and providing the medical image of the patient.

A first image including a first line segment is projected onto a projection surface to acquire first imaging data of a first projected image. A second image including a first mark and a second mark overlapping the first line segment is projected onto the projection surface to acquire second imaging data of a second projected image. Based on a positional relation between a third mark and a fourth mark located on a second line segment corresponding to the first line segment and a positional relation between the first mark and the second mark located on the first line segment, relation data that associates the first mark and the third mark and associates the second mark and the fourth mark is generated. Correction data is generated based on the relation data. Image data is corrected based on the correction data. A corrected image is projected onto the projection surface.

Systems and methods for identifying landmarks of a document from a digital representation of the document. The method comprises accessing the digital representation of the document and operating a Machine Learning Algorithm (MLA), the MLA having been trained based on a set of training digital representations of documents associated with labels. The operating the MLA comprises down-sampling the digital representation of the document, detecting landmarks, generating fractional pixel coordinates for the detected landmarks. The method further determines the pixel coordinates of the landmarks by upscaling the fractional pixel coordinates from the second resolution to the first resolution and outputs the pixel coordinates of the landmarks.

The invention relates to a system for determining an optimal position of a surgical instrument relative to a patient's bone tracker, the system comprising:—a medical imaging system configured to acquire at least one cone beam computed tomography intraoperative image of the patient;—a localization device;—a computer configured to receive images from the medical imaging system and localization data from the localization device and to implement the following method: the method comprising: ⋅(a) receiving at least one preoperative 2D X-ray image of the bone while the patient is in a position of interest; ⋅(b) acquiring an intraoperative 3D medical image of the bone by cone beam computed tomography while the patient is in an operative position different from the position of interest, the 3D image being registered with the coordinate system of the bone tracker; ⋅(c) registering the intraoperative 3D medical image onto the at least one preoperative 2D X-ray image, so as to obtain a registered 3D image representing the bone in the position of interest; ⋅(d) planning a surgical procedure on the registered 3D medical image taking into account said position of interest; ⋅(e) determining an optimal position of the surgical instrument relative to the patient's bone tracker for implementing said planned surgical procedure.

An apparatus includes a control system that defines a test part having multiple features of multiple feature types. The control system controls an additive manufacturing (AM) machine to print multiple copies of the test part, with each copy being printed according to a respective set of values used as printing parameters. A measurement system obtains a computed tomography (CT) image of each of the copies of the test part. An analysis system, for each of the plurality of feature types, analyzes the CT images to identify a selected set of values for the printing parameters. The analysis system identifies a portion of the CT image related to a first feature and assesses its density based on an average grayscale value. The AM machine is then controlled to print production parts according to, for each feature type of the production parts, the selected set of values for the printing parameters.

Tomographic images are obtained by processing a tilt series of 2D images by aligning and combining images withing a group of neighbor images. The tilt series generally includes sparsely sampled images. Images of the tilt series at tilt angles associated with the sparsely sample images are selected as reference frames, grouped with neighbor images, and the group of images aligned. The aligned images are combined to produce replacement frames and a replacement frame tilt series that can be used for tomographic reconstruction.

Methods and systems for deep learning alignment for semiconductor applications are provided. One method includes transforming first actual information for an alignment target on a specimen from either design data to a specimen image or a specimen image to design data by inputting the first actual information into a deep generative model such as a GAN. The method also includes aligning the transformed first actual information to second actual information for the alignment target, which has the same information type as the transformed first actual information. The method further includes determining an offset between the transformed first actual information and the second actual information based on results of the aligning and storing the determined offset as an align-to-design offset for use in a process performed on the specimen.

A method for obtaining a reconstructed image is provided. The method includes capturing, by the electronic device, a first sensor image and a second sensor image including a scene and an obstruction in the scene. The method includes generating, by the electronic device, an obstruction-free first image, a first obstruction template, an obstruction-free second image and a second obstruction template. Further, determining, a parallax shift between the obstruction-free first image and the obstruction-free second image and aligning the obstruction-free second image with respect to the obstruction-free first image and the second sensor image with respect to the first sensor image using the determined parallax shift. Further, the method includes determining occluded portions in the first sensor image and in the obstruction-free first image at corresponding locations in the aligned second sensor image and aligned obstruction-free second image respectively and obtaining the reconstructed obstruction-free first image.

A map fusing method includes receiving a source graph and a target graph. The source graph is representative of a source map and the target graph is representative of a target map and includes nodes and edges that connect the nodes. The method further includes processing each of the source graph and the target graph in a graph convolutional layer to provide graph convolutional layer outputs related to the source graph and to the target graph, processing each of the graph convolutional layer outputs for the source graph and the target graph in a linear rectifying layer to output node feature maps related to the source graph and the target graph. The method further includes selecting pairs of node representations from the node feature maps related to the source graph and the target graph and concatenating the selected pairs to output selected and concatenated pairs of node representations.

A method for creating a high-resolution image of an object from low-resolution images of the object is provided. Both the low-resolution images and the high-resolution image are composed of a pixel grid. An image recording device successively records low-resolution images, in which pitches of the grid points of the pixel grid are increased in one image dimension in comparison with the pitches of the grid points of the pixel grid in the high-resolution image to be created. A data processing system registers the low-resolution images with respect to one another to obtain registered images which are superimposed to obtain the high-resolution image. The grid points of the low-resolution images and the grid points of the high-resolution image have same dimensions and the data processing system uses image information obtained from different positions of the object relative to the grid points in the individual low-resolution images to create the high-resolution images.