A kit for a fiducial marker-based registration of preinterventional image data to an intra-interventional scene is disclosed. The kit comprises: at least one first component, wherein the first component is configured for attachment to a body of a patient, wherein the first component comprises at least one base part of an arresting mechanism, at least one second component, wherein the second component comprises at least one fiducial which is localizable in the preinterventional image data, wherein the second component comprises at least one first counterpart of the arresting mechanism, at least one third component, wherein the third component comprises at least one mounting unit for mounting a spatially localizable tracking object on the third component, wherein the third component comprises at least one second counterpart of the arresting mechanism;
wherein the second component and the third component are selectively attachable to the first component by establishing a releasable mechanical connection between the base part and the first counterpart or between the base part and the second counterpart.

A kit for a fiducial marker-based registration of preinterventional image data to an intra-interventional scene is disclosed. The kit comprises: at least one first component, wherein the first component is configured for attachment to a body of a patient, wherein the first component comprises at least one base part of an arresting mechanism, at least one second component, wherein the second component comprises at least one fiducial which is localizable in the preinterventional image data, wherein the second component comprises at least one first counterpart of the arresting mechanism, at least one third component, wherein the third component comprises at least one mounting unit for mounting a spatially localizable tracking object on the third component, wherein the third component comprises at least one second counterpart of the arresting mechanism;
wherein the second component and the third component are selectively attachable to the first component by establishing a releasable mechanical connection between the base part and the first counterpart or between the base part and the second counterpart.

There are provided a method of accurately detecting a measurement error of SEM equipment by comparing and aligning a design image with an SEM image, and a method of accurately aligning SEM equipment based on a detected measurement error. The method of detecting a measurement error of SEM equipment includes acquiring SEM images of a measurement target, performing pre-processing on the SEM images and design images corresponding thereto, selecting training SEM images from among the SEM images, performing training by using the training SEM images and training design images and generating a conversion model between the SEM images and the design images, converting the SEM images into conversion design images by using the conversion model, extracting an alignment coordinate value by comparing and aligning the conversion design images with the design images, and determining a measurement error of the SEM equipment based on the alignment coordinate value.

There are provided a method of accurately detecting a measurement error of SEM equipment by comparing and aligning a design image with an SEM image, and a method of accurately aligning SEM equipment based on a detected measurement error. The method of detecting a measurement error of SEM equipment includes acquiring SEM images of a measurement target, performing pre-processing on the SEM images and design images corresponding thereto, selecting training SEM images from among the SEM images, performing training by using the training SEM images and training design images and generating a conversion model between the SEM images and the design images, converting the SEM images into conversion design images by using the conversion model, extracting an alignment coordinate value by comparing and aligning the conversion design images with the design images, and determining a measurement error of the SEM equipment based on the alignment coordinate value.

A method for training a neural network includes receiving a plurality of images and, for each individual image of the plurality of images, generating a training triplet including a subset of the individual image, a subset of a transformed image, and a homography based on the subset of the individual image and the subset of the transformed image. The method also includes, for each individual image, generating, by the neural network, an estimated homography based on the subset of the individual image and the subset of the transformed image, comparing the estimated homography to the homography, and modifying the neural network based on the comparison.

A method for training a neural network includes receiving a plurality of images and, for each individual image of the plurality of images, generating a training triplet including a subset of the individual image, a subset of a transformed image, and a homography based on the subset of the individual image and the subset of the transformed image. The method also includes, for each individual image, generating, by the neural network, an estimated homography based on the subset of the individual image and the subset of the transformed image, comparing the estimated homography to the homography, and modifying the neural network based on the comparison.

During an intraoral scan session, a processing device receives a plurality of intraoral images of a dental site. The processing device determines that a historical template of the dental site is existent and registers a first intraoral image of the plurality of intraoral images to the historical template at a first region of the dental site depicted in the historical template. The processing device may register one or more remaining intraoral images of the plurality of intraoral images to the historical template at a second region of the dental site depicted in the historical template. The first region may be separated from the second region.

The invention relates to a computer-implemented medical data processing method for determining a mapping of medical image content into a reference system, the method comprising executing, on a processor of a computer, steps of: a) acquiring, at the processor, medical image data describing a digital medical image of an anatomical structure of a patient's body; b) acquiring, at the processor, image attribute data describing attribute information associated with the medical image data, the attribute information including an indication of an initial reference system in which spatial relationships of the digital medical image are defined; c) acquiring, at the processor, reference system transformation data describing a spatial relationship (REG) between the initial reference system and a second reference system which is different from the initial reference system; d) determining, by the processor and based on the medical image data and the reference system transformation data, transformed image data describing a representation of the digital medical image in the second reference system.

A system and method that allows the capture of a series of images to create a single linear panoramic image is disclosed. The method includes capturing an image, dynamically comparing a previously captured image with a preview image on a display of a capture device until a predetermined overlap threshold is satisfied, generating a user interface to provide feedback on the display of the capture device to guide a movement of the capture device, and capturing the preview image with enough overlap with the previously captured image with little to no tilt for creating a linear panorama.

An imaging device includes a light separator that separates light into light bands, and imaging elements that each receives one of the light bands and generates a corresponding signal. Each of the imaging elements has a pixel size of at most 2.5 μm by 2.5 μm. A registration error among the imaging elements is equal to or less than a threshold determined according to the pixel size.