Systems and methods provide guidance for selection of projection perspectives to utilize to obtain complementary combinations of projection images of an object. The systems and methods provide a first two-dimensional image of the object which has been obtained from a first perspective having a first spatial orientation with reference to a coordinate system. The systems and methods define a first parameter indicative of a degree to which candidate perspectives complement the first perspective, define at least one scale of values between first and second limits, the first and second limits are associated with first and second candidate perspectives having complementary and non-complementary relations to the first perspective. The systems and methods associate the values to the first parameter for the candidate perspectives and display indicia indicative of the values of the first parameter with reference to the coordinate system as guidance for selecting candidate perspectives.

Described herein are systems, methods, and instrumentalities associated with automatically annotating a 3D image dataset. The 3D automatic annotation may be accomplished based on a 2D annotation provided by an annotator and by propagating the 2D annotation through multiple images of a sequence of 2D images associated with the 3D image dataset. The automatically annotated 3D image dataset may then be used to annotate other 3D image datasets based on similarities between the first 3D image dataset and the other 3D image datasets. The automatic annotation of the first 3D image dataset and/or the other 3D image datasets may be conducted based on one or more machine-learning models trained for performing those tasks.

Described herein are systems, methods, and instrumentalities associated with automatically annotating a 3D image dataset. The 3D automatic annotation may be accomplished based on a 2D manual annotation provided by an annotator and by propagating, using a set of machine-learning (ML) based techniques, the 2D manual annotation through sequences of 2D images associated with the 3D image dataset. The automatically annotated 3D image dataset may then be used to annotate other 3D image datasets upon passing a readiness assessment conducted using another set of ML based techniques. The automatic annotation of the images may be performed progressively, e.g., by processing a subset or batch of images at a time, and the ML based techniques may be trained to ensure consistency between a forward propagation and a backward propagation.

Provided is a medical image processing apparatus and method. The medical image processing apparatus includes: an image processor configured to extract a blood vessel area and at least one contour line of the blood vessel area from a first image representing the blood vessel area, and to obtain a second image representing an area of at least one plaque based on the blood vessel area and the at least one contour line; a display configured to display the second image; and a user interface configured to receive a user input for correcting at least one contour line corresponding to at least one of the at least one plaque represented in the second image, wherein the image processor corrects the second image based on the user input. The medical image processing apparatus may precisely visualize a contour line of the blood vessel area.

An image processing apparatus is configured to acquire a first image group and a second image group and execute image processing on the first and second image groups. The image processing apparatus includes: a processor comprising hardware, wherein the processor is configured to: compare the number of images of interest in the first image group, with the number of images of interest in the second image group; and determine, based on a result of the comparison, priority of processing on the first image group and processing on the second image group.

Registration of a surgical image acquisition device (e.g. an endoscope) using preoperative and live contour signatures of an anatomical object is described. A control unit includes a processor configured to compare the real-time contour signature to the database of preoperative contour signatures of the anatomical object to generate a group of potential contour signature matches for selection of a final contour match. Registration of an image acquisition device to the surgical site is realized based upon an orientation corresponding to the selected final contour signature match.

The present disclosure provides a three-dimensional posture estimating method and apparatus, a device and a computer storage medium, wherein the method comprises: obtaining two-dimensional posture information of an object in an image and three-dimensional size information of the object; determining coordinates of key points of the object in an object coordinate system according to the three-dimensional size information of the object; determining a transformation relationship between a camera coordinate system and the object coordinate system according to a geometrical relationship between coordinates of key points of the object in the object coordinate system and the two-dimensional posture information of the object. Application of this manner to the field of autonomous driving may implement mapping a detection result of a two-dimensional obstacle to a three-dimensional space to obtain its posture.

An x-ray imaging system data acquisition and image reconstruction system and method are disclosed which enable optimizing the image parameters based on multiple tomographic volumes of the sample that have been captured using an x-ray microscopy system. This enables the operator to control the image contrast, for example, of selected slices, and apply the information associated with optimizing the contrast of the selected slice to all slices in two or more tomographic volume data sets. This creates a combined volume with optimized image contrast throughout. Also, the system enables navigation within the volumes through functional annotation, improvements in volume registration and improvements in noise suppression both within the volumes and within slice histograms of the sample.

A system and a computer-implemented method are provided far segmenting an object in a medical image using a graphical segmentation interface. The graphical segmentation interface may comprise a set of segmentation tools tier enabling a user to obtain a first segmentation of the object in the image. This first segmentation may be represented by segmentation data. Interaction data may be obtained which is indicative of a set of user interactions of the user with the graphical segmentation interface by which the first segmentation of the object was obtained. The system may comprise a processor configured for analyzing the segmentation data and the interaction data to determine an optimized set of user interactions which, when carried out by the user, obtains a second segmentation similar to the first segmentation, yet in a quicker and more convenient manner. A video may be generated for training the user by indicating the optimized set of user interactions to the user.

A tangible, non-transitory, machine-readable medium including instructions presents a graphical user interface (GUI) and the GUI provides an indication of two or more output file types. Further, the medium including instructions receives an indication of a selection of at least two of the two or more output file types. Moreover, the medium including instructions generates corresponding output files for the selection of the at least two of the two or more output file types by accessing an applicable computer-aided-design (CAD) model associated with a part number. Also, the medium including instructions generates corresponding output files for the selection of the at least two of the two or more output file types.