Systems and methods to perform image-based three-dimensional (3D) lane detection involve obtaining known 3D points of one or more lane markings in an image including the one or more lane markings. The method includes overlaying a grid of anchor points on the image. Each of the anchor points is a center of i concentric circles. The method also includes generating an i-length vector and setting an indicator value for each of the anchor points based on the known 3D points as part of a training process of a neural network, and using the neural network to obtain 3D points of one or more lane markings in a second image.

A computer-implemented method is for providing quantitative airway information. In an embodiment, the method includes receiving and/or determining first medical image data of an airway segment; applying a first trained function to the first medical image data, to generate output data; determining the at least one quantitative airway information of the airway segment based on the output data; and providing the at least one quantitative airway information.

Systems and methods to perform image-based three-dimensional (3D) lane detection involve obtaining known 3D points of one or more lane markings in an image including the one or more lane markings. The method includes overlaying a grid of anchor points on the image. Each of the anchor points is a center of i concentric circles. The method also includes generating an i-length vector and setting an indicator value for each of the anchor points based on the known 3D points as part of a training process of a neural network, and using the neural network to obtain 3D points of one or more lane markings in a second image.

The invention relates to an apparatus for identifying a candidate object in image data and determining a likelihood that the candidate object is an object from an object class. The apparatus comprises an image data receiving unit for receiving image data of an object of the object class, a seed element selecting unit for selecting a portion of the image elements as seed elements, a contour point identifying unit for identifying, for each seed element (SE), contour points, the contour points of a seed element circumscribing a candidate object which comprises the seed element, and a seed score determining unit for determining, for each seed element, a seed score indicative of a likelihood that the candidate object is an object from the object class. The invention allows differentiation between an object of an object class of interest and artifacts.

A method, for two-dimensional mapping of anatomical structures of a patient, includes acquiring three-dimensional image data of anatomical structures of a patient; adapting a virtual network structure to a spatial course of the anatomical structures; defining a user-defined map projection for projection of two-dimensional pixel positions of an image to be output onto a geometric figure around a center of the anatomical structures for which mapping onto a two-dimensional space is defined; ascertaining points of intersection of radially extending half lines assigned to the two-dimensional pixel positions of the image to be output with the virtual network structure; and ascertaining the image to be output based upon image intensity values assigned to the points of intersection ascertained. A method for two-dimensional mapping of the tree-like elongated structure of the patient; a method for simultaneous mapping of a tree-like elongated structure; and corresponding apparatuses are also described.

An image processing method that includes setting a plurality of search areas of a predetermined size having mutually different circumferential positions along a peripheral edge part and extending in a radial direction from a center of a recess toward the peripheral edge part near the peripheral edge part in an image, executing an edge detection in each search area to obtain detected edge position and edge intensity for each search area, obtaining a relative shift amount for making a degree of similarity of image patterns highest for each search area when another search area adjacent to the search area in the circumferential direction is shifted in the radial direction with respect to the search area, and specifying a position of the boundary in one search area based on the edge positions, the edge intensities and the relative shift amounts in the search area and each of the search areas in neighboring ranges in the circumferential direction.

In part, the invention relates to systems and methods of calibrating a plurality of frames generated with respect to a blood vessel as a result of a pullback of an intravascular imaging probe being pullback through the vessel. A calibration feature disposed in the frames that changes between a subset of the frames can be used to perform calibration. Calibration can be performed post-pullback. Various filters and image processing techniques can be used to identify one or more feature in the frames including, without limitation, a calibration feature, a guidewire, a side branch, a stent strut, a lumen of the blood vessel, and other features. The feature can be displayed using a graphic user interface.

Methods, devices and systems, including computer-implemented methods for building a lipid core plaque (LCP) cap collagen structural integrity classifier are described. The blood vessel wall is illuminated with near-infrared light. Reflected near-infrared light from the blood vessel wall is received. A reflectance spectrum based on the reflected near-infrared light from the blood vessel wall is determined. Whether the reflectance spectrum is indicative of the presence of an LCP is determined. Collagen structural integrity indicator data associated with the blood vessel wall are determined. The LCP cap collagen structural integrity classifier is generated based on the reflectance spectrum and the collagen structural integrity indicator data.

A method for use in medical imaging of a patient including, with the patient immobilized with respect to an imaging reference frame, acquiring first digital imaging information including a first region of interest using a first imaging modality; processing the first digital imaging information to identify a feature for analysis; and using a second imaging modality to acquire targeted second imaging information for a second region of interest, the second region of interest corresponding to a subset of the first region of interest, wherein the second region of interest includes the feature for analysis. An apparatus for use in medical imaging comprising structure for immobilizing a patient with respect to an imaging reference frame; a first imaging system for acquiring first digital imaging information including a first region of interest using a first imaging modality; a processor processing the first digital imaging information using a diagnostic tool to identify a feature of interest; and a second imaging system for acquiring second imaging information using a second imaging modality, the second imaging information corresponding to a second region of interest including the feature for analysis.

A robotic system includes a robot having an associated workspace; a vision sensor constructed to obtain a 3D image of a robot scene including a workpiece located in the workspace; and a control system communicatively coupled to the vision sensor and to the robot. The control system is configured to execute program instructions to filter the image by segmenting the image into a first image portion containing substantially only a region of interest within the robot scene, and a second image portion containing the balance of the robot scene outside the region of interest; and by storing image data associated with the first image portion. The control system is operative to control movement of the robot to perform work, on the workpiece based on the image data associated with the first image portion.