Systems and methods are disclosed for generating synthetic medical images, including images presenting rare conditions or morphologies for which sufficient data may be unavailable. In one aspect, style transfer methods may be used. For example, a target medical image, a segmentation mask identifying style(s) to be transferred to area(s) of the target, and source medical image(s) including the style(s) may be received. Using the mask, the target may be divided into tile(s) corresponding to the area(s) and input to a trained machine learning system. For each tile, gradients associated with a content and style of the tile may be output by the system. Pixel(s) of at least one tile of the target may be altered based on the gradients to maintain content of the target while transferring the style(s) of the source(s) to the target. The synthetic medical image may be generated from the target based on the altering.

A projection device and a projection image correction method are provided. Four target coordinates of four target vertices forming a target quadrilateral boundary are obtained. A first trapezoidal boundary is obtained according to a predetermined image boundary and a first coordinate component of each of the four target coordinates. At least one edge of the target quadrilateral boundary is extended until intersecting with at least one of two reference line segments to obtain a second trapezoidal boundary. Bases of the first trapezoidal boundary are perpendicular to bases of the second trapezoidal boundary. First direction scaling processing is performed according to the first trapezoidal boundary, and second direction scaling processing is performed according to the second trapezoidal boundary, to scale an original image into a target image block aligned with the target quadrilateral boundary in an output image. The projection device projects the output image to display a rectangular projection image.

A method for processing an image is provided in which an omnidirectional image is received. The omnidirectional image is displayed on a display. Two panoramic images are generated based on the omnidirectional image by correcting distortion of the omnidirectional image. The two panoramic images are displayed on the display in response to a user input. Both of the two panoramic images are scrolled in response to a user input conducted on one of the two panoramic images displayed on the display.

Techniques are provided for segmentation of objects, in videos comprising a sequence of color and depth image frames. A methodology implementing the techniques according to an embodiment includes receiving image frames, including an initial reference frame, and receiving a mask to outline a region in the reference frame that contains the object to be segmented. The method also includes calculating Gaussian mixture models associated with both the masked region and a background region external to the masked region. The method further includes segmenting the object from a current frame based on a modelling of the pixels within an active area of the current frame as a Markov Random Field of nodes for cost minimization. The costs are based in part on the Gaussian mixture models. The active area is based on the segmentation of a previous frame and on an estimation of optical flow between the previous frame and the current frame.

In the present invention, a system and method for selection of an optimal catheter for use in a medical procedure relative to the anatomy of a patient includes the steps of providing a system including a scanning device capable of obtaining image data on a ROI within the anatomy of a patient and reconstructing a 3D image of the ROI from the image data, a display capable of illustrating the 3D image and a 3D catheter model, and a CPU operably connected to the scanning device and the display and operable to analyze the 3D image in comparison with the 3D catheter model, obtaining image data of the ROI of the patient, reconstructing a 3D image of the ROI from the image data and comparing the 3D catheter model with the 3D image of the ROI to determine the catheter with the optimal configuration for use in the procedure.

Systems and methods are disclosed for anatomic structure segmentation in image analysis, using a computer system. One method includes: receiving an annotation and a plurality of keypoints for an anatomic structure in one or more images; computing distances from the plurality of keypoints to a boundary of the anatomic structure; training a model, using data in the one or more images and the computed distances, for predicting a boundary in the anatomic structure in an image of a patient's anatomy; receiving the image of the patient's anatomy including the anatomic structure; estimating a segmentation boundary in the anatomic structure in the image of the patient's anatomy; and predicting, using the trained model, a boundary location in the anatomic structure in the image of the patient's anatomy by generating a regression of distances from keypoints in the anatomic structure in the image of the patient's anatomy to the estimated boundary.

According to one exemplary implementation, a method for use by a global illumination system including a hardware processor includes identifying, using the hardware processor, a first interior vertex of multiple first interior vertices of a light path, the first interior vertices being situated within a volume having a refractive boundary. In addition, the method includes determining, using the hardware processor, a surface vertex of the light path at the refractive boundary, and determining, using the hardware processor, a linear direction from the surface vertex to a light source of the light path. The method also includes determining, using the hardware processor, one or more second interior vertices for completing the light path by constructing a path from the surface vertex to the first interior vertex, based on the linear direction, the surface vertex and the first interior vertex.

A computer implemented method to present digital images may include storing a digital image in a database and applying a digital image processing technique to the digital image to identify a region of interest of the digital image. The method may also include storing region data that identifies the region of interest of the digital image in the database and receiving a request for information associated with the digital image from a digital device. In response to the request, the method may include providing the digital image and the region data for transmission to the digital device, the digital device configured to adjust a cropping view of the digital image based on the region data to display the region of interest of the digital image.

A method and device for automatically identifying a point of interest (e.g., the deepest or highest point) on a viewed object using a video inspection device. The method involves placing a first cursor on an image of the object to establish a first slice plane and first surface contour line, as well as placing another cursor, offset from the first cursor, used to establish an offset (second) slice plane and an offset (second) surface contour line. Profile slice planes and profile surface contour lines are then determined between corresponding points on the first surface contour line and the offset (second) surface contour line to automatically identify the point of interest.

This disclosure relates to system and methods for segmenting a video in a higher order dimensional space. A video may be segmented by obtaining visual information defining an image of the video. The visual information may include pixels of the image and may be represented in a display space having a first dimensionality. A designation of a subset of the visual information represented in the display space as a part of an object portrayed in the image may be obtained. The visual information and the designation may be represented in the higher order dimensional space having a second dimensionality greater than the first dimensionality. An association of the visual information represented in the higher order dimensional space with the object may be obtained. The association may be correlated with the visual information represented in the display space. The correlation may define a location of the object in the image.