6 results about "Image Reslicing" patented technology

This invention discloses a large image processing method and system based on adaptive slicing and feathering fusion, comprising: acquiring the original image and parameters; adaptively determining the slicing parameters through iterative calculation with a minimum overlap width requirement as a constraint, and outputting slicing configuration information; expanding the boundaries of the original image according to the filling amount, and extracting multiple image slices with sizes conforming to the input size of the target processing unit from the expanded image; and performing feathering fusion and layered stitching on the image slices using a weight mask generated based on a Gaussian function based on the overlap size to reconstruct a final image with the same size as the original image. This invention calculates the minimum slice grid layout required to meet seamless stitching quality requirements. Through the synergy of reflection filling and Gaussian weighted feathering fusion techniques, it achieves imperceptible pixel value changes at the seams while minimizing the total number of calls to downstream processing units, thereby resolving the contradiction between image quality and computational cost.

A method for decoding a picture from a bitstream. In one embodiment, The method includes: receiving a slice header for a slice of the picture, wherein the slice header comprises a state syntax element; decoding a state value from the state syntax element in the slice header, wherein a) if the state value is not equal to a first value, then the state value indicates that i) the bitstream includes for the picture a picture header comprising a set of picture syntax elements and ii) the slice header does not comprise the set of picture syntax elements and b) if the state value is equal to the first value, then the state value indicates that i) the slice header contains said set of picture syntax elements and ii) the bitstream does not include a picture header for the picture; and using the set of picture syntax elements to decode the slice of the picture.

The present invention discloses a method, device, medium, and equipment for determining the number of slice layers in a three-dimensional image, relating to the field of three-dimensional display imaging technology. The method includes: determining the number of left neighboring slice layers N‑n and the number of right neighboring slice layers N+n based on the initial number of slice layers N and the initial search range n; obtaining restored three-dimensional images corresponding to the number of layers N, N‑n, and N+n, capturing two-dimensional plane images of the restored three-dimensional image from different angles, and obtaining characteristic values ​​for characterizing the quality of the restored three-dimensional image based on the pixel distribution in the two-dimensional plane images at different angles; using the number of slice layers with the optimal characteristic value as the new initial number of slice layers, and repeating the operation until the optimal number of slice layers is obtained. By analyzing the pixel distribution in the two-dimensional plane images of the restored three-dimensional image captured at different angles, the quality of the restored three-dimensional image can be quantified more comprehensively and accurately, thereby obtaining the number of slices that maximizes the imaging mechanical efficiency and achieves the best imaging effect.

A device (12) is presented that receives image data comprising an ROI (108), and generates a volumetric segmentation of the ROI by using a first machine learning method to generate a segmentation of a first image slice comprising the ROI and a second machine learning method to adapt the segmentation to one or more slices neighboring the first image slice, the segmentation comprising a 2D segmentation (110).

Some embodiments relate to 3D visualization of medical image data. An overlay may be generated from a particular 2D image slice of the plurality of 2D image slices and anatomical entities segmented therein. In the overlay, the segmented anatomical entities are interactive for selection or deselection. A 3D visualization is displayed in which the selected one or more anatomical entities are visually distinguishable.

A method for constructing a dynamic 3D mesh model of an anatomical region is disclosed. The method includes constructing a 3D volume of the anatomical region based on a plurality of DICOM image slices of the anatomical region and a verified 3D mesh model of the anatomical region. The method further includes segmenting, based on the verified 3D mesh model, the 3D volume to generate one or more segmented volumes using a deep-learning based volume segmentation model. The method further includes constructing a dynamic 3D mesh model of the anatomical region based on the one or more segmented volumes. The dynamic 3D mesh model is indicative of structural and functional characteristics of the anatomical region.