Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaptive image alignment using locally optimal transformations

An image, image-in-image technology, applied in the field of digital pathology, can solve problems of deformation, local calibration error, manual correction, etc.

Active Publication Date: 2019-12-20
GOOGLE LLC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing techniques either use rigid transformations (leading to local calibration errors), deformations (leading to distortion of cellular and morphological features), or require manual correction by the user

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adaptive image alignment using locally optimal transformations
  • Adaptive image alignment using locally optimal transformations
  • Adaptive image alignment using locally optimal transformations

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Without loss of generality, we describe the calibration of two images below, it being understood that the same process described below will apply when calibrating N images, where N is an integer greater than or equal to 2.

[0042] Calibrating two images A and B is typically done by identifying salient features common to both images (e.g. using SIFT, the scale-invariant feature transform), correlating feature pairs of A and B, and then finding a map that maps image B to image A (or A to B, or both to a virtual middle ground, without loss of generality) to accomplish this.

[0043] Image maps include different transformation operations, including all or a subset of: 1) translation, 2) rotation, 3) scaling, 4) shearing, 5) perspective, and 6) deformation. Transformations that include only (1)-(2) are called rigid transformations, only (1)-(4) are called affine transformations, and transformations potentially include all these operations that cause local deformation of the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for aligning two different magnified images of the same subject includes a first step of precomputing rigid transformations for the two different images globally (i.e., for all or approximately all regions of the images). Pairs of corresponding features in the two different magnified images are identified and transformation values are assigned to each of the pairs of corresponding features, in a second step, while images are being generated for display to a user, a locally optimal rigid transformation for the current field of view is computed, in a third step the images are aligned asper the locally optimal rigid transformation. Non-zero weight is given to transformation values for pairs of features that are outside the current field of view. Typically, the second and third stepsare repeated many times as the images are generated for display and user either changes magnification or pans / navigates to a different location in the images.

Description

Background technique [0001] The present disclosure relates to the field of digital pathology, and more particularly to methods for calibrating a pair of corresponding images, typically very large images, e.g., gigapixel histopathology tissue images, for use together Observe the image. For example, the pair of images can be two different images of the same tissue, e.g., one image (image A) of a slide of a tissue section stained with hematoxylin and eosin (H&E) and stained with, for example, immunohistochemistry (IHC). ) another image of an adjacent tissue section stained with a particular stain for the stain (image B). [0002] In some applications, such as cancer diagnosis, precise local calibration is important, eg displaying H&E stained images next to IHC-stained serial section images. At the same time, when generating calibration images, it is important that the tissue images are not distorted, since viewing an image in the presence of distortion may affect the diagnosis ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/33
CPCG06T7/33G06T2207/30024G06T3/20G06T3/40G06T2207/10056G06T2207/20092
Inventor M.斯顿普V.戈德博尔
Owner GOOGLE LLC