Subtle cornea deformation identification method and device based on pixel-level corneal biomechanical parameter
AssigneesTianjin Eye Hospital, Wenzhou University of Technology
InventorsYan WANG, Xuan CHEN, Zuoping TAN, Riwei WANG
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a subtle cornea deformation identification method and device based on a pixel-level corneal biomechanical parameter, including the following steps: step 1, sampling and analyzing a dynamic video of corneal stress deformation in a historical database, and calculating pixel-level data; and step 2, configuring an ensemble classifier based on a sampling result and detecting a local change in corneal biomechanics, thus identifying a subtle cornea deformation. The present disclosure has high measurement accuracy and is capable of detecting a local subtle biomechanical change.
Claims5
A subtle cornea deformation identification method based on a pixel-level corneal biomechanical parameter, comprising the following steps:
- step 1, sampling and analyzing a dynamic video of corneal stress deformation in a historical database, and calculating pixel-level data;
- and
- step 2, configuring an ensemble classifier based on a sampling result and detecting a local change in corneal biomechanics, thus identifying a subtle cornea deformation,
- wherein the step 1 is specifically as follows:
- acquiring and partitioning the dynamic video of corneal stress deformation in the historical database, extracting a corneal contour in each position according to a pixel, fitting a curvilinear equation of the corneal contour, and calculating the pixel-level data based on a pixel point;
- and
- the pixel-level data comprises:
- variation of full contour length at first applanation, variation of full contour length at second applanation, maximum depression area, time at the first applanation, time at the second applanation, maximum curvature, depth of a thinnest point at the first applanation, depth of a thinnest point at the second applanation, depth of a thinnest point at maximum depression, length at the first applanation, length at the second applanation, peak distance, relative displacement of a thinnest point (1 mm), and relative displacement of a thinnest point (2 mm).
A subtle cornea deformation identification device based on a pixel-level corneal biomechanical parameter, comprising:
- a pixel-level data computation module, configured to conduct sampling analysis on a dynamic video of corneal stress deformation in a historical database, and to calculate pixel-level data;
- and
- a subtle cornea deformation identification module, configured to configure an ensemble classifier based on a sampling result, and detect a local change in corneal biomechanics, thus identifying a subtle cornea deformation;
- wherein the pixel-level data computation module is specifically configured to acquire and partition the dynamic video of corneal stress deformation in the historical database, extract a corneal contour in each position according to a pixel, fit a curvilinear equation of the corneal contour, and calculate the pixel-level data based on a pixel point;
- and
- the pixel-level data comprises:
- variation of full contour length at first applanation, variation of full contour length at second applanation, maximum depression area, time at the first applanation, time at the second applanation, maximum curvature, depth of a thinnest point at the first applanation, depth of a thinnest point at the second applanation, depth of a thinnest point at maximum depression, length at the first applanation, length at the second applanation, peak distance, relative displacement of a thinnest point (1 mm), and relative displacement of a thinnest point (2 mm).
Dependencies are inferred from the claim text.