Method and device for quick segmentation of optical coherence tomography image

A method for quick segmentation of an optical coherence tomography image, comprising steps of:

• extracting a feature value related to a pixel in the optical coherence tomography image from the pixel to obtain a feature value representative of the pixel feature, the extracted feature value including at least one of an intensity gradient value of the pixel, an intensity multi-scale mean value of the pixel, or an angular feature value extracted from the pixel;
• inputting the extracted feature value into a Sparse Bayesian Classification model containing values related to image features corresponding to a border, to obtain a probability that the image feature belongs to features of various image region borders;
• and
• obtaining borders of various image regions contained in a predefined image region based on the probabilities obtained for various pixels in the predefined image region,
• wherein the step of extracting a feature value related to a pixel in the optical coherence tomography image from the pixel to obtain a feature value representative of the pixel feature comprises:
• extracting a plurality of feature values related to a pixel in the optical coherence tomography image from the pixel to obtain a feature value vector representative of the pixel feature,
• wherein the extracted feature values include the intensity gradient value and intensity multi-scale mean value of each pixel, and the step of inputting the extracted feature values into a Sparse Bayesian Classification model containing values related to image features corresponding to the border to obtain a probability that the image feature belongs to features of various image region borders comprises:
• inputting the extracted feature value vector into a Sparse Bayesian Classification model containing related vectors of the intensity gradient value and intensity multi-scale mean value of a border pixel, to obtain a probability that the image feature belongs to features of various image region borders.