Automatic identification method of epidermal layers in skin optical coherence tomography images

Abstract

A method for automatic identification of epidermal layers in optical coherence tomography (OCT) images of skin. This method first finds the maximum position of the axial gradient in each column in the two-dimensional skin OCT image, and combines the boundary continuity to obtain the air-epidermal boundary line; then takes out a certain number of pixels in the depth direction of each boundary pixel in the image to form a new Image, the new image is processed by sliding window to get the average signal of each column, and the approximate area of ​​the epidermis-dermis boundary is obtained according to the peak value; the continuous gradient boundary line is obtained by multi-scale topological transfer; seed filling and morphological algorithms are used in this image Identify the area where the epidermis is located, and extract the boundary position of the epidermis area through the boundary tracking algorithm. The present invention does not require manual identification, can automatically segment the curved mastoid structure at the boundary between the epidermis and the dermis, and is suitable for OCT images of skin whose signal strength in the dermis is weakened due to diseases such as dermatitis.

Description

technical field [0001] The present invention relates to optical coherence tomography (OCT for short), in particular to a method for automatically extracting information in a skin optical coherence tomography image, more precisely a method for extracting information in a skin optical coherence tomography image. A method for automatic identification of epidermal layers. Background technique [0002] Optical coherence tomography (OCT) is a biomedical imaging technology based on low-coherence light interferometry to detect backscattered light from samples. structure. In the early 1990s, J.G.Fujimoto and D.Huang of the Massachusetts Institute of Technology proposed this concept for the first time, and obtained structural images of retinal and coronary artery plasma tissues. In recent years, its application fields have gradually expanded, including dermatology, cardiovascular, dentistry and neurology. [0003] Human skin is a complex system composed of different layers. Aging ...

AI Technical Summary

Problems solved by technology

[0009] All of the above methods can identify the epidermis, but the manual method takes a long time and is greatly influenced by the subjectivity of the measurer; the method of prior art 2 can only obtain the average thickness of the epidermis, which can be judged according to the peak value of the gray scale of the image column The dividing line method has only one epidermis-dermis dividing point in each column by default, and the curved papillae structure on the epidermis-dermis dividing line cannot be recognized; the method in the prior art 3 considers the image intensity from the low reflection to the higher reflection band The excessive changes of the epidermis-dermis boundary, but for psoriasis and other diseases caused by the decrease in the strength of the dermis, such as the image in the prior art 1, the judgment results of this method are quite different from the results of the epidermis obtained by histology

Images