Optical coherence angiography imaging method based on machine learning

Abstract

The invention discloses an optical coherence angiography imaging method based on machine learning. According to the method, OCT three-dimensional structure images of a sample are acquired by using OCTA equipment, an original data set required by network model training is generated, a whole group of OCT structure images with a poor registration effect is eliminated, contrast imaging is performed byusing an OCTA algorithm to generate a training data set, a machine learning network model is established, and the machine learning network model is trained; The OCTA radiography is carried out through a machine learning network model; The method can play a huge role in the field of OCTA (Optical Coherence Tomography Angiography), can generate an angiography image with higher signal-to-noise ratioand better vascular connectivity, and inhibits the common speckle effect in the OCT image to a great extent; a label image is automatically generated by an algorithm, so that the applicability of themethod is expanded, and the influence of system errors caused by different systems is avoided; imaging can be performed by using lower detection power to reduce damage, or the data volume required byimaging is reduced during imaging, so that scanning can be completed more quickly.

Description

technical field [0001] The invention relates to an optical coherent angiography imaging technology, in particular to a machine learning-based optical coherence angiography imaging method. Background technique [0002] Optical coherent tomography (Optical Coherent Tomography, OCT) is a high-resolution, non-contact, fast three-dimensional imaging technology. It utilizes the coherence principle of scattered light in biological tissues, and its signal contrast comes from the difference in the light scattering ability of different biological tissues. OCT technology combines semiconductor and ultrafast laser technology, uses broadband light source, Michelson interferometer and photodetector and other core components to obtain the backscattering signal of biological tissue, and finally can obtain the real-time micron level of biological tissue through digital signal processing of computer Tomographic image. Therefore, OCT technology has long been one of the important means of ima...

AI Technical Summary

Problems solved by technology

However, these methods often only use part of the information in the OCT signal, resulting in problems such as low signal-to-noise ratio and serious speckle in contrast images.

At present, the main means to solve this problem is to increase the number of scans at the same position and enhance the intensity of blood vessel signals. This method will lead to too long scan time, and the vibration of the sample will produce artifacts, such as the shaking of the patient's eyes and breathe

In addition, long-term laser irradiation will also cause damage to biological tissues

Images