WO2022007353A1 - Method and apparatus for enhancing choroid oct image on basis of signal reverse compensation - Google Patents

Abstract

A method and apparatus for enhancing a choroid OCT image on the basis of signal reverse compensation. After preprocessing a choroid image signal obtained by a system, establish, on the basis of the idea of the reverse compensation of an OCT backscattered signal, a reverse signal attenuation compensation model, reversely compensate the choroid signal, and enhance the signal-to-noise ratio between blood vessels and non-vascular tissue, thus solving the defect in which the boundary of a choroid vessel OCT image is difficult to segment.

Description

A method and device for choroidal OCT image enhancement based on signal inverse compensation technical field

The present invention relates to the technical field of OCT, in particular to a method and device for enhancing choroidal OCT images based on signal inverse compensation.

Background technique

The choroid is a highly vascularized and pigment-rich tissue located between the retina and sclera. The main function is to provide oxygen and nutrients to the RPE and the outer layer of the retina. The oxygen transported accounts for about 90% of the retinal oxygen consumption and is necessary to maintain the high metabolic activity of photoreceptor cells in the outer layer of the retina; especially in the fovea of the macula without blood vessels The choroid is the only way of its material exchange. Many diseases are closely related to the abnormal vascular structure of the choroid, such as age-related macular degeneration, high myopia macular degeneration, diabetic retinopathy and so on. Therefore, it is of great significance to realize the quantitative analysis of choroidal vessels.

Frequency domain optical coherence tomography technology can realize three-dimensional imaging of fundus. After averaging image enhancement technology or using high-penetration swept frequency light source, it can display the complete choroidal vascular tissue and stromal tissue, which is very beneficial for choroidal vascular analysis. imaging technology. However, the current system does not solve the problem of poor signal-to-noise ratio of blood vessels in the deep choroid caused by backscatter attenuation, which leads to the difficulty of segmentation of blood vessel boundaries. For this reason, most of the quantitative choroidal blood vessel analysis algorithms in OCT images only use traditional image processing methods. However, because the choroid is located below the RPE, the light passes through the RPE and is attenuated by pigment absorption. Attenuation of the light signal occurred at the depth of the choroid, resulting in blurring of the border between the choroid and the pigment epithelium and the border between the choroid and the sclera.

SUMMARY OF THE INVENTION

In order to solve the problems existing in the prior art, the present invention provides a choroidal OCT image enhancement method and device based on inverse signal compensation. An inverse signal attenuation compensation model was established to inversely compensate the choroidal signal and enhance the signal-to-noise ratio between vascular and non-vascular tissues.

The technical solution adopted in the present invention is: a choroid OCT image enhancement method based on signal inverse compensation, comprising the following steps:

(1) Data acquisition: use OCT to acquire fundus images, preprocess the images including appropriate cropping, and retain the OCT choroidal intensity map;

(2) Reverse attenuation compensation for choroidal signal: By extracting the attenuation principle and law of choroidal scattered light, and constructing a signal compensation and enhancement algorithm, the visualization and contrast of choroidal images can be improved.

The step (2) inversely attenuating and compensating the choroidal signal specifically includes the following steps: by extracting the attenuation principle and law of choroidal scattered light, constructing a signal compensation and enhancement algorithm, which can improve the visualization and contrast of the choroidal image, and an attenuation correction processing algorithm for the OCT signal. It consists of two steps, namely, the attenuation compensation of light and the contrast of image enhancement. In the OCT system, the photoelectric signal of the interference between the reference arm and the sample arm can be expressed by the following formula:

Where k is the wave number, wave number of signal acquisition is divided into equally spaced m, [rho] is the photoelectric conversion efficiency OCT probe, S [k _m] refers to the wavelength band corresponding radiant energy source, is [Delta] x between the reference arm and the sample arm optical path difference, R _R and R _S are the reflectances of the reference arm and the sample arm, respectively;

_{The interaction term H[k m} ] between the reference arm and the sample arm can be obtained from the above formula (1):

The reflectivity profile function S(z) along the depth direction can be obtained by performing inverse discrete Fourier transform on the above formula (2):

By discretizing the formula, attenuation correction compensation can be performed on the OCT signal of each pixel:

where N is the number of pixels in the A scan, and α can be adjusted according to the tissue. The premise of the above formula (3) is to assume that most of the beam energy is attenuated within the imaging depth range, and the attenuation outside the imaging depth range can be ignored.

The original signal after attenuation correction and compensation will be exponentiated to enhance the image contrast. At this time, the signal intensity of each pixel is:

In formula (5), S _ac (z) is the signal after attenuation correction.

A choroidal OCT image enhancement device based on signal inverse compensation, comprising the following modules,

Input module: used to input OCT choroid intensity map;

Image processing module: By extracting the principle and law of choroidal scattered light attenuation, a signal compensation and enhancement algorithm is constructed to improve the visualization and contrast of choroidal images;

Output module: used to output the map after attenuation correction to remove artifacts.

The image processing module includes the following algorithm models: by extracting the choroidal scattered light attenuation principle and law, the attenuation correction processing algorithm of the OCT signal, to improve the visualization and contrast of the choroidal image, the attenuation correction processing algorithm of the OCT signal includes two steps, respectively. For light attenuation compensation and image enhancement contrast, in the OCT system, the photoelectric signal of the interference between the reference arm and the sample arm can be expressed by the following formula:

Where k is the wave number, wave number of signal acquisition is divided into equally spaced m, [rho] is the photoelectric conversion efficiency OCT probe, S [k _m] refers to the wavelength band corresponding radiant energy source, is [Delta] x between the reference arm and the sample arm optical path difference, R _R and R _S are the reflectances of the reference arm and the sample arm, respectively;

_{The interaction term H[k m} ] between the reference arm and the sample arm is obtained from the above formula (1):

The reflectivity profile function S(z) along the depth direction is obtained by performing inverse discrete Fourier transform on the above formula (2):

The formula is discretized, and the OCT signal of each pixel is subjected to attenuation correction compensation:

where N is the number of pixels in the A scan, and α can be adjusted according to the tissue. The premise of the above formula (3) is to assume that most of the beam energy is attenuated within the imaging depth range, and the attenuation outside the imaging depth range can be ignored.

The original signal after attenuation correction and compensation will be exponentiated to enhance the image contrast. At this time, the signal intensity of each pixel is:

In formula (5), S _ac (z) is the signal after attenuation correction.

The beneficial effects of the present invention are as follows: the present invention provides a choroidal OCT image enhancement method and device based on inverse signal compensation. The inverse signal attenuation compensation model reversely compensates the choroidal signal and enhances the signal-to-noise ratio between blood vessels and non-vascular tissues, thereby solving the defect that the boundary of the choroidal blood vessel OCT image is difficult to segment.

Description of drawings

FIG. 1 is a flow chart of the technical solution of the present invention.

Figure 2 shows OCT fundus image acquisition and preprocessing.

Figure 3 is a schematic diagram of choroidal signal attenuation correction and image contrast de-enhancement; the left image is the original image, and the right image is the image after attenuation correction to remove artifacts.

Figure 4 shows the comparison between the traditional dynamic programming algorithm and the deep learning automatic segmentation of the inner and outer boundaries of the choroid; the left picture is the result of the traditional algorithm, and the right picture is the result of the deep learning algorithm.

Figure 5 shows the self-adaptive threshold to separate the choroidal vessels and non-vessels; the upper image is a high myopia, and the lower image is an emmetropic eye.

Figure 6 is a diagram of the choroidal blood vessels after three-dimensional reconstruction.

detailed description

The present invention can be better described below with reference to the accompanying drawings and some specific embodiments.

(1) Data acquisition and preprocessing:

The fundus images were obtained using current commercial instruments or self-built OCT, and the images were preprocessed including appropriate cropping, and the OCT choroid intensity map was retained, as shown in Figure 2.

(2) Reverse attenuation compensates the choroidal signal:

The signals received by the OCT detector are backscattered and reflected signals. Due to the influence of RPE and choroid's own pigment on light absorption, the light scattering of a certain wavelength is lost. By extracting the principle and law of choroid scattered light attenuation, and constructing a signal compensation and enhancement algorithm, the visualization and contrast of choroid images can be improved.

The attenuation correction processing algorithm of OCT signal includes two steps, which are the attenuation compensation of light and the contrast of image enhancement. In the OCT system, the photoelectric signal of the interference between the reference arm and the sample arm can be expressed by the following formula:

Where k is the wave number, wave number of signal acquisition is divided into equally spaced m, [rho] is the photoelectric conversion efficiency OCT probe, S [k _m] refers to the wavelength band corresponding radiant energy source, is [Delta] x between the reference arm and the sample arm The optical path difference, R _R and R _S are the reflectances of the reference arm and the sample arm, respectively. _{The interaction term H[k m} ] between the reference arm and the sample arm can be obtained from equation (1):

The reflectivity profile function S(z) along the depth direction can be obtained by performing the inverse discrete Fourier transform on equation (2):

The conditions for the establishment of formulas (1)-(3) are assuming that the beam does not undergo energy attenuation during the propagation process. But the beam will decay in energy during propagation, so we need to improve the above formula. When the light beam penetrates the tissue sample, a small part is converted into heat and the rest is scattered, at which point the light beam is attenuated by absorption. Assuming that the local attenuation of the beam is only related to the scattering of light and backscattered at a fixed proportion, it can be calculated that the local attenuation of the beam at depth Z is proportional to the reflectivity R and the backscattering constant α at that location.

In practice, the attenuated signal DA is obtained after OCT direct data processing, not the original signal S(z). This is the main reason why shadows appear in strongly attenuated tissues such as blood vessels and pigments, that is, the reason for the appearance of artifacts. In order to correct the attenuated signal, the attenuation term needs to be removed, which also removes artifacts. By discretizing the formula, attenuation correction compensation can be performed on the OCT signal of each pixel:

where N is the number of pixels in the A scan, and α can be adjusted according to the tissue. The premise of the above formula is that most of the beam energy is attenuated within the imaging depth range, and the attenuation outside the imaging depth range is negligible.

In the later stage, the present invention will perform an exponentiation operation on the original signal after the attenuation correction and compensation to enhance the image contrast, and the signal intensity of each pixel is now:

where S _ac (z) is the signal after attenuation correction, as shown in FIG. 3 .

(3) Deep learning intelligent segmentation:

Accurate identification of the inner and outer boundaries of the choroid is an important step to accurately quantify the three-dimensional vascular indices of the choroid.

The suprachoroidal border was defined as the dividing line between Bruch's membrane and the retinal pigment epithelium (RPE), and the inferior choroidal border was defined as the dividing line between the choroid and the sclera. Since the RPE layer appears as a high signal band in the OCT image, based on the traditional shortest path graph theory algorithm, the automatic segmentation of the suprachoroidal border can be well achieved; however, the contrast of the dividing line between the choroid and the sclera on the OCT image is poor, It is difficult to realize the automatic segmentation of the lower boundary by the shortest path graph theory algorithm. As the most important breakthrough in the field of artificial intelligence, deep learning has made great breakthroughs in the field of computer vision. The efficiency of deep learning-based algorithms is significantly better than traditional algorithms. The present invention will establish a deep learning segmentation model to realize the automatic segmentation of the upper and lower boundaries of the choroid, and the specific steps are as follows:

①Based on the traditional shortest path graph theory algorithm and semi-automatic labeling of the inner and outer boundaries of the choroid in thousands of OCT images, the upper and lower boundaries of the choroid in the images are accurately depicted; the labeled choroid image set is randomly divided into the training set according to 8:2 , two parts of the test set.

② Input the training image into the open source deep learning neural network model, the training optimization algorithm is set to stochastic gradient descent (SGD), the algorithm learning ratio is 1.0e-5, the iterative momentum is 0.9, and the iterative cost function is the Dice coefficient (dice coefficient). ), the number of iterations (epoch) is 150, and the batch size (batch size) is 8. In addition, necessary enhancement processing (such as translation, rotation and flipping, etc.) is performed on the input image to improve the robustness of the model. Among them, the calculation formula of Dice coefficient is:

X represents the choroidal boundary prediction set, Y represents the choroidal boundary annotation set, |X∩Y| represents the intersection or overlap between the two sets, and |X|+|Y| represents the total amount of both. The larger the Dice coefficient, the higher the similarity between the two sets and the more accurate the model; when the prediction set is exactly the same as the annotation set, the Dice coefficient is 1; when the prediction set is not related to the annotation set, the Dice coefficient is 0. During the model training process, set the Dice coefficient greater than 0.95 as the objective function.

② Input the test set images into the deep learning neural network model, and calculate the Dice coefficient and boundary error between the output results of the choroid boundary and the label set to evaluate the segmentation performance of the deep learning neural network model. The results are shown in Figure 4 and Table 1.

③Table 1 The performance of deep learning in segmenting the choroidal boundary of OCT images

(4) Adaptive threshold to separate choroidal vessels and non-vessels: choroidal vessels and stroma show different characteristics in OCT images, in which vessels are dominated by low-intensity signals, while stroma is dominated by high-intensity signals. Since the brightness of the choroidal signal in the OCT image is affected by related factors such as the RPE layer, the type of instrument, and the focus during the operation, the separation of choroidal blood vessels and stroma based on the fixed threshold method has great limitations in theory, and the universality is poor. . In contrast, based on the adaptive threshold, the interference effect caused by the overall shift of the choroidal signal brightness can be better avoided, and the automatic separation of the choroidal blood vessels and the stroma can be better achieved. The process of the method is as follows:

① In the OCT image, a square box with a length and width of 2*w+1 pixel blocks is used as a local window. The coordinates (x, y) are the geometric center of the square frame, and the brightness information of all pixel blocks in the frame is counted to obtain the mean m(x, y) and variance s(x, y). According to the parameter k, the threshold value T(x, y) in the frame can be obtained, and the calculation formula is as follows:

T(x,y)=m(x,y)+k*s(x,y) (7)

②According to the threshold T(x,y) in the frame, all pixel blocks in the frame can be binarized, as shown below:

where i and j are the relative coordinates representing the relative geometric center (x, y) of the pixel block, A _{x+i, y+j} represents the brightness of the pixel block with coordinates (x+i, y+j), A _{x+i, y +j} represents the binarized data of the pixel block of coordinates (x+i, y+j).

③ By moving the local windows in turn, the binarization process of the brightness matrix A of all pixel blocks in the OCT image can be realized, and the binarization matrix B can be obtained. The results are shown in Figure 5.

(5) Three-dimensional global and regional quantitative indicators:

Based on a single OCT image, only the characteristic information of a certain cross-section of the choroid can be obtained, but due to the uneven spatial distribution of some choroidal lesions, it is difficult to accurately assess the disease progression through a single OCT image analysis mode. The present invention will image the fundus through the radial scanning mode, obtain the choroid three-dimensional space data, register and reconstruct the image, and realize the choroid three-dimensional space reconstruction. In the OCT image, the fovea is used as the reference point, and the position of the fovea is horizontally shifted, so that the abscissa of the fovea in all OCT images is the same in space coordinates, and the three-dimensional image reconstruction is realized. The distribution and proportion of choroidal ischemia were calculated, and the global and regional quantitative indicators that could characterize choroidal ischemia were calculated. Specific steps are as follows:

①Image acquisition: Take the fovea of the fundus as the center, perform imaging in radial scanning mode, and obtain m pieces of two-dimensional cross-sectional data of the choroid.

② Feature point marking: Since all OCT images contain the characteristic structure of the fovea, the present invention uses the fovea as the feature point of the OCT image for marking for subsequent image registration.

③Image registration: By translating the position of the fovea horizontally, the fovea in all OCT images has the same abscissa in the spatial coordinates to achieve image registration.

④Three-dimensional reconstruction of the choroid: Based on the upper and lower bounds of the choroid obtained by the deep learning neural network model, the choroid region template M(x, y, z) in the registered image is extracted, and the blood vessels and the matrix are automatically separated by the adaptive threshold method. The binarized three-dimensional space choroid structure matrix V(x, y, z) is obtained.

⑤Indices establishment and testing: We established choroidal vascular volume CVV, choroidal non-vascular volume SV, choroidal vascular index CVI and choroidal ischemia index CII for quantification. The calculation formula of each indicator is as follows:

where P _x , P _y , and P _z represent the physical geometric lengths of voxels along the x, y and z axes in three-dimensional space, respectively. n, m and k represent the number of pixels along the x, y and z axes in the three-dimensional space matrix, respectively.

In the present invention, the same operator repeatedly performs OCT imaging on the same subject twice to test the repeatability of the index, and compare it with the corresponding two-dimensional index. The test results are shown in the following table.

		0-6mm	Left 3-6mm	Left 1-3mm	0-1mm	Right 1-3mm	Right 3-6mm
CVV	vertical	0.995	0.989	0.987	0.985	0.963	0.964
	level	0.994	0.981	0.98	0.99	0.96	0.989
	three-dimensional	0.998	0.997	0.998	0.997	0.998	0.999
CVI	vertical	0.883	0.736	0.815	0.814	0.714	0.731
	level	0.865	0.664	0.798	0.864	0.786	0.541
	three-dimensional	0.991	0.986	0.965	0.975	0.983	0.982
CII	vertical	0.883	0.736	0.815	0.814	0.714	0.731
	level	0.865	0.664	0.798	0.864	0.786	0.541
	three-dimensional	0.991	0.986	0.965	0.975	0.983	0.982
SV	vertical	0.968	0.86	0.962	0.871	0.927	0.934
	level	0.935	0.694	0.964	0.939	0.91	0.768
	three-dimensional	0.994	0.977	0.989	0.990	0.994	0.992

It can be seen that the repeatability of the three-dimensional index is significantly better than that of the two-dimensional index. Among the two-dimensional indicators, the repeatability of vertical two-dimensional indicators is better than that of horizontal two-dimensional indicators.

After preprocessing the choroidal image signal acquired by the system, the invention establishes a reverse signal attenuation compensation model based on the idea of reverse compensation of the OCT backscattered signal, reversely compensates the choroidal signal, and enhances the signal-to-noise ratio between blood vessels and non-vascular tissues. And further use the segmentation method based on deep learning to intelligently segment the inner and outer boundaries of the choroid; on the basis of boundary segmentation, an improved adaptive threshold method is further used to automatically separate the three-dimensional choroidal vessels and non-vascular tissues, and based on the blood vessels in the image. The distribution and proportion in the three-dimensional volume space, the global and regional quantitative indicators that can characterize choroidal ischemia are calculated. The method is suitable for all OCT systems and their images that can acquire the choroid with high penetration to the tissue.

The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions that belong to the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those skilled in the art, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims (4)

1. A choroid OCT image enhancement method based on signal inverse compensation, is characterized in that, comprises the following steps:

   (1) Data acquisition: use OCT to acquire fundus images, preprocess the images including appropriate cropping, and retain the OCT choroidal intensity map;

   (2) Reverse attenuation compensation for choroidal signal: By extracting the attenuation principle and law of choroidal scattered light, a signal compensation and enhancement algorithm is constructed to improve the visualization and contrast of choroidal images.
2. The choroidal OCT image enhancement method based on inverse signal compensation according to claim 1, wherein the step (2) inversely attenuating compensation for choroidal signals specifically includes the following steps: extracting the principle and law of choroidal scattered light attenuation by extracting , OCT signal attenuation correction processing algorithm to improve the visualization and contrast of choroid images, OCT signal attenuation correction processing algorithm consists of two steps, respectively, attenuation compensation of light and image enhancement contrast, in the OCT system, the reference arm and the sample arm The photoelectric signal of inter-interference can be expressed by the following formula:

   

   Where k is the wave number, wave number of signal acquisition is divided into equally spaced m, [rho] is the photoelectric conversion efficiency OCT probe, S [k _m] refers to the wavelength band corresponding radiant energy source, is [Delta] x between the reference arm and the sample arm optical path difference, R _R and R _S are the reflectances of the reference arm and the sample arm, respectively;

   _{The interaction term H[k m} ] between the reference arm and the sample arm is obtained from the above formula (1):

   

   The reflectivity profile function S(z) along the depth direction is obtained by performing inverse discrete Fourier transform on the above formula (2):

   

   The formula is discretized, and the OCT signal of each pixel is subjected to attenuation correction compensation:

   

   where N is the number of pixels in the A scan, and α can be adjusted according to the tissue. The premise of the above formula (3) is to assume that most of the beam energy is attenuated within the imaging depth range, and the attenuation outside the imaging depth range can be ignored.

   The original signal after attenuation correction and compensation will be exponentiated to enhance the image contrast. At this time, the signal intensity of each pixel is:

   

   In formula (5), S _ac (z) is the signal after attenuation correction.
3. A choroidal OCT image enhancement device based on signal inverse compensation, characterized in that it includes the following modules:

   Input module: used to input OCT choroid intensity map;

   Image processing module: By extracting the principle and law of choroidal scattered light attenuation, a signal compensation and enhancement algorithm is constructed to improve the visualization and contrast of choroidal images;

   Output module: used to output the map after attenuation correction to remove artifacts.
4. The choroidal OCT image enhancement device based on signal inverse compensation according to claim 1, wherein the image processing module includes the following algorithm model: by extracting the choroidal scattered light attenuation principle and law, the attenuation correction of the OCT signal Processing algorithm to improve the visualization and contrast of choroid images. The attenuation correction processing algorithm of OCT signal consists of two steps, which are the attenuation compensation of light and the contrast of image enhancement. In the OCT system, the photoelectric signal of the interference between the reference arm and the sample arm can be It is expressed by the following formula:

   

   Where k is the wave number, wave number of signal acquisition is divided into equally spaced m, [rho] is the photoelectric conversion efficiency OCT probe, S [k _m] refers to the wavelength band corresponding radiant energy source, is [Delta] x between the reference arm and the sample arm optical path difference, R _R and R _S are the reflectances of the reference arm and the sample arm, respectively;

   _{The interaction term H[k m} ] between the reference arm and the sample arm is obtained from the above formula (1):

   

   The reflectivity profile function S(z) along the depth direction is obtained by performing inverse discrete Fourier transform on the above formula (2):

   

   The formula is discretized, and the OCT signal of each pixel is subjected to attenuation correction compensation:

   

   where N is the number of pixels in the A scan, and α can be adjusted according to the tissue. The premise of the above formula (3) is to assume that most of the beam energy is attenuated within the imaging depth range, and the attenuation outside the imaging depth range can be ignored.

   The original signal after attenuation correction and compensation will be exponentiated to enhance the image contrast. At this time, the signal intensity of each pixel is:

   

   In formula (5), S _ac (z) is the signal after attenuation correction.

Images