PICC (Peripherally Inserted Central Catheter) positioning and identifying device and method based on optical coherence tomography

Abstract

The invention discloses a PICC (Peripherally Inserted Central Catheter) positioning and identifying device and method based on optical coherence tomography. The device comprises an OCT (Optical Coherence Tomography) probe, a signal collecting and processing unit, an image display unit and a position identifying unit, the OCT probe is used for acquiring OCT images of a blood vessel and a PICC catheter in the PICC catheterization process; the signal acquisition and processing unit is used for processing the acquired OCT image signal to obtain a processed OCT image; the image display unit is used for displaying the processed OCT image in real time; and the position identification unit is used for analyzing and identifying the processed OCT image to obtain real-time position information of the PICC catheter, and comparing the real-time position information with a preset optimal position to obtain a position judgment result.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and in particular to a PICC catheter positioning and identification device and method based on optical coherence tomography. Background Art

[0002] In clinical medicine, PICC (Peripherally Inserted Central Catheter) placement is a common operation used to provide patients with long-term intravenous infusion access. Accurate PICC placement positioning is crucial to ensure treatment effectiveness and patient safety. Currently, ultrasound is a commonly used method for PICC placement positioning, but ultrasound imaging may be affected by factors such as patient body shape and operator experience in some cases, resulting in inaccurate positioning. Therefore, a new real-time imaging technology is needed that can provide clearer and more accurate intravascular images during the catheterization process, and the equipment should be portable for use in different medical scenarios. Summary of the invention

[0003] The present invention aims to provide a PICC catheter positioning and identification device and method based on optical coherence tomography (OCT) to solve the problems in the prior art that PICC catheter positioning is not accurate enough and the device is not portable.

[0004] In a first aspect of an embodiment of the present invention, a PICC catheter positioning and identification device based on optical coherence tomography (OCT) is disclosed, comprising: an OCT probe, a signal acquisition and processing unit, an image display unit, and a position identification unit;

[0005] The OCT probe is used to obtain OCT images of the blood vessels and PICC catheter during the PICC catheterization process;

[0006] The signal acquisition and processing unit is connected to the OCT probe and is used to process the acquired OCT image signal to obtain a processed OCT image;

[0007] The image display unit is connected to the signal acquisition and processing unit and is used to display the processed OCT image in real time;

[0008] The position identification unit is connected to the image display unit and the signal acquisition processing unit, and is used to analyze and identify the processed OCT image to obtain the real-time position information of the PICC catheter, compare it with the preset optimal position, and obtain the position discrimination result.

[0009] The OCT probe is implemented using a cardiovascular OCT imaging device.

[0010] The signal acquisition and processing unit is used to process the acquired OCT image signal to obtain a processed OCT image, including:

[0011] The signal acquisition and processing unit performs image denoising on the acquired OCT image signal to obtain a first image signal;

[0012] performing contrast enhancement processing on the first image signal to obtain a second image signal;

[0013] Correction processing is performed on the second image signal to obtain a processed OCT image.

[0014] In a second aspect of an embodiment of the present invention, a method for PICC catheter positioning and identification based on optical coherence tomography is disclosed, which is implemented by using the PICC catheter positioning and identification device based on optical coherence tomography, and includes:

[0015] S1, using the OCT probe to obtain OCT images of the blood vessels and PICC catheter during PICC placement;

[0016] S2, using a signal acquisition and processing unit to process the acquired OCT image signal to obtain a processed OCT image;

[0017] S3, using an image display unit to display the processed OCT image in real time;

[0018] S4, using a position recognition unit to analyze and recognize the processed OCT image to obtain real-time position information of the PICC catheter, and using the real-time position information of the PICC catheter to compare with a preset optimal position to obtain a position determination result.

[0019] The step of processing the collected OCT image signal to obtain a processed OCT image includes:

[0020] S21, performing image denoising processing on the collected OCT image signal to obtain a first image signal;

[0021] S22, performing contrast enhancement processing on the first image signal to obtain a second image signal;

[0022] S23, performing correction processing on the second image signal to obtain a processed OCT image.

[0023] The correction process comprises:

[0024] S231, calculating and obtaining the grayscale histogram of each detector of the OCT image;

[0025] S232, calculating the comprehensive histogram of all detectors, matching the histograms, and obtaining the relative radiation correction coefficient of each gray value;

[0026] S233: For each pixel point of the second image signal, multiply the grayscale value of the pixel point by the relative radiation correction coefficient corresponding to the grayscale value of the pixel point to obtain a processed OCT image.

[0027] The processing of analyzing and identifying the processed OCT image to obtain the real-time position information of the PICC catheter, and using the real-time position information of the PICC catheter to compare with a preset optimal position to obtain a position determination result, includes:

[0028] S41, obtaining three-dimensional image information of the PICC catheter; the three-dimensional image information of the PICC catheter is represented by a three-dimensional matrix S;

[0029] S42, performing matching calculation processing on the processed OCT image and the three-dimensional image information of the PICC catheter to obtain a real-time position information sequence of the PICC catheter;

[0030] S43, performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result.

[0031] The matching calculation process of the processed OCT image and the three-dimensional image information of the PICC catheter is performed to obtain a real-time position information sequence of the PICC catheter, including:

[0032] S421, performing a three-dimensional convolution calculation on the processed OCT image at each moment and the three-dimensional image information of the PICC catheter to obtain a convolution value of each three-dimensional position of the processed OCT image;

[0033] S422, determining the three-dimensional position of the processed OCT image with the largest convolution value as the real-time position information of the PICC catheter at the moment;

[0034] S423, constructing a real-time position information sequence of the PICC catheter using the real-time position information of the PICC catheter at all times.

[0035] The performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result includes:

[0036] S431, performing total similarity calculation processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a total similarity value;

[0037] S432, determine whether the total similarity value is greater than the set similarity threshold, and obtain a first judgment result; if the first judgment result is yes, determine that the position judgment result is that the preset position is reached; if the first judgment result is no, determine that the position judgment result is that the preset position is not reached.

[0038] The expression for the total similarity value calculation process is:

[0039]

[0040] Among them, R(t) is the position information at time t in the real-time position information sequence, Q is the preset optimal position, P is the total similarity value, E is the total number of moments, and | | represents the Euclidean distance calculation.

[0041] The third aspect of the present invention is to disclose a PICC catheter positioning and identification device based on optical coherence tomography, the device comprising:

[0042] A memory storing executable program code;

[0043] a processor coupled to the memory;

[0044] The processor calls the executable program code stored in the memory to execute the PICC catheter positioning and identification method based on optical coherence tomography.

[0045] According to a fourth aspect of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the PICC catheter positioning and identification method based on optical coherence tomography.

[0046] The fifth aspect of the present invention discloses an information data processing terminal, which is used to implement the PICC catheter positioning and identification method based on optical coherence tomography.

[0047] The beneficial effects of the present invention are:

[0048] High-resolution imaging: OCT technology can provide high-resolution intravascular images, clearly showing the relative position of the catheter and the blood vessel wall, and improving the accuracy of catheterization.

[0049] Real-time imaging: The device can acquire and display OCT images in real time, helping medical staff to monitor the catheter insertion process in real time.

[0050] Portability: The device is designed to be lightweight and portable, making it easy to use in different medical scenarios and improving medical efficiency.

[0051] Intelligent alarm: The combination of the position recognition unit and the alarm unit can promptly remind medical staff whether the catheter has reached the optimal position, reducing operational errors.

[0052] Real-time position detection and high detection accuracy: The present invention specifically proposes corresponding matching calculation processing and similarity discrimination processing algorithms for target recognition and position detection of OCT images. The real-time position information sequence of the PICC catheter is obtained by matching the processed OCT image with the three-dimensional image information of the PICC catheter. The real-time position information sequence of the PICC catheter is subjected to similarity discrimination processing with the preset optimal position to obtain a position discrimination result, thereby improving the detection accuracy.

[0053] Before performing image recognition and detection, the present invention establishes a corresponding image correction model based on the characteristics of the OCT image, thereby ensuring the accuracy of the acquired image and providing an image source for correct detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the composition of the device of the present invention;

[0055] Figure 2 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0056] In order to better understand the content of the present invention, an embodiment is given here.

[0057] Figure 1 It is a schematic diagram of the composition of the device of the present invention; Figure 2 It is a flow chart for implementing the method of the present invention.

[0058] In a first aspect of an embodiment of the present invention, a PICC catheter positioning and identification device based on optical coherence tomography (OCT) is disclosed, comprising: an OCT probe, a signal acquisition and processing unit, an image display unit, and a position identification unit;

[0059] The OCT probe is used to obtain OCT images of the blood vessel and the PICC catheter during the PICC catheterization process; the probe has high resolution, can scan the internal structure of the blood vessel in real time, and clearly display the relative position of the catheter and the blood vessel wall.

[0060] The signal acquisition and processing unit is connected to the OCT probe and is used to process the acquired OCT image signal to obtain a processed OCT image;

[0061] The image display unit is connected to the signal acquisition and processing unit and is used to display the processed OCT image in real time for observation by medical staff.

[0062] The position identification unit is connected to the image display unit and the signal acquisition processing unit, and is used to analyze and identify the processed OCT image to obtain the real-time position information of the PICC catheter, compare it with the preset optimal position, and obtain the position discrimination result;

[0063] The OCT probe is implemented using cardiovascular OCT imaging equipment; specifically, it can be implemented using Weiguang Medical's cardiovascular OCT system and disposable intravascular imaging catheter, or Hengyu Medical's intravascular OCT imaging system and imaging catheter, or Wolfman's OCT equipment and imaging catheter.

[0064] The signal acquisition and processing unit is used to process the acquired OCT image signal to obtain a processed OCT image, including:

[0065] The signal acquisition and processing unit performs image denoising on the acquired OCT image signal to obtain a first image signal;

[0066] performing contrast enhancement processing on the first image signal to obtain a second image signal;

[0067] Performing correction processing on the second image signal to obtain a processed OCT image;

[0068] The correction process comprises:

[0069] Calculate and obtain the grayscale histogram of each detector of the OCT image;

[0070] Calculate the comprehensive histogram of all detectors, match the histograms, and obtain the relative radiation correction coefficient of each gray value;

[0071] For each pixel point of the second image signal, multiply the gray value of the pixel point by the relative radiation correction coefficient corresponding to the gray value of the pixel point to obtain a processed OCT image;

[0072] The position identification unit analyzes and identifies the processed OCT image to obtain real-time position information of the PICC catheter, and compares the real-time position information of the PICC catheter with a preset optimal position to obtain a position determination result, including:

[0073] Acquire three-dimensional image information of the PICC catheter; the three-dimensional image information of the PICC catheter is represented as a three-dimensional matrix S;

[0074] Performing matching calculation processing on the processed OCT image and the three-dimensional image information of the PICC catheter to obtain a real-time position information sequence of the PICC catheter;

[0075] Performing similarity discrimination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position discrimination result;

[0076] The matching calculation process of the processed OCT image and the three-dimensional image information of the PICC catheter is performed to obtain a real-time position information sequence of the PICC catheter, including:

[0077] Performing a three-dimensional convolution calculation on the processed OCT image at each moment and the three-dimensional image information of the PICC catheter to obtain a convolution value of each three-dimensional position of the processed OCT image;

[0078] Determine the three-dimensional position of the processed OCT image with the maximum convolution value as the real-time position information of the PICC catheter at the moment;

[0079] The real-time position information of the PICC catheter at all times is used to construct a real-time position information sequence of the PICC catheter.

[0080] The performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result includes:

[0081] Performing total similarity calculation processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a total similarity value;

[0082] Determine whether the total similarity value is greater than a set similarity threshold value to obtain a first determination result; if the first determination result is yes, determine that the position determination result is that the preset position has been reached; if the first determination result is no, determine that the position determination result is that the preset position has not been reached;

[0083] The expression for the total similarity value calculation process is:

[0084]

[0085] Among them, R(t) is the position information at time t in the real-time position information sequence, Q is the preset optimal position, P is the total similarity value, E is the total number of moments, and | | represents the Euclidean distance calculation.

[0086] When the position determination result is that the preset position is reached, the position identification unit sends an alarm signal to the alarm unit, and the alarm unit sends an alarm message.

[0087] The correction process comprises:

[0088] For the detector in the jth column of the OCT probe, calculate the grayscale histogram P of the image obtained by the single detector j And the cumulative probability density function S j, 1≤j≤N;

[0089] For the grayscale histogram P j , when the gray value is k, the corresponding gray histogram P j The calculation formula of (k) is:

[0090] P j (k) = m j (k) / M j ,

[0091] In the formula, m j (k) is the number of pixels in the image whose grayscale value is equal to k obtained by the jth detector, M j The total number of pixels of the image obtained by the jth detector is, then for the grayscale histogram P j , when the pixel gray value is k, the corresponding cumulative probability density function S j (k) is:

[0092]

[0093] Where l is the gray value of the pixel; the gray histogram of each detector is merged to obtain the comprehensive histogram P of all detectors; for the comprehensive histogram P, when the gray value is k, the calculation formula of the corresponding comprehensive histogram P(k) is:

[0094]

[0095] For the comprehensive histogram P of all detectors, when the pixel gray value is k, the corresponding cumulative probability density function V(k) is:

[0096]

[0097] In the histogram matching process, the comprehensive histogram of all detectors is the expected histogram. A lookup table is established based on the expected histogram so that the probability density function of the comprehensive histogram of each detector after matching is the same as the probability density function of the expected histogram.

[0098] According to the gray histogram P of the jth detector j The corresponding cumulative probability density function S j The cumulative probability density function V corresponding to the expected histogram is used to calculate the relative radiation correction coefficient of the jth detector and record the relative radiation correction coefficient of the jth detector in the grayscale lookup table T j , 1≤j≤N; T j Represents the grayscale lookup table corresponding to the j-th detector;

[0099] For the grayscale histogram P j The cumulative probability density function S of the pixel gray value k j(k), starting from gray value 0, search gray value l that satisfies the following condition in the cumulative probability density function V corresponding to the expected histogram:

[0100] V(l)≤S j (k)≤V(l+1),

[0101] After finding the gray value l, in |V(l)-S j (k)|-|V(l+1)-S j (k)|≤0, the grayscale lookup table T j The relative radiation correction coefficient T of the jth detector recorded at the pixel gray value k j (k) is:

[0102] T j (k) = l,

[0103] In |V(l)-S j (k)|-|V(l+1)-S j (k)|>0, the grayscale lookup table T j The relative radiation correction factor T recorded at the pixel gray value k j (k) is:

[0104] T j (k) = l + 1,

[0105] The above operation process is performed for each detector to obtain a relative radiation correction coefficient for each gray value;

[0106] For each pixel point of the second image signal, a relative radiation correction coefficient corresponding to the gray value of the pixel point is multiplied by the gray value of the pixel point to obtain a processed OCT image.

[0107] The expression of the three-dimensional convolution calculation is:

[0108] Con(i,j,k)=conv(R(i,j,k),S),

[0109] Among them, R(i,j,k) represents the pixel point in the jth row and kth column of the i-th layer of the processed OCT image, Con(i,j,k) represents the convolution value of the pixel point in the jth row and kth column of the i-th layer of the OCT image, and the three-dimensional position of the pixel point in the jth row and kth column of the i-th layer of the OCT image is (i,j,k,).

[0110] The three-dimensional convolution calculation can be implemented by using the three-dimensional convolution module in the neural network, specifically torch.nn.Conv3d in the PyTorch framework. torch.nn.Conv3d is a module in PyTorch specifically used to implement three-dimensional convolution. It applies the convolution operation on the three-dimensional volume of the input data by setting the parameters of the depth, height and width of the convolution kernel. For example, torch.nn.Conv3d(in_channels,out_channels,kernel_size,stride=1,padding=0,dilation=1,groups=1,bias=True,padding_mode='zeros'), where in_channels is the number of input channels, out_channels is the number of output channels, kernel_size is the size of the convolution kernel, which can be an integer or a triplet to specify the size in the depth, height and width directions respectively, stride is the step size of the convolution kernel movement, padding is the size of the padding around the input data, dilation is the spacing between convolution kernel elements, groups is the number of groups for grouped convolution, bias is whether to add a bias term, and padding_mode is the padding mode.

[0111] A processed OCT image at a time is a processed OCT image obtained at a collection time;

[0112] The device of the present invention also includes an alarm unit, which is connected to the position identification unit and emits an audible and visual alarm prompt when the PICC catheter reaches a preset optimal position.

[0113] During the PICC catheterization process, the OCT probe is placed on the patient's body surface or inserted into the blood vessel through an adapter to obtain real-time OCT images of the blood vessel and PICC catheter. After the signal acquisition and processing unit processes the image, the image display unit displays the processed image in real time. The position recognition unit analyzes the image and identifies the catheter position. When the catheter reaches the optimal position, the alarm unit issues an alarm prompt to help medical staff accurately complete the catheterization operation.

[0114] In this embodiment, the OCT probe adopts a handheld design, which is convenient for medical staff to operate. The signal acquisition and processing unit is integrated in the portable device and connected to the OCT probe wirelessly or wired. The image display unit is a high-resolution touch screen that displays the OCT image in real time and provides interactive functions such as image zooming and rotation. The position recognition unit adopts an advanced image recognition algorithm to quickly and accurately identify the position of the catheter. The alarm unit includes an audible alarm and flashing lights to ensure that medical staff can notice the alarm prompt in time.

[0115] In this embodiment, the OCT probe is designed as a disposable sterile probe suitable for PICC catheterization operations on different patients. The signal acquisition and processing unit and the image display unit are integrated into a portable medical device. The device housing is waterproof and dustproof, suitable for use in various medical environments. The position recognition unit combines artificial intelligence technology to improve the accuracy of catheter position recognition through deep learning algorithms. In addition to sound and light alarms, the alarm unit also adds a vibration alarm function to meet the needs of different medical staff.

[0116] In a second aspect of an embodiment of the present invention, a PICC catheter positioning and identification method based on optical coherence tomography (OCT) is disclosed, which is implemented by using the PICC catheter positioning and identification device based on optical coherence tomography (OCT), comprising:

[0117] Use the OCT probe to obtain OCT images of blood vessels and PICC catheters during PICC placement;

[0118] Using the signal acquisition and processing unit, the acquired OCT image signal is processed to obtain a processed OCT image;

[0119] The processed OCT images are displayed in real time using the image display unit for observation by medical staff.

[0120] The processed OCT image is analyzed and identified by using a position recognition unit to obtain real-time position information of the PICC catheter. The real-time position information of the PICC catheter is compared with a preset optimal position to obtain a position determination result.

[0121] The step of processing the collected OCT image signal to obtain a processed OCT image includes:

[0122] Performing image denoising processing on the collected OCT image signal to obtain a first image signal;

[0123] performing contrast enhancement processing on the first image signal to obtain a second image signal;

[0124] Performing correction processing on the second image signal to obtain a processed OCT image;

[0125] The correction process comprises:

[0126] Calculate and obtain the grayscale histogram of each detector of the OCT image;

[0127] Calculate the comprehensive histogram of all detectors, match the histograms, and obtain the relative radiation correction coefficient of each gray value;

[0128] For each pixel point of the second image signal, multiply the gray value of the pixel point by the relative radiation correction coefficient corresponding to the gray value of the pixel point to obtain a processed OCT image;

[0129] The processing of analyzing and identifying the processed OCT image to obtain the real-time position information of the PICC catheter, and using the real-time position information of the PICC catheter to compare with a preset optimal position to obtain a position determination result, includes:

[0130] Acquire three-dimensional image information of the PICC catheter; the three-dimensional image information of the PICC catheter is represented as a three-dimensional matrix S;

[0131] Performing matching calculation processing on the processed OCT image and the three-dimensional image information of the PICC catheter to obtain a real-time position information sequence of the PICC catheter;

[0132] Performing similarity discrimination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position discrimination result;

[0133] The three-dimensional image information of the PICC catheter is obtained by photographing the three-dimensional image information of the PICC catheter using an OCT probe;

[0134] The matching calculation process of the processed OCT image and the three-dimensional image information of the PICC catheter is performed to obtain a real-time position information sequence of the PICC catheter, including:

[0135] Performing a three-dimensional convolution calculation on the processed OCT image at each moment and the three-dimensional image information of the PICC catheter to obtain a convolution value of each three-dimensional position of the processed OCT image;

[0136] Determine the three-dimensional position of the processed OCT image with the maximum convolution value as the real-time position information of the PICC catheter at the moment;

[0137] The real-time position information of the PICC catheter at all times is used to construct a real-time position information sequence of the PICC catheter.

[0138] The performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result includes:

[0139] Performing total similarity calculation processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a total similarity value;

[0140] Determine whether the total similarity value is greater than a set similarity threshold value to obtain a first determination result; if the first determination result is yes, determine that the position determination result is that the preset position has been reached; if the first determination result is no, determine that the position determination result is that the preset position has not been reached;

[0141] The expression for the total similarity value calculation process is:

[0142]

[0143] Among them, R(t) is the position information at time t in the real-time position information sequence, Q is the preset optimal position, P is the total similarity value, E is the total number of moments, and | | represents the Euclidean distance calculation.

[0144] When the position determination result is that the preset position is reached, the position identification unit sends an alarm signal to the alarm unit, and the alarm unit sends an alarm message.

[0145] The correction process comprises:

[0146] For the detector in the jth column of the OCT probe, calculate the grayscale histogram P of the image obtained by the single detector j And the cumulative probability density function S j , 1≤j≤N;

[0147] For the grayscale histogram P j , when the gray value is k, the corresponding gray histogram P j The calculation formula of (k) is:

[0148] P j (k) = m j (k) / M j ,

[0149] In the formula, m j (k) is the number of pixels in the image whose grayscale value is equal to k obtained by the jth detector, M j The total number of pixels of the image obtained by the jth detector is, then for the grayscale histogram P j , when the pixel gray value is k, the corresponding cumulative probability density function S j (k) is:

[0150]

[0151] Where l is the gray value of the pixel; the gray histogram of each detector is merged to obtain the comprehensive histogram P of all detectors; for the comprehensive histogram P, when the gray value is k, the calculation formula of the corresponding comprehensive histogram P(k) is:

[0152]

[0153] For the comprehensive histogram P of all detectors, when the pixel gray value is k, the corresponding cumulative probability density function V(k) is:

[0154]

[0155] In the histogram matching process, the comprehensive histogram of all detectors is the expected histogram. A lookup table is established based on the expected histogram so that the probability density function of the comprehensive histogram of each detector after matching is the same as the probability density function of the expected histogram.

[0156] According to the grayscale histogram P of the jth detector j The corresponding cumulative probability density function S j The cumulative probability density function V corresponding to the expected histogram is used to calculate the relative radiation correction coefficient of the jth detector and record the relative radiation correction coefficient of the jth detector in the grayscale lookup table T j , 1≤j≤N; T j Represents the grayscale lookup table corresponding to the j-th detector;

[0157] For the grayscale histogram P j The cumulative probability density function S of the pixel gray value k j (k), starting from gray value 0, search gray value l that satisfies the following condition in the cumulative probability density function V corresponding to the expected histogram:

[0158] V(l)≤S j (k)≤V(l+1),

[0159] After finding the gray value l, in |V(l)-S j (k)|-|V(l+1)-S j (k)|≤0, the grayscale lookup table T j The relative radiation correction coefficient T of the jth detector recorded at the pixel gray value k j (k) is:

[0160] T j (k) = l,

[0161] In |V(l)-S j (k)|-|V(l+1)-S j (k)|>0, the grayscale lookup table T j The relative radiation correction factor T recorded at the pixel gray value k j (k) is:

[0162] T j (k) = l + 1,

[0163] The above operation process is performed for each detector to obtain a relative radiation correction coefficient for each gray value;

[0164] For each pixel point of the second image signal, a relative radiation correction coefficient corresponding to the gray value of the pixel point is multiplied by the gray value of the pixel point to obtain a processed OCT image.

[0165] The expression of the three-dimensional convolution calculation is:

[0166] Con(i,j,k)=conv(R(i,j,k),S),

[0167] Among them, R(i,j,k) represents the pixel point in the jth row and kth column of the i-th layer of the processed OCT image, Con(i,j,k) represents the convolution value of the pixel point in the jth row and kth column of the i-th layer of the OCT image, and the three-dimensional position of the pixel point in the jth row and kth column of the i-th layer of the OCT image is (i,j,k,).

[0168] The three-dimensional convolution calculation can be implemented by using the three-dimensional convolution module in the neural network, specifically torch.nn.Conv3d in the PyTorch framework. torch.nn.Conv3d is a module in PyTorch specifically used to implement three-dimensional convolution. It applies the convolution operation on the three-dimensional volume of the input data by setting the parameters of the depth, height and width of the convolution kernel. For example, torch.nn.Conv3d(in_channels,out_channels,kernel_size,stride=1,padding=0,dilation=1,groups=1,bias=True,padding_mode='zeros'), where in_channels is the number of input channels, out_channels is the number of output channels, kernel_size is the size of the convolution kernel, which can be an integer or a triplet to specify the size in the depth, height and width directions respectively, stride is the step size of the convolution kernel movement, padding is the size of the padding around the input data, dilation is the spacing between convolution kernel elements, groups is the number of groups for grouped convolution, bias is whether to add a bias term, and padding_mode is the padding mode.

[0169] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A PICC catheter positioning and identification device based on optical coherence tomography, characterized in that: include: OCT probe, signal acquisition and processing unit, image display unit and position recognition unit; The OCT probe is used to obtain OCT images of the blood vessels and PICC catheter during the PICC catheterization process; The signal acquisition and processing unit is connected to the OCT probe and is used to process the acquired OCT image signal to obtain a processed OCT image; The image display unit is connected to the signal acquisition and processing unit and is used to display the processed OCT image in real time; The position identification unit is connected to the image display unit and the signal acquisition processing unit, and is used to analyze and identify the processed OCT image to obtain the real-time position information of the PICC catheter, and use the real-time position information of the PICC catheter to compare with the preset optimal position to obtain a position discrimination result.

2. The PICC catheter positioning and identification device based on optical coherence tomography according to claim 1, characterized in that: The OCT probe is implemented using a cardiovascular OCT imaging device.

3. The PICC catheter positioning and identification device based on optical coherence tomography according to claim 1, characterized in that: The signal acquisition and processing unit is used to process the acquired OCT image signal to obtain a processed OCT image, including: The signal acquisition and processing unit performs image denoising on the acquired OCT image signal to obtain a first image signal; performing contrast enhancement processing on the first image signal to obtain a second image signal; Correction processing is performed on the second image signal to obtain a processed OCT image.

4. A PICC catheter positioning and identification method based on optical coherence tomography, characterized in that: The method is implemented by using the PICC catheter positioning and identification device based on optical coherence tomography according to any one of claims 1 to 3, comprising: S1, using the OCT probe to obtain OCT images of the blood vessels and PICC catheter during PICC placement; S2, using a signal acquisition and processing unit to process the acquired OCT image signal to obtain a processed OCT image; S3, using an image display unit to display the processed OCT image in real time; S4, using a position recognition unit to analyze and recognize the processed OCT image to obtain real-time position information of the PICC catheter, and using the real-time position information of the PICC catheter to compare with a preset optimal position to obtain a position determination result.

5. The PICC catheter positioning and identification method based on optical coherence tomography according to claim 4, characterized in that: The step of processing the collected OCT image signal to obtain a processed OCT image includes: S21, performing image denoising processing on the collected OCT image signal to obtain a first image signal; S22, performing contrast enhancement processing on the first image signal to obtain a second image signal; S23, performing correction processing on the second image signal to obtain a processed OCT image.

6. The PICC catheter positioning and identification method based on optical coherence tomography according to claim 5, characterized in that: The correction process comprises: S231, calculating and obtaining the grayscale histogram of each detector of the OCT image; S232, calculating the comprehensive histogram of all detectors, matching the histograms, and obtaining the relative radiation correction coefficient of each gray value; S233: For each pixel point of the second image signal, multiply the grayscale value of the pixel point by the relative radiation correction coefficient corresponding to the grayscale value of the pixel point to obtain a processed OCT image.

7. The PICC catheter positioning and identification method based on optical coherence tomography according to claim 4, characterized in that: The processing of analyzing and identifying the processed OCT image to obtain the real-time position information of the PICC catheter, and using the real-time position information of the PICC catheter to compare with a preset optimal position to obtain a position determination result, includes: S41, obtaining three-dimensional image information of the PICC catheter; the three-dimensional image information of the PICC catheter is represented by a three-dimensional matrix S; S42, performing matching calculation processing on the processed OCT image and the three-dimensional image information of the PICC catheter to obtain a real-time position information sequence of the PICC catheter; S43, performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result.

8. The method for PICC catheter positioning and identification based on optical coherence tomography according to claim 7, characterized in that: The matching calculation process of the processed OCT image and the three-dimensional image information of the PICC catheter is performed to obtain a real-time position information sequence of the PICC catheter, including: S421, performing a three-dimensional convolution calculation on the processed OCT image at each moment and the three-dimensional image information of the PICC catheter to obtain a convolution value of each three-dimensional position of the processed OCT image; S422, determining the three-dimensional position of the processed OCT image with the largest convolution value as the real-time position information of the PICC catheter at the moment; S423, constructing a real-time position information sequence of the PICC catheter using the real-time position information of the PICC catheter at all times.

9. The PICC catheter positioning and identification method based on optical coherence tomography according to claim 7, characterized in that: The performing similarity determination processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a position determination result includes: S431, performing total similarity calculation processing on the real-time position information sequence of the PICC catheter and the preset optimal position to obtain a total similarity value; S432, determine whether the total similarity value is greater than the set similarity threshold, and obtain a first judgment result; if the first judgment result is yes, determine that the position judgment result is that the preset position is reached; if the first judgment result is no, determine that the position judgment result is that the preset position is not reached.

10. The PICC catheter positioning and identification method based on optical coherence tomography according to claim 9, characterized in that: The expression for the total similarity value calculation process is: Among them, R(t) is the position information at time t in the real-time position information sequence, Q is the preset optimal position, P is the total similarity value, E is the total number of moments, and || represents the Euclidean distance calculation.

Images