Laser heat effect evaluation method and device

Abstract

The invention discloses a laser heat effect evaluation method and device, and belongs to the technical field of biology. The method comprises the following steps: acquiring an original laser speckle blood flow image sequence, and analyzing an original laser speckle image by adopting a time contrast analysis algorithm to obtain a laser speckle contrast image; and converting the laser speckle contrast image to obtain a laser speckle blood flow image. Calculating the full width at half maximum of the blood vessel in the laser speckle blood flow image as the width of the blood vessel; subtraction is conducted on the blood flow image obtained after laser irradiation and the blood flow image obtained before laser irradiation, and a difference image is obtained; blood vessels with blood flow changes due to laser irradiation are obtained according to the difference image, then a region of interest is selected, the blood flow mean value of the blood vessels before and after laser irradiation is obtained, and therefore the final laser treatment effect is evaluated. The mouse spine window 108 is irradiated from the complete skin side of the mouse spine window 108, and the blood flow change is monitored in real time on the opposite exposed blood vessel side by adopting technologies such as laser speckle blood flow imaging and the like. The influence of the upper skin tissue is considered, the blood flow change is monitored in real time, and accurate evaluation of the blood vessel laser heat effect is achieved.

Description

Technical Field

[0001] The invention provides a laser thermal effect evaluation method and device, belonging to the field of biotechnology. Background Art

[0002] The production process of the mouse spinal window model has been carefully designed to minimize surgical trauma and accelerate animal recovery. Through delicate surgical techniques, researchers are able to accurately create a transparent observation window in the dorsal spinal region of mice. This process is not only technically feasible, but also relatively short in operation time, which improves the efficiency of the experiment. In addition, the introduction of the transparent window allows microstructures such as blood vessels to be clearly visible without additional staining or labeling, greatly simplifying the experimental steps and costs.

[0003] In the study of laser therapy, the thermal response of blood vessels is one of the key factors in evaluating the efficacy and safety of treatment. The unique design of the mouse spinal window model allows researchers to directly and in real time observe the changes in vascular morphology, blood flow velocity, and thermal effects of surrounding tissues after laser irradiation. This observation method not only has high resolution, but also can capture instantaneous physiological responses, providing valuable data support for a deeper understanding of the interaction between lasers and biological tissues.

[0004] Although the mouse spinal window model has significant advantages in vascular observation, in traditional research methods, the therapeutic laser is often directly irradiated on the blood vessels on the side of the excised skin. This practice ignores the influence of the upper skin tissue on the absorption, scattering and heat transfer of laser energy to a certain extent. This neglect may lead to inaccurate evaluation of the thermal effect of deep blood vessels, because the skin is the first barrier for laser to enter the body, and its optical and thermal properties will have an important influence on the distribution and transfer of laser energy. This leads to the traditional laser thermal effect evaluation method of irradiating the laser on the skinned side of the mouse spinal window and monitoring the laser thermal effect at the same time, ignoring the influence of the absorption, scattering and heat transfer of the upper skin tissue, and failing to accurately evaluate the thermal effect of deep blood vessels. Summary of the invention

[0005] In order to overcome the deficiency of the existing technology that cannot accurately evaluate the thermal effect of deep blood vessels, the present invention proposes a laser thermal effect evaluation method and device, which illuminates the mouse spinal window from the intact skin side of the mouse spinal window, and uses laser speckle blood flow imaging and other technologies to monitor blood flow changes in real time on the exposed blood vessel side on the opposite side. It not only takes into account the influence of the upper skin tissue, but also monitors blood flow changes in real time, thus achieving an accurate evaluation of the laser thermal effect of blood vessels.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: In a first aspect, the present invention provides a laser thermal effect evaluation method, comprising: Acquire the original laser speckle blood flow image sequence, analyze the original laser speckle image using a time contrast analysis algorithm to obtain a laser speckle contrast image; convert the laser speckle contrast image to obtain a laser speckle blood flow index image; The half-height width of the blood vessel in the laser speckle blood flow index image is calculated as the width of the blood vessel; the difference image is obtained by subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation; The blood vessels whose blood flow changes due to laser irradiation are obtained based on the difference image, and then the region of interest is selected to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

[0007] As a further improvement of the present invention, after acquiring the original laser speckle blood flow image sequence, the method further includes: Deep learning is used to reduce the noise of the original laser speckle blood flow image in real time and convert it into a speckle blood flow image; The deep learning is a laser speckle blood flow image denoising generation adversarial denoising method, the deep neural network of the laser speckle blood flow image denoising generation adversarial denoising method is composed of a denoiser and a discriminator, and denoising is achieved by the denoiser and the discriminator confronting each other; The denoiser and the discriminator both adopt the Unet architecture; the denoiser consists of an encoder, a bridge and a decoder; the encoder unit uses three sequentially arranged lightweight residual blocks with a stride of 1 or 2 for feature extraction, and the number of filters is doubled after the downsampling operation; the downsampling with a stride of 1 in the first layer is postponed; the extracted features are passed to the decoder through the bridge for estimating the denoised input in the feature domain; the features are transformed into the image domain by each decoder layer through a conversion unit, which consists of n residual blocks, followed by a 1×1 convolutional layer and a sigmoid activation layer; the number of filters in the conversion unit is halved n times, and the filter size of the 1×1 convolutional layer is set to C; It also includes a vascular structure enhancer, which contains a large kernel depthwise separable convolution to extract low-level features, followed by a set of parallel depthwise separable convolutions to capture structural information at different scales; the structural features are fused through two 1×1 convolutional layers, and the vascular structure enhancer is attached to the last decoder layer before entering the transformation unit; The discriminator network consists of ordinary convolutional layers. The output of the conversion unit in the discriminator is converted into a binary mask through a mapper, which consists of a convolutional layer and a sigmoid activation layer.

[0008] As a further improvement of the present invention, a contrast signal-to-noise ratio loss function is introduced into the temporal contrast analysis algorithm, and the contrast between blood vessels and tissues is enhanced by guiding an adversarial distortion learning network.

[0009] As a further improvement of the present invention, the laser speckle contrast image is converted to obtain the laser speckle blood flow index image using a sequence formed by the original laser speckle blood flow image.

[0010] In a second aspect, a laser speckle blood flow imaging device includes a laser speckle imaging system and a therapeutic laser; the laser speckle imaging system includes an imaging laser, a beam expander, an imaging optical system, an image acquisition system, a bandpass filter, a neutral density adjustable attenuator, and a reflector; The mouse spinal window animal model is fixed in the laser speckle imaging system through a fixing device. The laser generated by the treatment laser is reflected by the first reflector and incident perpendicularly to the intact skin side of the mouse spinal window. At the same time, the blood flow of the side with the skin removed is monitored by the laser speckle imaging system. The imaging laser selects a laser light source in the near-infrared band, and the laser power is adjusted by changing the angle of the neutral density adjustable attenuation plate; the adjusted light beam is expanded by a spot beam expander and then irradiates the mouse spine window through a second reflector; the mouse spine window is imaged by an imaging optical system, and a detector is used to collect the image, which is then transmitted to a data acquisition and analysis system for processing.

[0011] Optionally, an interference bandpass filter with the same central wavelength as the imaging laser is installed in front of the detector to collect dynamic scattering signals; the therapeutic laser uses therapeutic laser to irradiate the intact skin side of the mouse spinal window.

[0012] In a third aspect, the present invention provides a laser thermal effect evaluation system, comprising: An acquisition module is used to acquire a sequence of original laser speckle blood flow images, analyze the original laser speckle images using a time contrast analysis algorithm to acquire a laser speckle contrast image; and convert the laser speckle contrast image to acquire a laser speckle blood flow index image; A calculation module is used to calculate the half-height width of the blood vessel in the laser speckle blood flow index image as the width of the blood vessel; and to obtain a difference image by subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation; The evaluation module is used to obtain the blood vessels with blood flow changes due to laser irradiation based on the difference image, and then select the region of interest to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

[0013] As a further improvement of the present invention, a noise reduction module is also included: The noise reduction module uses deep learning to reduce the noise of the original laser speckle blood flow image in real time and convert it into a speckle blood flow image; The deep learning is a laser speckle blood flow image denoising generation adversarial denoising method, the deep neural network of the laser speckle blood flow image denoising generation adversarial denoising method is composed of a denoiser and a discriminator, and denoising is achieved by the denoiser and the discriminator confronting each other; The denoiser and the discriminator both adopt the Unet architecture; the denoiser consists of an encoder, a bridge and a decoder; the encoder unit uses three sequentially arranged lightweight residual blocks with a stride of 1 or 2 for feature extraction, and the number of filters is doubled after the downsampling operation; the downsampling with a stride of 1 in the first layer is postponed; the extracted features are passed to the decoder through the bridge for estimating the denoised input in the feature domain; the features are transformed into the image domain by each decoder layer through a conversion unit, which consists of n residual blocks, followed by a 1×1 convolutional layer and a sigmoid activation layer; the number of filters in the conversion unit is halved n times, and the filter size of the 1×1 convolutional layer is set to C; It also includes a vascular structure enhancer, which contains a large kernel depthwise separable convolution to extract low-level features, followed by a set of parallel depthwise separable convolutions to capture structural information at different scales; the structural features are fused through two 1×1 convolutional layers, and the vascular structure enhancer is attached to the last decoder layer before entering the transformation unit; The discriminator network consists of ordinary convolutional layers. The output of the conversion unit in the discriminator is converted into a binary mask through a mapper, which consists of a convolutional layer and a sigmoid activation layer.

[0014] As a further improvement of the present invention, in the acquisition module, a contrast signal-to-noise ratio loss function is introduced into the temporal contrast analysis algorithm, and the contrast between blood vessels and tissues is enhanced by guiding an adversarial distortion learning network.

[0015] As a further improvement of the present invention, in the acquisition module, the laser speckle contrast image is converted to obtain the laser speckle blood flow index image using a sequence formed by the original laser speckle blood flow image.

[0016] In a fourth aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the laser thermal effect evaluation method is implemented when the processor executes the computer program.

[0017] In a fifth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the laser thermal effect evaluation method when executed by a processor.

[0018] In a sixth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions instruct a computer to execute the laser thermal effect evaluation method.

[0019] The beneficial effects of the present invention compared with the prior art are as follows: The laser speckle imaging technology used in the present invention is a non-contact, non-invasive imaging method that does not cause any harm to the subject and is suitable for a wide range of applications in clinical and scientific research. The time contrast analysis algorithm can capture the blood flow changes in micro-vessels, making the method highly sensitive to blood flow changes caused by laser irradiation. By calculating the mean of blood flow in blood vessels before and after laser irradiation, a quantitative evaluation of the effect of laser treatment can be achieved, providing a scientific basis for clinical decision-making. Laser speckle imaging technology can capture the dynamic changes of blood flow in real time, making the method advantageous in evaluating the immediate effect during laser treatment. This method is not only suitable for evaluating the effect of laser treatment, but also for monitoring vascular diseases, studying hemodynamics and other fields, and has broad application prospects. The present invention proposes to irradiate the mouse spinal window from the intact skin side of the mouse spinal window, and use laser speckle blood flow imaging and other technologies on the exposed blood vessel side on the opposite side to monitor blood flow changes in real time. It not only takes into account the influence of the upper skin tissue, but also monitors blood flow changes in real time, thereby achieving an accurate evaluation of the laser thermal effect of blood vessels. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a schematic diagram of the mouse spine window 108; Figure 2 This is a system diagram of the laser speckle blood flow imaging device of the present invention; Figure 3 A physical diagram of the placement of the mouse spine window 108 of the present invention; Figure 4 This is a flow chart of data collection and analysis of laser speckle blood flow imaging of the present invention; Figure 5 Comparison of blood flow images between traditional skin peeling irradiation and the transmission method of the present invention.

[0022] In the figure, 100, imaging laser; 101, adjustable attenuator; 102, beam expander; 103, second reflector; 104, treatment laser; 105, detector; 106, bandpass filter; 107, imaging optical system; 108, mouse spine window; 109, first reflector; 110, data acquisition and analysis system. DETAILED DESCRIPTION

[0023] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0024] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0025] The first object of the present invention is to provide a laser thermal effect evaluation method, comprising: S1, obtaining an original laser speckle blood flow image sequence, analyzing the original laser speckle image using a time contrast analysis algorithm to obtain a laser speckle contrast image; further converting the laser speckle contrast image to obtain a laser speckle blood flow index image.

[0026] S2, calculating the half-height width of the blood vessel in the laser speckle blood flow index image as the width of the blood vessel; subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation to obtain a difference image; S3, obtaining the blood vessels whose blood flow changes due to laser irradiation based on the difference image, and then selecting the region of interest to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

[0027] Wherein, the time contrast algorithm, ; in and are the standard deviation and mean of the time series of a single pixel in the original speckle image, respectively.

[0028] The laser speckle contrast image is converted to obtain the original laser speckle blood flow index image BFI The formula is as follows: ; This laser thermal effect evaluation method is mainly based on laser speckle imaging technology and image processing algorithms, which is used to evaluate the effect of laser irradiation on blood flow and then evaluate the effect of laser treatment. Its principle is: Laser speckle blood flow imaging: Laser speckle is a random interference pattern formed by the scattering of particles (such as red blood cells) inside the tissue when the laser is irradiated onto the surface of biological tissue. The change of these speckle patterns over time reflects the dynamic information of blood flow. By capturing these speckle image sequences with a high-speed camera, the dynamic changes of blood flow can be obtained.

[0029] Time contrast analysis: By processing the laser speckle image sequence using the time contrast analysis algorithm, a contrast image reflecting the change in blood flow velocity can be extracted. Time contrast is an indicator of how fast the speckle pattern changes over time and is proportional to the blood flow velocity. Therefore, the contrast image can intuitively show the distribution and velocity of blood flow. The laser speckle contrast image is converted to obtain the laser speckle blood flow index image.

[0030] Vessel width measurement: By calculating the half-height width of the blood vessels in the laser speckle blood flow index image (i.e. the width when the brightness of the blood vessels reaches half of the peak), the width of the blood vessels can be estimated. This step helps to locate and analyze the blood vessel area more accurately.

[0031] Difference image generation: The blood flow image after laser irradiation is subtracted from the image before irradiation to obtain a difference image. The bright or dark areas in the difference image represent areas where blood flow has changed significantly after laser irradiation, and these areas are often the key to evaluating the treatment effect.

[0032] Evaluation of laser treatment effect: Select a region of interest (ROI) in the difference image, calculate and compare the mean blood flow of the blood vessels in the region before and after laser irradiation. By comparing these values, the effect of laser irradiation on blood flow can be quantitatively evaluated, and then the effect of laser treatment can be evaluated.

[0033] The invention can be used for animal experiment evaluation of various medical lasers, which is beneficial to the accurate diagnosis and treatment of vascular and pigmented skin diseases and has great economic benefits. The patented technology of the invention can improve the accuracy of animal experiments on laser thermal effects, which is beneficial to obtain more accurate treatment parameters and improve treatment effects.

[0034] The content of the present invention is described in detail below.

[0035] First, the mouse spinal window 108 is made. When making the mouse spinal window 108, the back skin is lifted up and fixed at a location with rich blood vessels. One side of the skin is removed with a pair of scissors disinfected with alcohol and cut into the shape of a circular window 108. Then a titanium alloy sheet is used to fix it and it is sutured with needle and thread. The finished mouse spinal window 108 is as shown in FIG. Figure 1 shown.

[0036] like Figure 2 As shown, unlike the traditional treatment laser direct irradiation method, the present invention proposes a new method of transdermal treatment laser irradiation of the subcutaneous blood vessels on the intact skin side of the mouse spinal window 108, and the laser speckle blood flow imaging blood flow monitoring method is preferentially used on the opposite side to monitor the blood flow changes in real time during the treatment process. The blood flow monitoring method can be ultrasound Doppler, laser Doppler, magnetic resonance, etc., and the transdermal treatment laser irradiation is closer to the real treatment scene, and the imaging laser can effectively observe the blood flow changes.

[0037] Figure 2 The schematic diagram of the laser speckle blood flow imaging device provided by the present invention is shown, which is mainly composed of a mouse spinal window 108 animal model and a fixing device, a laser speckle imaging system, and a therapeutic laser 104. The laser speckle imaging system is composed of an imaging laser 100, a beam expander 102, an imaging optical system 107, an image acquisition system and a bandpass filter 106, a neutral density adjustable attenuator 101, and a reflector (103, 109). The imaging laser 100 can be a laser light source in the near-infrared band, and the laser power can be adjusted by changing the angle of the neutral density adjustable attenuator. After the adjusted light beam is expanded by the spot beam expander 102, it is preferably irradiated to the mouse spinal window 108 at an angle of 60° to the vertical plane through the second reflector 103. The imaging optical system 107 is used to image the mouse spinal window 108, and a lens and a stereo microscope can be selected. CCD and sCMOS detectors 105 are used for image acquisition, and then transmitted to the data acquisition and analysis system 110 for processing. To prevent the therapeutic laser from interfering with the imaging laser, an interference bandpass filter 106 having the same central wavelength as the imaging laser 100 is installed in front of the detector 105 to collect the dynamic scattering signal. Figure 2 As shown, the mouse spine window 108 is placed and fixed on the hollow stage, with the skin removed facing upward. The laser generated by the treatment laser 104 is reflected by the first reflector 109 mounted on a 45-degree mirror frame to receive high-energy laser light, and then incident perpendicularly to the intact skin side of the mouse spine window 108, while the blood flow on the skin removed side is monitored by the laser speckle imaging system. Figure 1 The medium green spot indicates the area illuminated by the treatment laser.

[0038] The data processing flow of the present invention is as follows Figure 3 First, a self-made laser speckle blood flow imaging device is used to obtain the original laser speckle blood flow image sequence, and a time contrast analysis algorithm with high spatial resolution is used to analyze the original laser speckle blood flow image to obtain a laser speckle contrast image. The high spatial resolution of this method facilitates the observation of microvessels with smaller diameters.

[0039] Furthermore, in order to improve the temporal resolution while maintaining the signal-to-noise ratio of the image, deep learning is used to reduce the noise of the original laser speckle blood flow image in real time and convert it into a speckle blood flow image.

[0040] The optional domain adversarial distortion learning denoising method uses a deep neural network composed of a denoiser and a discriminator, which achieve high-quality denoising effects through mutual confrontation. The network structure is lightweight and can achieve real-time denoising.

[0041] In order to solve the problem of unclear boundaries between blood vessels and tissues, this method introduces a contrast signal-to-noise ratio loss function to guide the adversarial distortion learning network to enhance the contrast between blood vessels and tissues. This deep learning denoising method performs denoising on the original laser speckle blood flow images calculated with only 5 frames. The quality of the obtained speckle blood flow images exceeds the quality of the original speckle blood flow images of 25 frames of the traditional algorithm, and the time resolution is improved by 5 times, which greatly improves the monitoring ability of laser-induced transient thermal effects on blood vessels.

[0042] In summary, the laser speckle blood flow imaging device and deep learning algorithm developed above have the ability to monitor the instantaneous thermal effect of laser with high temporal and spatial resolution. The obtained high-quality blood flow image sequence is then analyzed to evaluate the efficacy of laser treatment.

[0043] The specific steps include: first, calculating the half-width of the blood vessels in the blood flow image as the width of the blood vessels, and then subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation to obtain a difference image, thereby obtaining the blood vessels whose blood flow changes due to laser irradiation, and then selecting the area of ​​interest to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

[0044] like Figure 4 As shown, the deep learning noise reduction algorithm is preferably used to reduce the noise of the speckle blood flow image in real time, which greatly improves the signal-to-noise ratio of the blood flow image. Only 5 frames of original laser speckle blood flow images are used to achieve high-quality blood flow imaging, which improves the temporal resolution. The Nd:YAG treatment laser is used to irradiate the intact skin side of the mouse spine window 108. Preferably, the laser incident energy density is 4.8 J / cm2, the frequency is 4 Hz, and the pulse width is 1 ms. It is difficult to cause thermal damage to the blood vessels. Under the same laser parameters, the traditional method laser is used to directly irradiate the peeling side, and the blood vessels shrink linearly, resulting in complete thermal damage.

[0045] Specifically, both the denoiser and the discriminator adopt the efficient Unet architecture.

[0046] The denoiser consists of an encoder, a bridge and a decoder. The encoder unit uses three sequentially arranged lightweight residual blocks with stride 1 or 2 for feature extraction, and the number of filters is doubled after the downsampling operation. The encoder structure is known for its deep learning efficiency and integrates residual blocks using deep separable convolutions for efficient denoising prior modeling. To ensure large activation maps, the downsampling with stride 1 in the first layer is postponed. The extracted features are passed to the decoder through the bridge for estimating the denoised input in the feature domain. The features are transformed to the image domain by each decoder layer through a transformation unit, which consists of n residual blocks followed by a 1 × 1 convolutional layer and a sigmoid activation layer. The number of filters in the transformation unit is halved n times, and the filter size of the 1 × 1 convolutional layer is set to C, the number of input channels. Unless otherwise specified, the kernel size and dilation rate of the convolutional layer are kept as 3 and 1, respectively. A vascular structure enhancer is designed to preserve sparse information that is not affected by noise. The vascular structure enhancer contains a large kernel depthwise separable convolution to extract low-level features, followed by a set of parallel depthwise separable convolutions to capture structural information at different scales. The structural features are fused through two 1 × 1 convolutional layers, and the vascular structure enhancer is attached to the last decoder layer before entering the transformation unit. The denoised data is the output of the transformation unit. The lightweight denoiser has only 1.19 million parameters, which helps to improve the model inference speed and support its deployment on mobile devices.

[0047] The discriminator also uses the efficient Unet architecture, but the difference is that its network consists of ordinary convolutional layers to ensure the accuracy of the discriminator. In the discriminator, the output of the conversion unit is converted into a binary mask through a mapper, which consists of a convolutional layer and a sigmoid activation layer.

[0048] Figure 5 In the image of the laser action process in (a), because the laser beam is relatively concentrated, the laser action area under direct irradiation is small, and the thermal effect is only produced in the blood vessel area, without any obvious impact on the surrounding tissues. Figure 5 In the image of the laser action process in (b), the laser has been transformed into diffuse light due to the scattering of the upper skin tissue, so its action range is larger but the beam is more divergent, which reduces the vascular efficacy while a larger area of ​​normal tissue around is affected by the laser thermal effect. This shows that the traditional method cannot simulate the laser-induced vascular thermal effect under the condition of skin existence and lacks real guidance. Therefore, based on this method, the treatment laser can be irradiated from the intact skin side, and the other side can be observed in real time using laser speckle contrast imaging technology, so as to obtain a laser thermal effect that is more in line with the actual situation and provide guidance for clinical treatment.

[0049] The second object of the present invention is to provide a laser thermal effect evaluation system, comprising: An acquisition module is used to acquire an original laser speckle blood flow image sequence, and analyze the original laser speckle blood flow image using a time contrast analysis algorithm to acquire a laser speckle contrast image; A calculation module is used to calculate the half-height width of the blood vessel in the laser speckle contrast image as the width of the blood vessel; and to obtain a difference image by subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation; The evaluation module is used to obtain the blood vessels with blood flow changes due to laser irradiation based on the difference image, and then select the region of interest to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

[0050] As an example, a noise reduction module is also included: The noise reduction module uses deep learning to reduce the noise of the original laser speckle blood flow image in real time and convert it into a speckle blood flow image; The deep learning is a laser speckle blood flow image denoising generation adversarial denoising method, the deep neural network of the laser speckle blood flow image denoising generation adversarial denoising method is composed of a denoiser and a discriminator, and denoising is achieved by the denoiser and the discriminator confronting each other; The denoiser and the discriminator both adopt the Unet architecture; the denoiser consists of an encoder, a bridge and a decoder; the encoder unit uses three sequentially arranged lightweight residual blocks with a stride of 1 or 2 for feature extraction, and the number of filters is doubled after the downsampling operation; the downsampling with a stride of 1 in the first layer is postponed; the extracted features are passed to the decoder through the bridge for estimating the denoised input in the feature domain; the features are transformed into the image domain by each decoder layer through a conversion unit, which consists of n residual blocks, followed by a 1×1 convolutional layer and a sigmoid activation layer; the number of filters in the conversion unit is halved n times, and the filter size of the 1×1 convolutional layer is set to C; It also includes a vascular structure enhancer, which contains a large kernel depthwise separable convolution to extract low-level features, followed by a set of parallel depthwise separable convolutions to capture structural information at different scales; the structural features are fused through two 1×1 convolutional layers, and the vascular structure enhancer is attached to the last decoder layer before entering the transformation unit; The discriminator network consists of ordinary convolutional layers. The output of the conversion unit in the discriminator is converted into a binary mask through a mapper, which consists of a convolutional layer and a sigmoid activation layer.

[0051] As an example, in the acquisition module, a contrast signal-to-noise ratio loss function is introduced into the temporal contrast analysis algorithm to enhance the contrast between blood vessels and tissues by guiding an adversarial distortion learning network.

[0052] As an example, in the acquisition module, the laser speckle contrast image is converted to obtain the laser speckle blood flow index image by using a sequence formed by the original laser speckle blood flow image.

[0053] The system is based on the above-mentioned laser thermal effect evaluation method.

[0054] The third object of the embodiment of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the laser thermal effect evaluation method when executing the computer program. It also includes a communication interface and a bus.

[0055] A fourth objective of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the laser thermal effect evaluation method is implemented.

[0056] A fifth objective of an embodiment of the present invention is to provide a computer program product, wherein the computer program product includes computer instructions, and is characterized in that the computer instructions instruct a computer to execute the laser thermal effect evaluation method.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0059] The present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, readable storage media, optical storage, etc.) containing computer-usable program codes.

[0060] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A laser thermal effect evaluation method, characterized in that: include: Acquire the original laser speckle blood flow image sequence, analyze the original laser speckle image using a time contrast analysis algorithm to obtain a laser speckle contrast image; convert the laser speckle contrast image to obtain a laser speckle blood flow index image; The half-height width of the blood vessel in the laser speckle blood flow index image is calculated as the width of the blood vessel; the difference image is obtained by subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation; The blood vessels whose blood flow changes due to laser irradiation are obtained based on the difference image, and then the region of interest is selected to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

2. A laser thermal effect evaluation method according to claim 1, characterized in that: After the original laser speckle blood flow image sequence is acquired, the method further includes: Deep learning is used to reduce the noise of the original laser speckle blood flow image in real time and convert it into a speckle blood flow image; The deep learning is a laser speckle blood flow image denoising generation adversarial denoising method, the deep neural network of the laser speckle blood flow image denoising generation adversarial denoising method is composed of a denoiser and a discriminator, and denoising is achieved by the denoiser and the discriminator confronting each other; The denoiser and the discriminator both adopt the Unet architecture; the denoiser consists of an encoder, a bridge and a decoder; the encoder unit uses three sequentially arranged lightweight residual blocks with a stride of 1 or 2 for feature extraction, and the number of filters is doubled after the downsampling operation; the downsampling with a stride of 1 in the first layer is postponed; the extracted features are passed to the decoder through the bridge for estimating the denoised input in the feature domain; the features are transformed into the image domain by each decoder layer through a conversion unit, which consists of n residual blocks, followed by a 1×1 convolutional layer and a sigmoid activation layer; the number of filters in the conversion unit is halved n times, and the filter size of the 1×1 convolutional layer is set to C; It also includes a vascular structure enhancer, which contains a large kernel depthwise separable convolution to extract low-level features, followed by a set of parallel depthwise separable convolutions to capture structural information at different scales; the structural features are fused through two 1×1 convolutional layers, and the vascular structure enhancer is attached to the last decoder layer before entering the transformation unit; The discriminator network consists of ordinary convolutional layers. The output of the conversion unit in the discriminator is converted into a binary mask through a mapper, which consists of a convolutional layer and a sigmoid activation layer.

3. A laser thermal effect evaluation method according to claim 1, characterized in that: A contrast signal-to-noise ratio loss function is introduced into the temporal contrast analysis algorithm, and the contrast between blood vessels and tissues is enhanced by guiding an adversarial distortion learning network.

4. A laser thermal effect evaluation method according to claim 1, characterized in that: The laser speckle contrast image is converted to obtain a laser speckle blood flow index image by using a sequence formed by the original laser speckle blood flow image.

5. A laser speckle blood flow imaging device, characterized in that: It includes a laser speckle imaging system and a therapeutic laser; the laser speckle imaging system consists of an imaging laser, a beam expander, an imaging optical system, an image acquisition system, a bandpass filter, a neutral density adjustable attenuator, and a reflector; The mouse spinal window animal model is fixed in the laser speckle imaging system through a fixing device. The laser generated by the treatment laser is reflected by the first reflector and incident perpendicularly to the intact skin side of the mouse spinal window. At the same time, the blood flow of the side with the skin removed is monitored by the laser speckle imaging system. The imaging laser selects a laser light source in the near-infrared band, and the laser power is adjusted by changing the angle of the neutral density adjustable attenuation plate; the adjusted light beam is expanded by a spot beam expander and then irradiates the mouse spine window through a second reflector; the mouse spine window is imaged by an imaging optical system, and a detector is used to collect the image, which is then transmitted to a data acquisition and analysis system for processing.

6. The laser speckle blood flow imaging device according to claim 5, characterized in that: The method also includes installing an interference bandpass filter with the same central wavelength as the imaging laser in front of the detector to collect dynamic scattering signals; the therapeutic laser uses the therapeutic laser to irradiate the intact skin side of the mouse spinal window.

7. A laser thermal effect evaluation system, characterized in that: include: An acquisition module is used to acquire a sequence of original laser speckle blood flow images, analyze the original laser speckle images using a time contrast analysis algorithm to acquire a laser speckle contrast image; and convert the laser speckle contrast image to acquire a laser speckle blood flow index image; A calculation module is used to calculate the half-height width of the blood vessel in the laser speckle blood flow index image as the width of the blood vessel; and to obtain a difference image by subtracting the blood flow image after laser irradiation from the blood flow image before laser irradiation; The evaluation module is used to obtain the blood vessels with blood flow changes due to laser irradiation based on the difference image, and then select the region of interest to obtain the average blood flow of the blood vessels before and after laser irradiation, so as to evaluate the final laser treatment effect.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the laser thermal effect evaluation method according to any one of claims 1 to 4 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the laser thermal effect evaluation method according to any one of claims 1 to 4 is implemented.

10. A computer program product, comprising computer instructions, characterized in that: The computer instructions instruct the computer to execute the laser thermal effect evaluation method according to any one of claims 1 to 4.

Images