Medical image acquisition and analysis method and system for endocrine patient

Abstract

The invention relates to the technical field of medical image processing, in particular to a medical image acquisition and analysis method and system for an endocrine patient, and the method comprises the following steps: uniformly irradiating the thyroid tissue of the endocrine patient with laser with a target wavelength, detecting and recording the intensity of light reflected back from the tissue surface, and performing initialization mapping on the internal structure of the tissue to obtain an original medical image of the speckles. According to the method, the light intensity change in the speckle image is analyzed, pixel-level calculation is carried out, and tiny change in the tissue is identified in a detailed mode, so that the information amount of the medical image is increased, high-precision basic data is provided for subsequent lesion analysis, and the accuracy of the medical image is improved through the light intensity distribution data. The brightness change between pixels is compared to mark different areas, pathological features are distinguished through texture analysis, the disease early detection and classification ability is improved, and doctors can make a more accurate recovery scheme for patients.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a method and system for collecting and analyzing medical images of endocrine patients. Background Art

[0002] The field of medical image processing technology mainly involves obtaining images of the human body through various imaging techniques, and using digital image processing methods to enhance, analyze and interpret the images to assist recovery. This field integrates knowledge from multiple disciplines such as radiology, computer science, physics and engineering. The main applications include analysis of CT scans, MRI, X-rays and ultrasound images. Through technology, doctors can observe the internal structure of patients without invasive procedures, which helps to diagnose various diseases such as cancer, cardiovascular disease, etc.

[0003] Among them, the medical image acquisition and analysis method for endocrine patients refers to the use of specific medical imaging technology to collect images of patients with endocrine system diseases, and analyze the images through advanced image processing technology to better understand the pathological state and monitor the progression of the disease. The uses of this method include improving the accuracy of early diagnosis of the disease, evaluating the recovery effect, and conducting disease prognosis analysis. Thyroid nodules can be detected and classified by analyzing thyroid ultrasound images, helping doctors develop more personalized recovery plans.

[0004] Existing medical image processing technologies mainly rely on conventional imaging methods, such as CT, MRI, and X-rays. Although the technology can provide clear images of internal structures, its resolution and sensitivity are limited when identifying tiny lesions or early stages of the disease. Early tiny tumors are not easily identified with conventional imaging technology, resulting in an increased risk of missed diagnosis or misdiagnosis. Existing technologies rely heavily on manual operations in the post-processing and analysis of images, which not only increases the time cost of the judgment process, but also affects the objectivity and consistency of the judgment due to the subjective judgment of the operator. In terms of processing details, such as texture feature recognition and classification of tiny lesions, existing technologies fail to provide sufficient analysis tools, making it difficult to meet the needs of precision medicine in clinical applications. Summary of the invention

[0005] In order to solve the problem that the existing technology has limited resolution and sensitivity when identifying tiny lesions or early stages of the disease. Early tiny tumors are not easy to be clearly identified in conventional imaging technology, resulting in an increased risk of missed diagnosis or misdiagnosis. The existing technology relies heavily on manual operation in the post-processing and analysis of images, which not only increases the time cost of the judgment process, but also affects the objectivity and consistency of the judgment due to the subjective judgment of the operator. In terms of processing details, such as texture feature recognition and classification of tiny lesions, the existing technology fails to provide sufficient analysis tools, resulting in technical problems that it is difficult to achieve the needs of precision medicine in clinical applications. The embodiment of the present invention provides a medical image acquisition and analysis method and system for endocrine patients. The technical solution is as follows: In one aspect, a method for collecting and analyzing medical images of endocrine patients is provided, the method comprising: S1: Use laser of target wavelength to evenly irradiate the thyroid tissue of endocrine patients, detect and record the intensity of light reflected from the tissue surface, perform initial mapping of the internal structure of the tissue, and obtain the original speckle medical image; S2: Analyzing the light intensity of each point in the original speckle medical image, performing pixel-level light intensity calculation, referring to the changes of multiple pixel points, identifying the distribution characteristics of the light spots in the original speckle medical image, and obtaining light intensity distribution data; S3: According to the light intensity distribution data, compare the brightness changes between the differentiated pixels, identify the areas with light and dark differences, mark the areas, perform texture analysis on the differentiated parts of the image, and output a texture feature map; S4: Based on the texture feature map, adjusting the brightness and contrast parameters of multiple regions of the medical image, automatically processing the details of the image, optimizing the resolution of the medical image, and obtaining an optimized speckle image; S5: Using the optimized speckle image, image segmentation is performed to divide the image into differential analysis areas, texture recognition is performed on each area, multiple texture types are marked and classified, characteristics of each area are identified, and endocrine pathology feature mapping records are obtained.

[0006] As a further solution of the present invention, the speckle original medical image includes a microstructure mapping of the tissue, a light reflection pattern after laser irradiation, and an initialized visualization of the light intensity; the light intensity distribution data includes information on pixel brightness values, brightness gradients, and speckle patterns; the texture feature mapping includes regional division, texture density within differentiated regions, and feature identification in light and dark contrast; the optimized speckle image includes adjusted color saturation, contrast optimization regions, and detail optimized regions; the endocrine pathology feature mapping record includes the spatial position, area size, and boundary with adjacent textures of each texture type.

[0007] As a further solution of the present invention, the steps of uniformly irradiating the thyroid tissue of an endocrine patient with a laser of a target wavelength, detecting and recording the intensity of light reflected from the tissue surface, and performing initialization mapping of the internal structure of the tissue to obtain the original speckle medical image are as follows: S101: Evenly irradiate the thyroid tissue of the endocrine patient with a laser of a target wavelength, set the output power and irradiation time of the laser, match the light absorption rate of the thyroid tissue, adjust the wavelength, check the uniform distribution of the laser intensity, and obtain evenly irradiated image data; S102: Based on the uniformly illuminated image data, use a photodetector to record the intensity of light reflected from the tissue, adjust the angle and distance of the detector to optimize signal reception, and optimize the time response of the detector to capture instantaneous changes, and obtain reflected light intensity data; S103: Analyze and reconstruct the reflected light intensity data, adjust the image contrast and brightness, optimize the quality of the medical image, improve the details of the image, and obtain the original speckle medical image.

[0008] As a further solution of the present invention, by analyzing the light intensity of each point in the original speckle medical image, performing pixel-level light intensity calculation, referring to the changes of multiple pixel points, identifying the distribution characteristics of the light spots in the original speckle medical image, the steps of obtaining light intensity distribution data are specifically as follows: S201: quantifying and calculating the light intensity of each pixel point according to the original speckle medical image, accurately measuring the light intensity value, and performing data normalization processing to obtain pixel-level light intensity data; S202: Using the pixel-level light intensity data, screening the light intensity by setting a threshold, removing noise using filtering technology and identifying the characteristics of the light spots in the original medical image of the speckle, optimizing the contrast and image sharpness, analyzing the distribution pattern of the light spots, and obtaining the light spot distribution information; S203: Utilizing the light spot distribution information, statistical analysis of multi-point light intensity is performed, light intensity changes in differentiated areas are compared, light intensity distribution characteristics are calculated, and light intensity distribution data is obtained.

[0009] As a further solution of the present invention, the formula for calculating the light intensity distribution characteristic is as follows: in, is the light intensity value, and represents the pixel position in the image, Representative The mixing weights of the components, and Respectively represent Gaussian components in and The mean value in the direction, Representative The standard deviation of the Gaussian components, is the natural exponential function, is the number of ingredients.

[0010] As a further solution of the present invention, according to the light intensity distribution data, the brightness changes between the differentiated pixels are compared, the areas with light and dark differences are identified, the areas are marked, and texture analysis is performed on the differentiated parts of the image to output the texture feature map. Specifically, the steps are as follows: S301: Analyze and compare brightness changes between differentiated areas based on the light intensity distribution data, set a brightness difference threshold to differentiate between light and dark areas, mark the light and dark differentiated parts, and obtain light and dark difference area data; S302: Using the light and dark difference area data, texture feature recognition is performed on the marked image area to match the recognition requirements of the differentiated texture, and the consistency of the texture data is enhanced through a statistical model to obtain regional texture feature data; S303: Using the regional texture feature data and image mapping technology, the texture features are visualized, mapping parameters are adjusted, the visual effects and texture detail representation of the medical image are optimized, and a texture feature map is output.

[0011] As a further solution of the present invention, based on the texture feature map, the brightness and contrast parameters of multiple regions of the medical image are adjusted, the details of the image are automatically processed, the resolution of the medical image is optimized, and the steps of obtaining the optimized speckle image are specifically as follows: S401: using the texture feature mapping, respectively adjusting brightness and contrast parameters for multiple regions of the acquired medical image, optimizing the visual performance of the regions one by one, optimizing the detail display of the image, and obtaining a brightness adjustment contrast record; S402: optimizing the details of the medical image through the brightness adjustment comparison record, adjusting the image resolution setting to match the output requirements, and obtaining detail-optimized image data; S403: Utilizing the detailed optimized image data, iteratively optimizing the overall visual effect of the medical image, verifying that the quality of the medical image of the endocrine patient matches the disease judgment criteria, and obtaining an optimized speckle image.

[0012] As a further solution of the present invention, the optimized speckle image is used to perform image segmentation, divide the image into differential analysis areas, perform texture recognition on each area, mark and classify multiple texture types, identify the characteristics of each area, and obtain the endocrine pathology feature mapping record in the following steps: S501: Based on the optimized speckle image, the speckle image is divided into differentiated analysis areas, region recognition and boundary refinement are performed, the regions to which the pixels belong are calculated, and image partition records are obtained; S502: using the image partition record, performing texture analysis on each partition, setting texture recognition thresholds and parameters to distinguish differentiated texture types, marking and classifying textures in the image, and obtaining texture classification data; S503: Using the texture classification data, the texture characteristics of each region are identified and recorded, and the texture types and characteristics in the medical image are compared and classified to obtain an endocrine pathology feature mapping record.

[0013] As a further solution of the present invention, the formula for calculating the region to which the pixel belongs is: in, is the region to which the pixel belongs, Represents pixel The gray value in the speckle image, represents the threshold value, Represents the grayscale standard deviation of the neighborhood around the pixel, , and is the weight coefficient, Represents the correction factor.

[0014] On the other hand, a medical image acquisition and analysis system for endocrine patients is provided, wherein the medical image acquisition and analysis system for endocrine patients is used to perform the above-mentioned medical image acquisition and analysis method for endocrine patients, and the system comprises: The laser irradiation module evenly irradiates the thyroid tissue of endocrine patients, selects the laser of the target wavelength, records the intensity of light reflected from the tissue surface, and obtains the reflected light intensity data; The initial mapping analysis module uses the reflected light intensity data to initialize the mapping of the internal structure of the thyroid tissue to obtain the original speckle medical image; The light intensity calculation module performs pixel-level calculation on the light intensity of each point in the original speckle medical image, analyzes the changes of multiple pixel points, identifies the distribution characteristics of the light spots, and obtains light intensity distribution data; The image texture analysis module compares the brightness changes between pixels according to the light intensity distribution data, marks the light and dark difference areas, performs texture analysis, and outputs a texture feature map; The image adjustment module adjusts the brightness and contrast parameters of multiple regions of the medical image based on the texture feature map, processes image details, optimizes resolution, and obtains an optimized speckle image; The image segmentation module uses the optimized speckle image to perform image segmentation, divide the differentiated analysis areas, perform texture recognition on each area, mark multiple texture types, and obtain endocrine pathology feature mapping records.

[0015] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: By irradiating the thyroid tissue of endocrine patients with lasers of a specific wavelength and recording the reflected light, the original speckle image is obtained, and the internal structure of the tissue is directly mapped using laser irradiation to provide preliminary structural visual information. The light intensity changes in the speckle image are analyzed, pixel-level calculations are performed, and small changes in the tissue are identified in a detailed manner, which not only increases the amount of information in the medical image, but also provides high-precision basic data for subsequent lesion analysis. Through the light intensity distribution data, the brightness changes between pixels are compared to mark different areas, and pathological features are distinguished through texture analysis. This refinement process significantly enhances the accuracy of disease judgment. Adjusting the image brightness and contrast to optimize the image resolution, and further analyzing endocrine patients through image segmentation and texture classification, the ability to detect and classify diseases early is improved, which helps doctors develop more accurate recovery plans for patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flow chart of S1 of the present invention; Figure 3 This is a detailed flow chart of S2 of the present invention; Figure 4 This is a detailed flow chart of S3 of the present invention; Figure 5 This is a detailed flow chart of S4 of the present invention; Figure 6 This is a detailed flow chart of S5 of the present invention; Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0018] In the embodiments of the present invention, words such as "exemplarily" and "set" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0019] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0020] See also Figure 1 The embodiment of the present invention provides a method for collecting and analyzing medical images of endocrine patients. The processing flow of the method may include the following steps: S1: Use laser of target wavelength to evenly irradiate the thyroid tissue of endocrine patients, detect and record the intensity of light reflected from the tissue surface, perform initial mapping of the internal structure of the tissue, and obtain the original speckle medical image; S2: Analyze the light intensity of each point in the original medical image of speckle, calculate the light intensity at the pixel level, refer to the changes of multiple pixel points, identify the distribution characteristics of the light spots in the original medical image of speckle, and obtain the light intensity distribution data; S3: According to the light intensity distribution data, compare the brightness changes between the differentiated pixels, identify the areas with light and dark differences, mark the areas, perform texture analysis on the differentiated parts of the image, and output a texture feature map; S4: Based on texture feature mapping, adjust the brightness and contrast parameters of multiple areas of the medical image, automatically process the details of the image, optimize the resolution of the medical image, and obtain the optimized speckle image; S5: Use the optimized speckle image to perform image segmentation, divide the image into differential analysis areas, perform texture recognition on each area, mark and classify multiple texture types, identify the characteristics of each area, and obtain endocrine pathology feature mapping records.

[0021] The original medical image of speckle includes the microstructure mapping of the tissue, the light reflection pattern after laser irradiation, and the initial visualization of the light intensity. The light intensity distribution data includes the pixel brightness value, brightness gradient, and speckle pattern information. The texture feature mapping includes area division, texture density in differentiated areas, and feature identification in light and dark contrast. The optimized speckle image includes adjusted color saturation, contrast optimization area, and detail optimization area. The endocrine pathology feature mapping record includes the spatial position, area size, and boundary with adjacent textures of each texture type.

[0022] See also Figure 2 , the thyroid tissue of endocrine patients is uniformly irradiated with laser of target wavelength, the intensity of light reflected from the tissue surface is detected and recorded, and the internal structure of the tissue is initialized and mapped. The specific steps to obtain the original speckle medical image are as follows: S101: Uniformly irradiate the thyroid tissue of the endocrine patient with a laser of a target wavelength, set the output power and irradiation time of the laser, match the light absorption rate of the thyroid tissue, adjust the wavelength to check the uniform distribution of the laser intensity, and obtain the uniformly irradiated image data in the following execution process; The power and irradiation time of the laser need to be set. These two parameters are crucial to the effect of laser restoration. The power and irradiation time must be precisely controlled to match the specific light absorption rate of the thyroid tissue. This needs to be determined through laboratory testing of the laser and preliminary analysis of thyroid tissue samples to ensure that the light energy is effectively absorbed and does not cause tissue damage. For the adjustment of the wavelength, the characteristics of the tissue absorption spectrum must also be considered and optimized through multiple experiments. The choice of wavelength directly affects the depth and range of recovery. The uniform distribution of laser intensity is achieved through a specific optical path design. Setting up the use of a beam homogenizer or adjusting the focus of the beam are all for obtaining better irradiation effects, ensuring that each part of the thyroid tissue can receive the same degree of light intensity, and obtaining uniformly irradiated image data through fine settings.

[0023] S102: Based on the uniformly illuminated image data, a photodetector is used to record the intensity of light reflected from the tissue, and the angle and distance of the detector are adjusted to optimize signal reception, while the time response of the detector is optimized to capture instantaneous changes. The execution process of obtaining reflected light intensity data is as follows; A photodetector is used to record the intensity of light reflected from thyroid tissue. Based on this data, the angle and distance of the detector are adjusted to the optimal position to optimize signal reception. This process involves adjusting the sensitivity of the detector and fine-tuning the angle to ensure that the weak signal reflected from the tissue can be captured. Optimizing the time response of the detector is also key. The detector's electronic components and algorithms need to be adjusted to improve the speed and accuracy of capturing changes in light signals, ensuring that even instantaneous changes in light intensity can be effectively recorded to obtain reflected light intensity data.

[0024] S103: Using the reflected light intensity data, analyzing and reconstructing the reflected data, adjusting the image contrast and brightness to optimize the quality of the medical image, improving the details of the image, and obtaining the speckle original medical image. The execution process is as follows; The reflection data is analyzed and reconstructed according to the formula: Calculate the reflected light intensity data, where: represents the intensity of reflected light, represents the incident light intensity, represents the reflectivity, represents the absorption coefficient of the tissue, represents the distance the light penetrates, is a natural constant; Set the incident light intensity is 100 units, reflectivity is 0.8, tissue absorption coefficient The light penetration distance is 0.1 per millimeter. is 2 mm, substitute into the formula: This result shows that the quantification of reflected light intensity after absorption and reflection by tissue can further optimize the quality of medical images and enhance the level of detail of the images by adjusting image contrast and brightness.

[0025] See also Figure 3 , by analyzing the light intensity of each point in the original speckle medical image, performing pixel-level light intensity calculation, referring to the changes of multiple pixel points, identifying the distribution characteristics of the light spots in the original speckle medical image, and obtaining the light intensity distribution data in the following steps: S201: According to the original speckle medical image, the light intensity of each pixel is quantitatively calculated, the light intensity value is accurately measured, and the data is normalized. The execution process of obtaining pixel-level light intensity data is as follows; The light intensity of each pixel is quantitatively calculated in detail and the light intensity value of each pixel is accurately measured. This process involves the use of high-precision image sensors and quantitative analysis software. Through this technology, the measurement accuracy and repeatability of light intensity can be ensured, and data normalization is performed. Normalization is to adjust the scale of the data to a common range, such as between 0 and 1, so that the image data is more suitable for subsequent processing and analysis steps to obtain light intensity distribution data.

[0026] S202: The execution process of filtering the light intensity by setting a threshold through the pixel-level light intensity data, removing noise and identifying the characteristics of the light spots in the original medical image of the speckle by using filtering technology, optimizing the contrast and image sharpness, analyzing the distribution pattern of the light spots, and obtaining the light spot distribution information is as follows; The light intensity is screened by setting a threshold. The determination of this threshold is based on the statistical analysis of the light intensity data. The purpose is to distinguish the meaningful light spots from the background noise in the image. The noise in the image is removed by filtering technology. The filtering technology mainly includes frequency domain filtering and spatial filtering, which can effectively remove irrelevant noise in the image, retain important light spot features, optimize contrast and image sharpness, and enhance the light spot features in the image by adjusting the color scale and sharpening the edges of the image, making the light spot more obvious. The distribution pattern of the light spot is analyzed, which involves image analysis technology, such as image segmentation and pattern recognition, to obtain the light spot distribution information.

[0027] S203: Utilize the light spot distribution information to perform statistical analysis of the light intensity at multiple points, compare the light intensity changes in the differentiated areas, calculate the light intensity distribution characteristics, and obtain the light intensity distribution data. The execution process is as follows; The formula for calculating the light intensity distribution characteristics is as follows: in, is the light intensity value, and represents the pixel position in the image, Representative The mixing weights of the components, and Respectively represent Gaussian components in and The mean value in the direction, Representative The standard deviation of the Gaussian components, is the natural exponential function, is the number of ingredients;

[0028] Parameter meaning and setting value: and Represents the pixel position in the image. For a specific image pixel, set , directly obtained from image data; Indicates The mixture weights of the Gaussian components are determined by the monitored data and set , indicating that the first Gaussian distribution contributes 30% to the total mixture model; and Respectively Gaussian components in and The mean value in the direction is obtained through cluster analysis in the image processing software, and the setting and , indicating that the center of the first Gaussian distribution is located at the ; For the The standard deviation of the Gaussian components determines the width of the Gaussian distribution, which is calculated by comparing the spot distribution statistics using image processing software. , describes the spread of the first Gaussian distribution; Substitute the parameters into the formula for calculation: The result 0.0168 indicates that at the image position The estimated light intensity is low and can be used to compare the light intensity of different areas within the same image to identify and refine structural differences within thyroid tissue.

[0029] See also Figure 4 , according to the light intensity distribution data, compare the brightness changes between the differentiated pixels, identify the areas with light and dark differences, mark the areas, and perform texture analysis on the differentiated parts of the image. The specific steps of outputting the texture feature map are: S301: Based on the light intensity distribution data, analyze and compare the brightness changes between the differentiated areas, set the brightness difference threshold to distinguish the light and dark areas, mark the light and dark differentiated parts, and the execution process of obtaining the light and dark difference area data is as follows; Through detailed analysis and comparison of the brightness between differentiated areas, a brightness difference threshold is set to distinguish the light and dark areas in the image. The setting of this threshold is determined based on the statistical distribution characteristics of the brightness of each area in the image. Areas above the threshold are considered bright areas, and areas below the threshold are considered dark areas. The parts distinguished between light and dark are clearly marked. This marking process needs to be completed with the help of automated tools in image processing software to improve processing efficiency and accuracy, and ensure that the data can reflect important brightness changes in the image, providing a basis for subsequent texture feature analysis and obtaining data on light and dark difference areas.

[0030] S302: Using the light and dark difference area data, texture feature recognition is performed on the marked image area to match the recognition requirements of the differentiated texture, and the consistency of the texture data is strengthened through the statistical model. The execution process of obtaining the regional texture feature data is as follows; Calculate the regional texture feature data, where: Represents texture features, Represents the number of texture data points, represents the brightness value of a single data point, Represents the average brightness; set up There are 10 data points, and the brightness value of each data point is is [120, 125, 130, 135, 140, 145, 150, 155, 160, 165], the average brightness is 137.5, substitute into the formula: This result shows that the texture inhomogeneity in this region is used to further enhance the consistency of texture data through statistical models, obtain more accurate regional texture feature data, and effectively identify differentiated textures.

[0031] S303: Using the regional texture feature data and image mapping technology, the texture features are visualized, the mapping parameters are adjusted, the visual effects and texture detail performance of the medical image are optimized, and the execution process of outputting the texture feature mapping is as follows; Image mapping technology is used to convert data into visual texture representation. In this process, adjusting the mapping parameters is crucial. It is necessary to fine-tune parameters such as color, contrast, and brightness to optimize the visual effects of the image and the representation of texture details. The adjustment of mapping parameters is based on the preset visual effect goals and involves color correction and dynamic range optimization to ensure the clarity and recognition of texture features in medical images. This process not only relies on the support of algorithms, but also requires the experience input of medical imaging experts to ensure that the representation of texture features matches clinical needs, providing doctors with more judgment information, facilitating disease identification, and outputting texture feature mapping.

[0032] See also Figure 5 Based on texture feature mapping, the brightness and contrast parameters of multiple areas of the medical image are adjusted to automatically process the details of the image and optimize the resolution of the medical image. The specific steps for obtaining the optimized speckle image are as follows: S401: Using texture feature mapping, adjust the brightness and contrast parameters of multiple regions of the collected medical image respectively, optimize the visual performance of the regions one by one, optimize the detail display of the image, and obtain the execution process of the brightness adjustment contrast record as follows; Adjust the brightness and contrast parameters of multiple areas of the acquired medical image separately according to the formula: Calculate the brightness adjustment contrast record, where, Represents the adjusted brightness value, Represents the original brightness value, Represents the brightness adjustment coefficient; Set the original brightness value The brightness adjustment factor is 100 units. is 0.2, substitute into the formula: This result shows that by optimizing the visual performance of each area one by one, the detail display of the image can be enhanced, making the medical image more suitable for subsequent clinical analysis and disease diagnosis.

[0033] S402: Optimizing the details of the medical image by comparing the records with brightness adjustment, adjusting the image resolution setting to match the output requirements, and obtaining the detailed optimized image data are performed as follows; Further optimization of the details of medical images includes adjusting the image resolution to match different output requirements. The resolution adjustment is determined by the application scenario of the image and the display characteristics of the viewing device. Setting a higher resolution image for a high-definition display requires image quality. This process involves the application of image resampling technology. The image is interpolated through an algorithm to increase the pixel points of the image and improve the resolution. The optimization of details also requires adjusting the image sharpening parameters. By enhancing the contrast of the image edges, the details of the image are made clearer. Through the application of this technology, detail-optimized image data is obtained.

[0034] S403: Optimizing image data with details, iteratively optimizing the overall visual effect of the medical image, verifying that the quality of the medical image of the endocrine patient matches the judgment criteria of the disease, and obtaining the optimized speckle image. The execution process is as follows; The overall visual effect of medical images is improved through an iterative optimization process. During this process, the focus is on verifying whether the image quality matches the disease judgment criteria of endocrine patients. The optimized image must be able to clearly show the characteristics of the lesion area. Iterative optimization includes continuously adjusting the color balance and contrast of the image to meet the visual needs of clinicians. The accuracy and reliability of medical information recognition are enhanced through specific image processing algorithms to ensure that doctors can make accurate disease judgments based on images and obtain optimized speckle images.

[0035] See also Figure 6 ,Using the optimized speckle image, image segmentation is performed to divide the image into differential analysis areas, texture recognition is performed for each area, multiple texture types are marked and classified, the characteristics of each area are identified, and the steps for obtaining the endocrine pathology feature mapping record are as follows: S501: Based on the optimized speckle image, the speckle image is divided into differentiated analysis areas, region identification and boundary refinement are performed, the regions to which the pixels belong are calculated, and image partition records are obtained; The formula for calculating the pixel's belonging area is: in, is the region to which the pixel belongs, Represents pixel The gray value in the speckle image, represents the threshold value, Represents the grayscale standard deviation of the neighborhood around the pixel, , and is the weight coefficient, represents the correction factor; Parameter meaning and setting value: Represents pixel The grayscale value in the speckle image is obtained by reading the pixels of the image, and the value is set to 150; is the threshold, which is determined by analyzing the overall grayscale distribution of the image and is set to 100; Represents the grayscale standard deviation of the neighborhood around the pixel, reflecting the texture change of the local image. It is calculated by counting the grayscale values ​​of all pixels in the neighborhood, and the set value is 200; , and is the weight coefficient, which is set according to the specific processing requirements of the image: Adjust the gray value difference. Adjust the effect of texture changes, Make sure the denominator is not zero while balancing the contribution of the numerator; is a correction factor used to adjust the effects of image noise or illumination changes, set to a constant, set to 0.2; Substitute the parameters into the formula for calculation: calculate ; calculate ; Substituting the values ​​into the formula: The result 24.37 indicates that the pixel According to the belonging area of ​​the calculation model, a quantitative basis is provided for the partitioning of the speckle image. If the value is higher than a certain set threshold, it indicates the boundary area, and if it is lower than a certain threshold, it belongs to the homogeneous area. This result is used to further identify and divide different partitions of the image, helping to more accurately identify the regional boundaries when processing speckle images.

[0036] S502: Using the image partition record, perform texture analysis on each partition, set texture recognition thresholds and parameters to distinguish differentiated texture types, mark and classify the textures in the image, and obtain texture classification data. The execution process is as follows; Perform a detailed texture analysis on each partition, set the threshold and parameters for texture recognition. The parameters mainly include texture roughness, directionality, contrast, etc. The threshold is set based on comparing the statistical characteristics between different textures to distinguish differentiated texture types. The various textures present in the image are marked and classified. This process involves the use of advanced image processing algorithms to identify and distinguish subtle texture differences. Through the algorithm, useful texture features can be effectively extracted from batch data. The results of marking and classification will be used for subsequent image analysis and medical judgment to improve the accuracy of judgment. The data can be used for further analysis and research to provide doctors with more information about disease characteristics and obtain texture classification data.

[0037] S503: Identify and record the texture characteristics of each region through texture classification data, compare and classify the texture types and characteristics in the medical image, and obtain the execution process of the endocrine pathology feature mapping record as follows; The texture characteristics of each area are identified and recorded, which includes detailed comparison and classification of various texture types and characteristics in the image. The purpose of texture analysis is to clearly distinguish the various tissue types shown in the image. The identification of each texture is based on specific image processing techniques, such as filters and pattern recognition algorithms. The technology can extract and emphasize the texture features in the image, making the judgment of medical images more accurate. Through comparison and classification, the differences in texture in each area can be clarified, which is crucial for identifying lesions and normal tissues. It provides detailed visual information for the medical team to assist in making better decisions in monitoring the disease process and obtain endocrine pathology feature mapping records.

[0038] See also Figure 7 On the other hand, a medical image acquisition and analysis system for endocrine patients is provided, and the medical image acquisition and analysis system for endocrine patients is used to perform the above-mentioned medical image acquisition and analysis method for endocrine patients, and the system includes: The laser irradiation module evenly irradiates the thyroid tissue of endocrine patients, selects the laser of the target wavelength, records the intensity of light reflected from the tissue surface, and obtains the reflected light intensity data; The initial mapping analysis module uses the reflected light intensity data to initialize the mapping of the internal structure of the thyroid tissue and obtain the original speckle medical image; The light intensity calculation module performs pixel-level calculation on the light intensity of each point in the original speckle medical image, analyzes the changes of multiple pixel points, identifies the distribution characteristics of the light spots, and obtains light intensity distribution data; The image texture analysis module compares the brightness changes between pixels based on the light intensity distribution data, marks the areas with different brightness and darkness, performs texture analysis, and outputs a texture feature map; The image adjustment module adjusts the brightness and contrast parameters of multiple regions of the medical image based on texture feature mapping, processes image details, optimizes resolution, and obtains an optimized speckle image; The image segmentation module uses the optimized speckle image to perform image segmentation, divide the differentiated analysis areas, perform texture recognition on each area, mark multiple texture types, and obtain endocrine pathology feature mapping records.

[0039] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for collecting and analyzing medical images of endocrine patients, characterized in that: The following steps are involved: The thyroid tissue of endocrine patients is uniformly irradiated with laser of target wavelength, the intensity of light reflected from the tissue surface is detected and recorded, and the internal structure of the tissue is initialized for mapping to obtain the original medical image of speckle; By analyzing the light intensity of each point in the original speckle medical image, performing pixel-level light intensity calculation, referring to the changes of multiple pixel points, identifying the distribution characteristics of the light spots in the original speckle medical image, and obtaining light intensity distribution data; According to the light intensity distribution data, the brightness changes between the differentiated pixels are compared, the areas with light and dark differences are identified, the areas are marked, and texture analysis is performed on the differentiated parts of the image to output a texture feature map; Based on the texture feature map, the brightness and contrast parameters of multiple regions of the medical image are adjusted, the details of the image are automatically processed, the resolution of the medical image is optimized, and an optimized speckle image is obtained; The optimized speckle image is used to perform image segmentation, divide the image into differential analysis areas, perform texture recognition on each area, mark and classify multiple texture types, identify the characteristics of each area, and obtain an endocrine pathology feature mapping record.

2. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: The original speckle medical image includes the microstructure mapping of the tissue, the light reflection pattern after laser irradiation, and the initial visualization of the light intensity. The light intensity distribution data includes the pixel brightness value, the brightness gradient, and the information of the speckle pattern. The texture feature mapping includes the area division, the texture density in the differentiated area, and the feature identification in the light and dark contrast. The optimized speckle image includes the adjusted color saturation, the contrast optimization area, and the detail optimization area. The endocrine pathology feature mapping record includes the spatial position, area size, and boundary with adjacent textures of each texture type.

3. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: The thyroid tissue of endocrine patients is uniformly irradiated with laser of target wavelength, the intensity of light reflected from the tissue surface is detected and recorded, and the internal structure of the tissue is initialized and mapped. The specific steps to obtain the original medical image of speckle are as follows: Use laser of target wavelength to evenly irradiate the thyroid tissue of endocrine patients, set the output power and irradiation time of the laser, match the light absorption rate of the thyroid tissue, adjust the wavelength to check the uniform distribution of laser intensity, and obtain uniform irradiation image data; Based on the uniformly illuminated image data, a photodetector is used to record the intensity of light reflected from the tissue, and the angle and distance of the detector are adjusted to optimize signal reception, while the time response of the detector is optimized to capture instantaneous changes, so as to obtain reflected light intensity data; The reflected light intensity data is used to analyze and reconstruct the reflected data, adjust the image contrast and brightness to optimize the quality of the medical image, improve the image details, and obtain the original speckle medical image.

4. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: The steps of analyzing the light intensity of each point in the original speckle medical image, performing pixel-level light intensity calculation, and identifying the distribution characteristics of the light spots in the original speckle medical image with reference to the changes of multiple pixel points to obtain the light intensity distribution data are specifically as follows: According to the original speckle medical image, the light intensity of each pixel is quantitatively calculated, the light intensity value is accurately measured, and the data is normalized to obtain pixel-level light intensity data; The light intensity is screened by setting a threshold through the pixel-level light intensity data, and the noise is removed and the characteristics of the light spots in the original medical image of the speckle are identified by filtering technology, the contrast and image sharpness are optimized, and the distribution pattern of the light spots is analyzed to obtain the light spot distribution information; The light spot distribution information is used to perform statistical analysis of the light intensity at multiple points, compare the light intensity changes in the differentiated areas, calculate the light intensity distribution characteristics, and obtain light intensity distribution data.

5. The medical image acquisition and analysis method for endocrine patients according to claim 4, characterized in that: The formula for calculating the light intensity distribution characteristic is as follows: in, is the light intensity value, and represents the pixel position in the image, Representative The mixing weights of the components, and Respectively represent Gaussian components in and The mean value in the direction, Representative The standard deviation of the Gaussian components, is the natural exponential function, is the number of ingredients.

6. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: According to the light intensity distribution data, the brightness changes between the differentiated pixels are compared, the areas with light and dark differences are identified, the areas are marked, and texture analysis is performed on the differentiated parts of the image to output the texture feature map. Specifically, the steps are as follows: Based on the light intensity distribution data, analyzing and comparing the brightness changes between the differentiated areas, setting a brightness difference threshold to differentiate between the light and dark areas, marking the light and dark differentiated parts, and obtaining light and dark difference area data; Using the light and dark difference area data, texture feature recognition is performed on the marked image area to match the recognition requirements of the differentiated texture, and the consistency of the texture data is strengthened through a statistical model to obtain regional texture feature data; By using the regional texture feature data and image mapping technology, the texture features are visualized, the mapping parameters are adjusted, the visual effects and texture detail representation of the medical image are optimized, and the texture feature map is output.

7. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: Based on the texture feature mapping, the brightness and contrast parameters of multiple regions of the medical image are adjusted, the details of the image are automatically processed, the resolution of the medical image is optimized, and the steps of obtaining the optimized speckle image are specifically as follows: Using the texture feature mapping, respectively adjusting the brightness and contrast parameters of multiple regions of the collected medical image, optimizing the visual performance of the regions one by one, optimizing the detail display of the image, and obtaining a brightness adjustment contrast record; By means of the brightness adjustment comparison record, the details of the medical image are optimized, the image resolution setting is adjusted to match the output requirements, and detail-optimized image data is obtained; The detailed optimized image data is used to iteratively optimize the overall visual effect of the medical image, verify that the quality of the medical image of the endocrine patient matches the judgment standard of the disease, and obtain the optimized speckle image.

8. The medical image acquisition and analysis method for endocrine patients according to claim 1, characterized in that: The optimized speckle image is used to perform image segmentation, divide the image into differential analysis areas, perform texture recognition on each area, mark and classify multiple texture types, identify the characteristics of each area, and obtain the endocrine pathology feature mapping record in the following steps: Based on the optimized speckle image, the speckle image is divided into differentiated analysis areas, region recognition and boundary refinement are performed, the regions to which the pixels belong are calculated, and image partition records are obtained; Using the image partition records, performing texture analysis on each partition, setting texture recognition thresholds and parameters to distinguish differentiated texture types, marking and classifying textures in the image, and obtaining texture classification data; The texture characteristics of each region are identified and recorded through the texture classification data, and the texture types and characteristics in the medical image are compared and classified to obtain an endocrine pathology feature mapping record.

9. The medical image acquisition and analysis method for endocrine patients according to claim 8, characterized in that: The formula for calculating the region to which the pixel belongs is: in, is the region to which the pixel belongs, Represents pixel The gray value in the speckle image, represents the threshold value, Represents the grayscale standard deviation of the neighborhood around the pixel, , and is the weight coefficient, Represents the correction factor.

10. A medical image acquisition and analysis system for endocrine patients, characterized in that: According to any one of claims 1 to 9, the medical image acquisition and analysis method for endocrine patients comprises: The laser irradiation module evenly irradiates the thyroid tissue of endocrine patients, selects the laser of the target wavelength, records the intensity of light reflected from the tissue surface, and obtains the reflected light intensity data; The initial mapping analysis module uses the reflected light intensity data to initialize the mapping of the internal structure of the thyroid tissue to obtain the original speckle medical image; The light intensity calculation module performs pixel-level calculation on the light intensity of each point in the original speckle medical image, analyzes the changes of multiple pixel points, identifies the distribution characteristics of the light spots, and obtains light intensity distribution data; The image texture analysis module compares the brightness changes between pixels according to the light intensity distribution data, marks the light and dark difference areas, performs texture analysis, and outputs a texture feature map; The image adjustment module adjusts the brightness and contrast parameters of multiple regions of the medical image based on the texture feature map, processes image details, optimizes resolution, and obtains an optimized speckle image; The image segmentation module uses the optimized speckle image to perform image segmentation, divide the differentiated analysis areas, perform texture recognition on each area, mark multiple texture types, and obtain endocrine pathology feature mapping records.

Images