Thoracic lung medical image processing and analyzing software system with high transmission efficiency

By adopting high-speed image acquisition, data compression and encoding, efficient transmission and image processing and analysis modules in the chest and lung medical image processing system, combined with DPCM and Huffman encoding and region growth algorithms, the bottleneck of data transmission and processing speed in traditional systems is solved. The problem has achieved efficient and fast image data transmission and intelligent analysis, improving diagnostic accuracy and user experience.

CN118967608AActive Publication Date: 2024-11-15XINGXIANG PRECISION MEDICAL TECHNOLOGY (CHENGDU) CO LTD

Patent Information

Application Number
CN202411020199.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-15
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

Traditional chest and lung medical imaging processing systems have bottlenecks in data transmission and processing speed, which cannot meet the real-time processing needs of large-scale imaging data, and it is difficult to achieve automated and high-precision imaging diagnosis based on the subjective experience of doctors.

Method used

A software system including high-speed image acquisition, data compression and coding, efficient transmission, image processing and analysis, result display and report generation was designed. Data compression is used by DPCM and Huffman encoding, and lesions are identified using regional growth algorithms. And efficient transmission and processing are achieved through high-speed network communication and parallel transmission protocols.

Benefits of technology

It realizes efficient, fast transmission and intelligent analysis of image data, reduces the storage space and transmission bandwidth requirements, improves the accuracy and efficiency of image diagnosis, provides an intuitive operation interface and diversified display methods, and improves user experience and medical care. Resource sharing and collaboration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967608A_ABST
    Figure CN118967608A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical information, in particular to a thoracic lung medical image processing and analysis software system with high transmission efficiency, which comprises an image high-speed acquisition module, a data compression and coding module, an efficient transmission module, an image processing and analysis module and a result display and report generation module, the image high-speed acquisition module is used for realizing acquisition of medical image data and ensuring the integrity and real-time performance of the data. Through mutual cooperation of the image high-speed acquisition module, the data compression and coding module, the efficient transmission module, the image processing and analysis module and the result display and report generation module, medical images are efficiently transmitted in real time, the images are processed in real time, lesions are intelligently analyzed and identified, lesion areas are segmented, and diagnosis reports are automatically generated. The requirements for storage space and transmission bandwidth are effectively reduced, and the method has important significance for promoting medical informatization construction and improving the medical service level.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of medical information technology, and specifically relates to a thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency. Background Art

[0002] With the rapid development of medical technology, medical imaging plays an increasingly important role in clinical diagnosis and treatment. Especially thoracic and pulmonary medical imaging, which refers to the imaging of the chest and lungs through medical imaging technology to assist doctors in the diagnosis, treatment and monitoring of diseases. Common medical imaging equipment includes X-ray, CT, and MRI. Through thoracic and pulmonary medical imaging, doctors can observe the structural changes of the lungs and chest, and make a preliminary diagnosis of the disease in combination with clinical symptoms and signs. It plays a key role in the early detection of lung diseases, the evaluation of treatment effects, and the formulation of personalized treatment plans. Traditional systems usually rely on local servers for data processing. Limited by server performance and storage capacity, the processing speed is slow and cannot meet the real-time processing requirements of large-scale image data. Image data is usually transmitted through a local area network or a wired network. The transmission rate is limited by the network bandwidth and stability, which affects the timeliness and accuracy of the data. It also relies on the subjective experience and manual annotation of doctors, making it difficult to achieve automated and high-precision image diagnosis. In this regard, we propose a thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency. Summary of the invention

[0003] In view of the deficiencies of the prior art, the present invention provides a thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency to solve the above technical problems.

[0004] To achieve the above-mentioned object, the present invention provides the following technical solutions: a thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency, the image processing and analysis software system comprising: an image high-speed acquisition module, a data compression and encoding module, an efficient transmission module, an image processing and analysis module, and a result display and report generation module;

[0005] The high-speed image acquisition module is used to collect medical image data and ensure the integrity and real-time performance of the data;

[0006] The data compression and encoding module is used to efficiently compress and encode the collected image data to reduce the data storage space and transmission bandwidth requirements while maintaining image quality;

[0007] The efficient transmission module is used to realize the safe and fast transmission of compressed and encoded image data, supports a variety of network environments and protocols, and ensures the stability and efficiency of data transmission;

[0008] The image processing and analysis module is used to process the received image data and perform intelligent analysis to identify lesions and segment the lesion area through the region growing algorithm;

[0009] The result display and report generation module is used to provide an intuitive and easy-to-use operating interface, support multi-modal and multi-dimensional image display, allow users to make dynamic adjustments and interactive operations, and automatically generate detailed reports containing analysis results to facilitate medical personnel to make accurate diagnoses.

[0010] Preferably, the high-speed image acquisition module is provided with a replaceable slot, and a compatible slot is replaced according to different medical imaging equipment interfaces, supporting rapid acquisition of multiple image formats, including X-ray, CT, and MRI.

[0011] Preferably, the steps of the data compression and encoding module to efficiently compress and encode the image data are as follows:

[0012] S1, the high-speed image acquisition module reads the original chest and lung medical image data;

[0013] S2. Design a predictor based on the characteristics of chest and lung medical images, use the predictor to predict each pixel in the image, calculate the error between the actual pixel value and the predicted value, quantize the prediction error, convert the continuous error value into a discrete quantized value, encode the quantized prediction error, and generate a DPCM-encoded data stream;

[0014] S3, performing frequency statistics on each symbol in the DPCM-encoded data stream to obtain the occurrence probability of each symbol, constructing a Huffman tree according to the frequency of the symbol, and assigning a unique code to each symbol, encoding the DPCM-encoded data stream using the Huffman coding table to generate a Huffman-encoded data stream;

[0015] S4, organize the Huffman-encoded data stream according to the requirements of the PNG format, including the PNG file header, image header, palette, and image data block part, compress the data of the image data block part using the PNG lossless compression algorithm, write the compressed data into the PNG file, and add the necessary file tail information to complete the generation of the PNG file;

[0016] S5. Use the PSNR indicator to evaluate the image quality of compressed chest and lung medical images.

[0017] Preferably, the high-speed transmission module adopts high-speed network communication technology and parallel transmission protocol, supports multi-channel concurrent transmission, and during data transmission, dynamically adjusts transmission parameters according to network conditions, optimizes transmission paths, and ensures efficient transmission of image data within a limited time.

[0018] Preferably, the step of designing a predictor according to the characteristics of chest and lung medical images in step S2 is:

[0019] A1. When selecting a prediction model, consider linear prediction and nonlinear prediction. Linear prediction is based on the linear combination of adjacent pixels, while nonlinear prediction uses polynomial regression to capture spatial relationships.

[0020] A2. According to the characteristics of chest and lung medical images, the weight parameters in the predictor are determined through experiments, and the prediction window size is selected to balance the prediction accuracy and computational complexity;

[0021] A3. Dynamically adjust the parameters of the predictor according to the local characteristics of the current pixel, divide the image into different regions and design different predictors for each region;

[0022] A4. Use global statistical information of the image to assist prediction;

[0023] A5. Collect a large amount of chest and lung medical imaging data, including normal and pathological images, evaluate the performance of different predictors through experiments, adjust the design of the predictor according to the experimental results, and perform multiple iterations to optimize the performance.

[0024] Preferably, the detailed steps of using the PSNR indicator to evaluate the image quality in step S5 are as follows:

[0025] B1. Use the original uncompressed chest and lung medical image as the reference image, and use the compressed chest and lung medical image as the image to be evaluated;

[0026] B2, MSE is the average value of the square difference between the corresponding pixels of two images, and the calculation formula is:

[0027]

[0028] Where I(i,j) and K(i,j) are the pixel values ​​of the original image and the compressed image at position (i,j), respectively, and m and n are the height and width of the image, respectively;

[0029] B3, PSNR is calculated based on MSE, and its calculation formula is:

[0030]

[0031] Among them, MAX is the maximum value of the pixel value in the image;

[0032] B4. According to the calculated PSNR value, the quality of the compressed chest and lung medical images is evaluated. A PSNR value between 30dB and 50dB indicates good image quality. When the PSNR value is greater than 50dB, the quality of the compressed image is almost the same as the original image. When the PSNR value is lower than 30dB, the image quality is poor.

[0033] Preferably, the image processing and analysis module processes the received image data using methods including image denoising, image enhancement, image registration and image three-dimensional reconstruction.

[0034] Preferably, the specific steps and methods of the region growing algorithm for intelligent analysis and identification of lesions and segmentation of lesion regions are as follows:

[0035] C1. Select one or more seed points in the medical image, located inside the lesion or lesion area, and the selection of seed points is achieved by manual designation method;

[0036] C2, the metric criteria for determining pixel similarity, including the difference in grayscale values, color differences, and texture features of pixels;

[0037] C3, take the initial seed point as a region and add it to the region set;

[0038] C4. In each iteration, select a region from the region set and traverse the neighboring pixels of the region;

[0039] C5. Repeat the above iterative growth process until all pixels have been visited or no new pixels can be added to the region;

[0040] C6. Output the final set of regions as the image segmentation result. In medical images, these segmented regions usually represent different tissues or lesion sites.

[0041] Preferably, the processed images and analysis results are displayed through a graphical user interface to provide a basis for diagnosis, and a standardized diagnostic report containing patient information, image description, and diagnostic conclusion is automatically generated.

[0042] Preferably, the system adopts a modular design, and each module is relatively independent to facilitate maintenance and upgrading.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] This application achieves the purpose of efficient real-time transmission of medical images, real-time processing of images and intelligent analysis to identify lesions, segment lesion areas, and automatically generate diagnostic reports through the cooperation of high-speed image acquisition module, data compression and encoding module, efficient transmission module, image processing and analysis module, and result display and report generation module. Through the data compression and encoding module and efficient transmission module, the redundant information of image data in the storage and transmission process is greatly reduced, and the demand for storage space and transmission bandwidth is effectively reduced, thereby realizing efficient and fast transmission of image data. While efficiently compressing and encoding, the system adopts advanced algorithms and technologies to ensure that the image data is minimally lost during the compression process, maintaining The high definition and detailed information of the original images provide a reliable data basis for subsequent image processing and analysis. The image processing and analysis module reduces the reliance on manual intervention through the regional growing algorithm, and improves the accuracy and efficiency of image diagnosis. The result display and report generation module provides an intuitive and easy-to-use operation interface and a variety of display methods, allowing users to make dynamic adjustments and interactive operations, greatly improving the user experience. It shows significant beneficial effects in improving image transmission efficiency, ensuring image data quality, improving image processing and analysis accuracy, optimizing user experience, and promoting medical resource sharing and collaboration. It is of great significance to promote the construction of medical informatization and improve the level of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is the framework diagram of the thoracic and pulmonary medical image processing and analysis software system. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] The present invention provides a technical solution: a thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency, the image processing and analysis software system comprising: an image high-speed acquisition module, a data compression and encoding module, an efficient transmission module, an image processing and analysis module, and a result display and report generation module;

[0048] The high-speed image acquisition module is used to collect medical image data and ensure the integrity and real-time performance of the data;

[0049] The data compression and encoding module is used to efficiently compress and encode the collected image data to reduce the data storage space and transmission bandwidth requirements while maintaining image quality;

[0050] The efficient transmission module is used to realize the safe and fast transmission of compressed and encoded image data, supports a variety of network environments and protocols, and ensures the stability and efficiency of data transmission;

[0051] The image processing and analysis module is used to process the received image data and perform intelligent analysis to identify lesions and segment the lesion area through the region growing algorithm;

[0052] The result display and report generation module is used to provide an intuitive and easy-to-use operating interface, support multi-modal and multi-dimensional image display, allow users to make dynamic adjustments and interactive operations, and automatically generate detailed reports containing analysis results to facilitate medical personnel to make accurate diagnoses.

[0053] Furthermore, the high-speed image acquisition module is equipped with a replaceable slot, which can be replaced with a compatible slot according to the different medical imaging device interfaces to ensure compatibility with the medical imaging device. This plug-and-play design simplifies the device connection process and avoids compatibility issues caused by interface mismatches, thereby improving the overall operating efficiency of the system and supporting rapid acquisition of multiple image formats, enabling the system to access different types of image data sources and provide materials for subsequent data processing and analysis, including X-ray, CT, and MRI.

[0054] Furthermore, the steps of the data compression and encoding module to efficiently compress and encode the image data are as follows:

[0055] S1, the high-speed image acquisition module reads the original chest and lung medical image data;

[0056] S2. Design a predictor based on the characteristics of chest and lung medical images. The predictor uses the spatial correlation between pixels in the image and uses the predictor to predict each pixel in the image. The prediction process is based on the grayscale value, texture features or structural information of the surrounding pixels, and calculates the error between the actual pixel value and the predicted value. The prediction error is quantized, and the continuous error value is converted into a discrete quantized value to reduce data redundancy. The quantized prediction error is encoded to generate a DPCM-encoded data stream. This process effectively reduces the dynamic range of the data and provides a more compressible data format for subsequent encoding.

[0057] S3. Perform frequency statistics on each symbol in the DPCM-encoded data stream to obtain the occurrence probability of each symbol. A Huffman tree is constructed based on the frequency of the symbol, and a unique code is assigned to each symbol, the length of which is inversely proportional to its occurrence probability. Using the Huffman coding table to encode the DPCM-encoded data stream can further reduce the length of the data, because symbols with high occurrence frequency are assigned shorter codes, while symbols with low frequency are assigned longer codes. This process generates a Huffman-encoded data stream to achieve efficient data compression;

[0058] S4. Organize the Huffman-encoded data stream according to the requirements of the PNG format. PNG is a widely used lossless compression image format that supports transparency, palette index and multiple compression algorithms, including PNG file header, image header, palette and image data block parts. The module first adds the PNG file header and image header data parts to describe the basic information of the image. If the image contains palette information, the palette part is added, and the data of the image data block part is compressed using the PNG lossless compression algorithm. The compressed data is written into the PNG file, and the necessary file tail information is added to complete the generation of the PNG file.

[0059] S5. Use the PSNR indicator to evaluate the image quality of compressed chest and lung medical images. PSNR is a common method to measure the quality of compressed images. It is calculated by comparing the grayscale value difference between the original image and the compressed image at the corresponding pixel points. A higher PSNR value means better quality of the compressed image, that is, less image distortion. By evaluating the PSNR value, medical personnel can understand the impact of compression processing on the diagnostic value of the image, and thus adjust the compression parameters to achieve the best effect.

[0060] Furthermore, as an important link in the entire thoracic and pulmonary medical image processing and analysis system, the performance and stability of the high-speed transmission module are directly related to whether the image data can be delivered to the target location in a timely and accurate manner, which in turn affects the efficiency and accuracy of medical diagnosis. To this end, the high-speed transmission module adopts high-speed network communication technology and parallel transmission protocol, and supports multi-channel concurrent transmission. Compared with traditional serial transmission, parallel transmission can transmit multiple data bits at the same time, thereby transmitting more data in the same amount of time. Through the designed parallel transmission protocol, the module can support multi-channel concurrent transmission, that is, using multiple transmission channels for data transmission at the same time. During the data transmission process, the transmission parameters are dynamically adjusted according to the network status to optimize the transmission path. This mechanism can monitor the network status in real time, including key indicators such as bandwidth, delay, and packet loss rate, to ensure that the image data is efficiently transmitted within a limited time.

[0061] Furthermore, in step S2, the predictor step is designed according to the characteristics of chest and lung medical images:

[0062] A1. Consider linear prediction and nonlinear prediction when selecting a prediction model. Linear prediction is based on the linear combination of adjacent pixels. This method is simple and intuitive, with high computational efficiency, and is suitable for relatively smooth or gradient areas in the image. However, chest and lung medical images often contain rich texture, edge and detail information. Nonlinear prediction uses polynomial regression to capture spatial relationships. By combining the advantages of linear prediction and nonlinear prediction, a more flexible and efficient predictor is designed in the edge and texture-rich areas of the image.

[0063] A2. According to the characteristics of chest and lung medical images, the weight parameters in the predictor are determined through experiments. For images of the lung area, due to the more uniform texture, it is more inclined to use smaller weight differences. For areas with lesions such as blood vessels and nodules, the weights need to be adjusted more finely to capture subtle changes. The prediction window size is selected, which determines the pixel range considered during prediction. If the window is too large, unnecessary noise and computational burden will be introduced, while if the window is too small, the spatial correlation of the image cannot be fully utilized. In this way, the prediction accuracy and computational complexity are balanced.

[0064] A3. Dynamically adjust the parameters of the predictor according to the local characteristics of the current pixel, divide the image into different regions and design different predictors for each region. For example, a set of parameters is used in the lung region to capture its uniform texture characteristics, while another set of parameters is required in the blood vessel or nodule region to better capture its edge and detail information. This local characteristic-driven parameter adjustment method enables the predictor to more flexibly cope with complex changes in the image, thereby improving the overall compression efficiency.

[0065] A4. Use the global statistical information of the image to assist prediction. The global statistical information includes the mean, variance, and histogram distribution of the image, which reflect the overall characteristics of the image. By using this information, the prediction results can be further corrected and optimized.

[0066] A5. Collect a large amount of chest and lung medical imaging data, including normal and pathological images, evaluate the performance of different predictors through experiments, adjust the design of the predictor according to the experimental results, and perform multiple iterations to optimize the performance.

[0067] Furthermore, the detailed steps of using the PSNR indicator to evaluate image quality in step S5 are as follows:

[0068] B1. Use the original uncompressed chest and lung medical image as the reference image, and use the compressed chest and lung medical image as the image to be evaluated;

[0069] B2, MSE is the average value of the square difference between the corresponding pixels of two images, and the calculation formula is:

[0070]

[0071] Where I(i,j) and K(i,j) are the pixel values ​​of the original image and the compressed image at position (i,j), respectively, and m and n are the height and width of the image, respectively;

[0072] B3, PSNR is calculated based on MSE, and its calculation formula is:

[0073]

[0074] Among them, MAX is the maximum value of the pixel value in the image;

[0075] B4. According to the calculated PSNR value, the quality of the compressed chest and lung medical images is evaluated. A PSNR value between 30dB and 50dB indicates good image quality. When the PSNR value is greater than 50dB, the quality of the compressed image is almost the same as the original image. When the PSNR value is lower than 30dB, the image quality is poor.

[0076] Furthermore, the image processing and analysis module processes the received image data using methods including image denoising, image enhancement, image registration and image three-dimensional reconstruction;

[0077] Image denoising aims to eliminate or reduce the noise components in the image to improve the clarity and signal-to-noise ratio of the image. The sources of noise in chest and lung medical images include equipment noise, transmission noise, and patient factors. There are many methods for image denoising, the most common of which are median filtering, Gaussian filtering, and wavelet transform denoising.

[0078] Image enhancement aims to improve the visual effect of the image, highlight the useful information in the image, and suppress or remove useless information. For chest and lung medical images, image enhancement methods include contrast enhancement, sharpening, and histogram equalization. Contrast enhancement can improve the contrast between different tissues in the image and make the lesion area more obvious. Sharpening can enhance the edge information of the image and make the details clearer. Histogram equalization adjusts the brightness distribution of the image to make the overall image look more uniform.

[0079] Image registration spatially aligns images acquired at different times, different viewing angles, or different imaging devices for subsequent comparative analysis, making it easier for doctors to compare images of patients at different time points and under different conditions to assess changes in their condition.

[0080] Image three-dimensional reconstruction is the process of converting two-dimensional image data into a three-dimensional model. It can provide doctors with more intuitive and comprehensive lesion information. Three-dimensional reconstruction can help doctors better understand the lesion's morphology, location, and relationship with surrounding tissues. In order to achieve three-dimensional reconstruction, it is first necessary to extract useful information from the two-dimensional image, and then use this information for three-dimensional modeling and rendering, and finally obtain the desired three-dimensional image.

[0081] Furthermore, the specific steps and methods of the region growing algorithm for intelligent analysis and identification of lesions and segmentation of lesion areas are as follows:

[0082] C1. Select one or more seed points in the medical image, located inside the lesion or lesion area. The selection of seed points is achieved by manual designation. The seed points are manually selected inside the lesion or lesion area through visual inspection. The seed points will serve as the starting point for the algorithm to grow and affect the quality and accuracy of the final segmentation result.

[0083] C2. Determine the metric criteria for pixel similarity, including the difference in pixel grayscale values, color differences, and texture features. One of the most commonly used similarity metrics is the difference in grayscale values ​​between pixels. By setting a threshold, the algorithm can determine whether adjacent pixels are similar enough to be added to the current region. For color images, the distance in color space is considered as a similarity metric. For regions with rich textures, texture features are introduced as a supplement to the similarity metric.

[0084] C3, take the initial seed point as a region and add it to the region set;

[0085] C4. In each iteration, a region is selected from the region set as the current processing object, and the neighboring pixels of the region are traversed. According to the previously defined similarity measurement criteria, it is determined whether these neighboring pixels meet the conditions for joining the current region;

[0086] C5. Repeat the above iterative growth process until all pixels have been visited or no new pixels can be added to the region;

[0087] C6. Output the final set of regions as the image segmentation result. In medical images, these segmented regions usually represent different tissues or lesion sites, providing doctors with intuitive lesion identification information.

[0088] Furthermore, the processed images and analysis results are displayed through a graphical user interface to provide a basis for diagnosis. The graphical user interface provides dynamic interactive functions, including zooming, panning, and rotation, so that doctors can freely adjust the display mode and angle of the image to obtain the best observation effect. This multi-view display method helps doctors to comprehensively and carefully observe the morphology, location and relationship of the lesion with surrounding tissues. After the doctor completes the image analysis and diagnosis, the system should be able to automatically extract relevant data from the patient information database, image processing and analysis results, and fill it into the diagnosis report template, and automatically generate a standardized diagnosis report containing patient information, image description, and diagnosis conclusion.

[0089] Furthermore, the system adopts a modular design, which reduces the direct dependency between modules and the degree of coupling between the various parts of the system. The modules are relatively independent. When the system fails or requires maintenance, the specific module can be checked and repaired without the need for a comprehensive inspection of the entire system, which facilitates maintenance and upgrades.

[0090] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0091] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A chest and lung medical image processing and analysis software system with high transmission efficiency, characterized in that: The image processing and analysis software system includes: high-speed image acquisition module, data compression and encoding module, efficient transmission module, image processing and analysis module and result display and report generation module; The high-speed image acquisition module is used to collect medical image data and ensure the integrity and real-time performance of the data; The data compression and encoding module is used to efficiently compress and encode the collected image data to reduce the data storage space and transmission bandwidth requirements while maintaining image quality; The efficient transmission module is used to realize the safe and fast transmission of compressed and encoded image data, supports a variety of network environments and protocols, and ensures the stability and efficiency of data transmission; The image processing and analysis module is used to process the received image data and perform intelligent analysis to identify lesions and segment the lesion area through the region growing algorithm; The result display and report generation module is used to provide an intuitive and easy-to-use operating interface, support multi-modal and multi-dimensional image display, allow users to make dynamic adjustments and interactive operations, and automatically generate detailed reports containing analysis results to facilitate medical personnel to make accurate diagnoses.

2. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized by: The high-speed image acquisition module is equipped with replaceable slots. Compatible slots can be replaced according to different medical imaging equipment interfaces to support rapid acquisition of multiple image formats, including X-ray, CT, and MRI.

3. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized in that: The steps of data compression and encoding module to efficiently compress and encode image data are as follows: S1, the high-speed image acquisition module reads the original chest and lung medical image data; S2. Design a predictor based on the characteristics of chest and lung medical images, use the predictor to predict each pixel in the image, calculate the error between the actual pixel value and the predicted value, quantize the prediction error, convert the continuous error value into a discrete quantized value, encode the quantized prediction error, and generate a DPCM-encoded data stream; S3, performing frequency statistics on each symbol in the DPCM-encoded data stream to obtain the occurrence probability of each symbol, constructing a Huffman tree according to the frequency of the symbol, and assigning a unique code to each symbol, encoding the DPCM-encoded data stream using the Huffman coding table to generate a Huffman-encoded data stream; S4, organize the Huffman-encoded data stream according to the requirements of the PNG format, including the PNG file header, image header, palette, and image data block part, compress the data of the image data block part using the PNG lossless compression algorithm, write the compressed data into the PNG file, and add the necessary file tail information to complete the generation of the PNG file; S5. Use the PSNR indicator to evaluate the image quality of compressed chest and lung medical images.

4. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized by: The high-speed transmission module adopts high-speed network communication technology and parallel transmission protocol, supports multi-channel concurrent transmission, and dynamically adjusts transmission parameters according to network conditions during data transmission, optimizes transmission paths, and ensures efficient transmission of image data within a limited time.

5. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 3 is characterized in that: In step S2, the steps for designing a predictor based on the characteristics of chest and lung medical images are: A1. When selecting a prediction model, consider linear prediction and nonlinear prediction. Linear prediction is based on the linear combination of adjacent pixels, while nonlinear prediction uses polynomial regression to capture spatial relationships. A2. According to the characteristics of chest and lung medical images, the weight parameters in the predictor are determined through experiments, and the prediction window size is selected to balance the prediction accuracy and computational complexity; A3. Dynamically adjust the parameters of the predictor according to the local characteristics of the current pixel, divide the image into different regions and design different predictors for each region; A4. Use global statistical information of the image to assist prediction; A5. Collect a large amount of chest and lung medical imaging data, including normal and pathological images, evaluate the performance of different predictors through experiments, adjust the design of the predictor according to the experimental results, and perform multiple iterations to optimize the performance.

6. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 3 is characterized in that: The detailed steps of using the PSNR indicator to evaluate image quality in step S5 are as follows: B1. Use the original uncompressed chest and lung medical image as the reference image, and use the compressed chest and lung medical image as the image to be evaluated; B2, MSE is the average value of the square difference between the corresponding pixels of two images, and the calculation formula is: Where I(i,j) and K(i,j) are the pixel values ​​of the original image and the compressed image at position (i,j), respectively, and m and n are the height and width of the image, respectively; B3, PSNR is calculated based on MSE, and its calculation formula is: Among them, MAX is the maximum value of the pixel value in the image; B4. According to the calculated PSNR value, the quality of the compressed chest and lung medical images is evaluated. A PSNR value between 30dB and 50dB indicates good image quality. When the PSNR value is greater than 50dB, the quality of the compressed image is almost the same as the original image. When the PSNR value is lower than 30dB, the image quality is poor.

7. The high-transmission-efficiency chest and lung medical image processing and analysis software system according to claim 1 is characterized by: The image processing and analysis module processes the received image data using methods including image denoising, image enhancement, image registration and image three-dimensional reconstruction.

8. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized in that: The specific steps and methods of the region growing algorithm for intelligent analysis and identification of lesions and segmentation of lesion areas are as follows: C1. Select one or more seed points in the medical image, located inside the lesion or lesion area, and the selection of seed points is achieved by manual designation method; C2, the metric criteria for determining pixel similarity, including the difference in grayscale values, color differences, and texture features of pixels; C3, take the initial seed point as a region and add it to the region set; C4. In each iteration, select a region from the region set and traverse the neighboring pixels of the region; C5. Repeat the above iterative growth process until all pixels have been visited or no new pixels can be added to the region; C6. Output the final set of regions as the image segmentation result. In medical images, these segmented regions usually represent different tissues or lesion sites.

9. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized by: The processed images and analysis results are displayed through a graphical user interface to provide a basis for diagnosis, and a standardized diagnostic report containing patient information, image description, and diagnostic conclusion is automatically generated.

10. The thoracic and pulmonary medical image processing and analysis software system with high transmission efficiency according to claim 1 is characterized by: The system adopts a modular design, and each module is relatively independent, which is easy to maintain and upgrade.

Citation Information

Patent Citations

  • Lossless compression-encoding device

    CN101715132A

  • Improving method based on Huffman lossless compression algorithm

    CN103402090A

  • Digital image compressing, encrypting and encoding combined method

    CN104144343A

  • Human body anatomical structure similarity-based medical image compression algorithm

    CN107146222A

  • Medical image-based focus detection method, model training method and model training device

    CN110414631A

Cited By

  • Image auxiliary analysis system for hospital department based on deep learning

    CN119943291A

  • Lossless compression method and system for medical image data

    CN120088347A

  • Medical image data complete transmission method and system

    CN120220984A

  • A medical image data complete transmission method and system

    CN120220984B

  • High anal fistula postoperative wound information management method and system based on regional big data

    CN120452827A