Wireless handheld super equipment image processing system and method

Abstract

The invention discloses an image processing system for wireless handheld super equipment. The image processing system comprises a wireless image acquisition module which acquires and transmits an ultrasonic image in real time through a wireless transmission technology; the image preprocessing module carries out denoising, enhancement and correction processing, the denoising unit removes noise through wavelet transform or mean filtering, the enhancement unit adopts histogram equalization or gamma correction to improve the contrast ratio, and the correction unit carries out geometric correction to improve the accuracy; the image analysis module extracts key features through an edge detection or region growing algorithm, and identifies lesions or anomalies based on a machine learning or deep learning model; and the result display module displays the analysis result, the diagnosis suggestion and the processing scheme through a user interface. Compared with the prior art, the system has the advantages that efficient real-time image processing is realized through an optimization algorithm and wireless transmission, the analysis accuracy is enhanced, the misdiagnosis rate is reduced, and meanwhile, the system has a flexible and user-friendly operation interface and is suitable for free use in various environments.

Description

Technical Field

[0001] The present application relates to the technical field of image processing and wireless transmission, and in particular to an image processing system and method for a wireless handheld ultrasound device. Background Art

[0002] With the rapid development of wireless communication technology and image processing technology, wireless handheld ultrasound (Handheld Ultrasound) devices have been widely used in medical diagnosis, industrial detection and other fields. Compared with traditional wired ultrasound devices, wireless handheld ultrasound devices have achieved portability and real-time operation through wireless transmission technology, greatly improving user convenience. However, there are still some technical challenges in the actual application of wireless handheld ultrasound devices, which limits the further improvement of their performance.

[0003] Traditional handheld ultrasound devices usually rely on wired connections for data transmission. This method not only increases the complexity of device connection, but also places higher requirements on the operating environment and flexibility. In some special scenarios, wired connections may affect the scope of use and operating efficiency of the device due to cable limitations. Wireless handheld ultrasound devices achieve real-time data transmission through wireless transmission technologies (such as Wi-Fi, Bluetooth, etc.), overcoming the above limitations. However, in actual use, delays and data loss problems during transmission may affect the real-time and integrity of the image, which places higher requirements on image processing.

[0004] In addition, in terms of image processing, wireless handheld ultrasound devices need to achieve efficient image processing and analysis with limited computing resources. However, the commonly used image processing algorithms in the prior art are mostly general algorithms and are not optimized for the specific application scenarios of wireless handheld ultrasound devices. This leads to the following problems:

[0005] Poor image quality: During wireless transmission, image quality may be degraded due to compression or noise introduction, and traditional preprocessing methods are difficult to effectively improve image clarity.

[0006] Insufficient processing speed: Real-time performance is a key requirement for wireless handheld ultrasound devices, but the computational efficiency of general algorithms is low, making it difficult to meet the requirements for high-speed processing in medical and industrial detection scenarios.

[0007] Lack of specificity: Different application scenarios (such as lesion detection in medical diagnosis or defect identification in industrial inspection) have different requirements for image processing. Existing algorithms lack optimization for specific scenarios, resulting in inaccurate processing results.

[0008] Therefore, developing an efficient and accurate image processing method and system for wireless handheld ultrasound devices to solve problems such as image quality, processing speed, and scene adaptability in the existing technology is a research hotspot and development direction in the current technical field. Summary of the invention

[0009] In view of the deficiencies in the prior art, an object of the present invention is to provide an image processing system and method for a wireless handheld ultrasound device to solve the problems raised in the above background technology.

[0010] According to one aspect of the present application, a wireless handheld ultrasound device image processing system includes:

[0011] A wireless image acquisition module, used to acquire ultrasound images through wireless transmission technology and transmit the image data to the processing unit in real time;

[0012] An image preprocessing module is used to perform denoising, enhancement and correction processing on the collected ultrasound image. The image preprocessing module includes:

[0013] De-noising unit, which removes image noise through wavelet transform or mean filtering algorithm;

[0014] Enhancement unit, which uses histogram equalization or gamma correction to improve image contrast;

[0015] a correction unit that performs geometric correction to improve the accuracy and consistency of the image;

[0016] An image analysis module is used to extract and analyze features of the preprocessed image. The image analysis module includes:

[0017] Feature extraction unit, extracting key features of the image through edge detection or region growing algorithm;

[0018] An analysis unit analyzes the extracted features based on a machine learning or deep learning model to identify lesion areas or abnormal phenomena;

[0019] The result display module is used to display the analysis results through the user interface, including feature information, diagnostic suggestions and subsequent treatment plans.

[0020] Preferably, the wireless image acquisition module adopts Wi-Fi, Bluetooth or other wireless communication technologies, and uses an optimized data compression algorithm to ensure that the image quality is maintained while reducing the transmission delay.

[0021] Preferably, the enhancement unit in the image preprocessing module further comprises:

[0022] A local histogram equalization submodule for contrast enhancement of local areas of an image;

[0023] Gamma correction submodule for optimizing image brightness distribution.

[0024] Preferably, the analysis unit in the image analysis module adopts a convolutional neural network (CNN) or a self-attention model, which can optimize specific application scenarios, thereby improving the accuracy and efficiency of image analysis.

[0025] Preferably, the result display module provides an interactive user interface to support users to manually annotate, correct or add explanations to the analysis results to improve the flexibility of diagnosis.

[0026] A method for processing images of a wireless handheld ultrasound device comprises the following steps:

[0027] Step S1, image acquisition: collecting ultrasound images through a wireless handheld ultrasound device, and transmitting the data to an image processing module in real time through a wireless image acquisition module;

[0028] Step S2: Image preprocessing:

[0029] Step S21, using a denoising algorithm (such as wavelet transform or mean filter) to remove noise in the image;

[0030] Step S22, performing contrast enhancement on the image by histogram equalization or gamma correction;

[0031] Step S23, performing geometric correction to ensure the geometric consistency of the image;

[0032] Step S3: feature extraction and analysis:

[0033] Step S31, extracting key features of the image by edge detection or region growing;

[0034] Step S32: Analyze the extracted features using a deep learning model to identify lesion areas or abnormal phenomena in the image;

[0035] Step S4, result output: The analysis results are displayed to the user in an intuitive form through the result display module, including the location of the lesion area, diagnosis suggestions and subsequent treatment plans.

[0036] Preferably, it further comprises:

[0037] Dynamically compress image data transmitted wirelessly to reduce transmission delay;

[0038] Adjust the hyperparameters and training data sets of the deep learning model according to the application scenario to improve the generalization ability of the model.

[0039] Preferably, the analysis results can be presented in the form of charts, heat maps or three-dimensional visualization through a user interface, and support real-time annotation and modification.

[0040] Preferably, the method further includes an automatic adjustment step of the acquisition device, judging the working state of the acquisition device according to the clarity and integrity of the acquired image, and adjusting the parameters of the device through instructions to optimize the acquisition effect.

[0041] The wireless handheld ultrasound device image processing system and method of the present invention have the following advantages:

[0042] 1. High efficiency: Through optimized image processing algorithms and wireless transmission technology, fast image acquisition and processing can be achieved to meet real-time application requirements.

[0043] 2. Accuracy: Image processing methods tailored to specific application scenarios improve the accuracy of image analysis and reduce the misdiagnosis rate.

[0044] 3. Flexibility: Wireless transmission technology makes the operation of the device more flexible, and users can use it freely in different environments.

[0045] 4. User-friendly: The user-friendly interface design makes the operation simple and easy to understand, convenient for medical staff and technicians to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 1 is a system schematic diagram of an image processing system for a wireless handheld ultrasound device according to an embodiment of the present application.

[0047] Figure 2 This is a flowchart of a wireless handheld ultrasound device image processing system according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the contents of the present application easier to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0049] like Figure 1 As shown, a wireless handheld ultrasound device image processing system includes the following modules:

[0050] The wireless image acquisition module uses Wi-Fi, Bluetooth or other wireless communication technologies to collect ultrasound images in real time through ultrasound equipment. The collected images are transmitted through an optimized data compression algorithm to reduce transmission delay and improve transmission efficiency while ensuring image quality.

[0051] The image preprocessing module mainly performs preliminary processing on the collected images to improve the quality and consistency of the images. Specifically, it includes:

[0052] De-noising unit: Use wavelet transform or mean filtering algorithm to denoise the image and remove random noise in the acquisition process.

[0053] Enhancement unit: Enhances the image contrast through histogram equalization or gamma correction to improve the visibility of the image. In addition, the enhancement unit also includes a local histogram equalization submodule, which can accurately enhance the local area of ​​the image.

[0054] Correction unit: performs geometric correction operations to correct distortion in the image and improve the accuracy and consistency of the image.

[0055] The image analysis module is used to perform in-depth analysis on the pre-processed image, extract key features and complete automatic recognition tasks. Specifically, it includes:

[0056] Feature extraction unit: Use edge detection or region growing algorithm to extract key features in the image, such as boundaries, shapes, etc.

[0057] Analysis unit: Analyzes the extracted features through a convolutional neural network (CNN) or a self-attention model to identify lesions or other abnormalities in the image. The analysis unit is optimized for specific application scenarios to improve the efficiency and accuracy of image analysis.

[0058] The result display module displays the analysis results through an interactive user interface, including the identified feature information, diagnostic suggestions, and subsequent treatment plans. The user interface supports real-time annotation, correction, and additional description functions so that users can personalize the analysis results. In addition, the result display module can present the analysis results in the form of charts, heat maps, or 3D visualizations to enhance the user experience.

[0059] Combination Figure 2 , a wireless handheld ultrasound device image processing method, specifically comprising the following steps:

[0060] Step S1, image acquisition: an ultrasonic image is acquired through a wireless handheld ultrasound device, and the image data is transmitted to an image processing module in real time through a wireless image acquisition module.

[0061] Step S2: Image preprocessing:

[0062] Step S21, denoising: using wavelet transform or mean filter algorithm to remove noise in the image and improve the signal-to-noise ratio of the image.

[0063] Step S22, image enhancement: enhancing the image contrast by histogram equalization or gamma correction, and enhancing the details of the local area of ​​the image by using the local histogram equalization submodule.

[0064] Step S23, geometric correction: geometrically correct the image to eliminate the deformation that may occur during the acquisition process and ensure image consistency.

[0065] Step S3: feature extraction and analysis:

[0066] Step S31, feature extraction: extract key features in the image through edge detection or region growing algorithm.

[0067] Step S32, image analysis: Use a deep learning model (such as a convolutional neural network) to analyze the extracted features and automatically identify lesion areas or abnormal phenomena.

[0068] Step S4, result output: The analysis results are displayed to the user in an intuitive form through the result display module, including the location of the lesion area, diagnostic suggestions and subsequent treatment plans. The user interface supports interactive operations, allowing users to mark and modify the results.

[0069] Step S5: Dynamic adjustment and optimization:

[0070] Step S51: For the wirelessly transmitted image data, a dynamic compression algorithm is used to reduce transmission delay and improve transmission efficiency.

[0071] Step S52: Dynamically adjust the hyperparameters and training data set of the deep learning model according to the specific application scenario to improve the generalization ability of the model.

[0072] Step S53: The system monitors the image acquisition quality in real time, determines the working status of the acquisition device, and sends adjustment instructions as needed to optimize the acquisition parameters to improve image clarity and integrity.

[0073] In addition, the wireless handheld ultrasound device image processing system of the present invention can further expand its functions, such as integrating a multimodal data processing module to support joint analysis of ultrasound images with other data sources (such as CT or MRI data) to improve the comprehensiveness and accuracy of diagnosis. In the future, cloud computing and edge computing technologies can be used to achieve more efficient data storage and processing, providing users with more powerful intelligent service support.

[0074] The above embodiments are only used to illustrate the technical solutions of the embodiments of the present application, rather than to limit them. Although the embodiments of the present application are described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents, without departing from the spirit and scope defined by the claims of the present application.

Claims

1. A wireless handheld ultrasound device image processing system, characterized in that: include: A wireless image acquisition module, used to acquire ultrasound images through wireless transmission technology and transmit the image data to the processing unit in real time; An image preprocessing module is used to perform denoising, enhancement and correction processing on the collected ultrasound image. The image preprocessing module includes: De-noising unit, which removes image noise through wavelet transform or mean filtering algorithm; Enhancement unit, which uses histogram equalization or gamma correction to improve image contrast; a correction unit that performs geometric correction to improve the accuracy and consistency of the image; An image analysis module is used to extract and analyze features of the preprocessed image. The image analysis module includes: Feature extraction unit, extracting key features of the image through edge detection or region growing algorithm; An analysis unit analyzes the extracted features based on a machine learning or deep learning model to identify lesion areas or abnormal phenomena; The result display module is used to display the analysis results through the user interface, including feature information, diagnostic suggestions and subsequent treatment plans.

2. The image processing system for a wireless handheld ultrasound device according to claim 1, characterized in that: The wireless image acquisition module uses Wi-Fi, Bluetooth or other wireless communication technologies, and through an optimized data compression algorithm, ensures that the image quality is maintained while reducing the transmission delay.

3. The image processing system for a wireless handheld ultrasound device according to claim 1, characterized in that: The enhancement unit in the image preprocessing module further includes: A local histogram equalization submodule for contrast enhancement of local areas of an image; Gamma correction submodule for optimizing image brightness distribution.

4. The image processing system for a wireless handheld ultrasound device according to claim 1, characterized in that: The analysis unit in the image analysis module adopts a convolutional neural network or a self-attention model, which can optimize specific application scenarios, thereby improving the accuracy and efficiency of image analysis.

5. The image processing system for a wireless handheld ultrasound device according to claim 1, characterized in that: The result display module provides an interactive user interface to support users to manually annotate, modify or add explanations to the analysis results to improve the flexibility of diagnosis.

6. A method for processing images of a wireless handheld ultrasound device, characterized in that: The following steps are involved: Step S1, image acquisition: collecting ultrasound images through a wireless handheld ultrasound device, and transmitting the data to an image processing module in real time through a wireless image acquisition module; Step S2: Image preprocessing: Step S21, using a denoising algorithm to remove noise in the image; Step S22, performing contrast enhancement on the image by histogram equalization or gamma correction; Step S23, performing geometric correction to ensure geometric consistency of the image; Step S3: feature extraction and analysis: Step S31, extracting key features of the image by edge detection or region growing; Step S32: Analyze the extracted features using a deep learning model to identify lesion areas or abnormal phenomena in the image; Step S4, result output: The analysis results are displayed to the user in an intuitive form through the result display module, including the location of the lesion area, diagnosis suggestions and subsequent treatment plans.

7. The method for processing images of a wireless handheld ultrasound device according to claim 6, characterized in that: Further including: Dynamically compress image data transmitted wirelessly to reduce transmission delay; Adjust the hyperparameters and training data sets of the deep learning model according to the application scenario to improve the generalization ability of the model.

8. The method for processing images of a wireless handheld ultrasound device according to claim 6, characterized in that: The analysis results can be presented in the form of charts, heat maps or three-dimensional visualization through a user interface, and support real-time annotation and modification.

9. The method for processing images of a wireless handheld ultrasound device according to claim 6, characterized in that: It further includes an automatic adjustment step for the acquisition device, judging the working state of the acquisition device according to the clarity and integrity of the acquired image, and adjusting the parameters of the device through instructions to optimize the acquisition effect.

Images