Tuberculosis accurate detection system based on ultrasonic intervention

Abstract

The invention belongs to the field of medical treatment, and provides an accurate tuberculosis detection system based on ultrasonic intervention, which comprises an ultrasonic probe used for acquiring an ultrasonic image of a target area; the three-dimensional modeling part is used for constructing a three-dimensional model of a target area based on the ultrasonic image and the spatial position information of the ultrasonic probe; the ultrasonic guiding part is connected with the three-dimensional modeling part and used for calculating an optimal detection path based on the three-dimensional model and the real-time position of the ultrasonic probe and guiding the operator to obtain a second ultrasonic image through the intercostal space; and the detection module is connected with the ultrasonic guide part and is used for accurately detecting tuberculosis based on the second ultrasonic image.

Description

Technical Field

[0001] The present invention belongs to the medical field, and more particularly relates to a precise tuberculosis detection system based on ultrasound intervention. Background Art

[0002] Tuberculosis is a chronic infectious disease caused by Mycobacterium tuberculosis, which mainly affects the lung tissue. Early detection and accurate diagnosis of tuberculosis are crucial for controlling the spread of the disease and improving the treatment effect. Imaging examination is an important means for tuberculosis diagnosis. Among them, chest X-ray (X-ray) and computed tomography (CT) are commonly used imaging tools in clinical practice at present. However, these methods have limitations such as radiation risk, high cost, and strong equipment dependence, and are not suitable for pregnant women, children, and patients who need multiple reexaminations. In contrast, ultrasound imaging has become a non-invasive auxiliary detection means that has attracted much attention in tuberculosis diagnosis in recent years due to its advantages of no radiation, real-time imaging, and portability.

[0003] However, the propagation characteristics of ultrasonic waves in different tissues are mainly affected by acoustic impedance. The acoustic impedance of bone tissue is much higher than that of soft tissue. When ultrasonic waves encounter rib, sternum, and other thoracic bony structures, most of the acoustic energy is reflected or absorbed, and only a very small amount of ultrasonic waves can penetrate through the bone tissue into the deeper lung tissue. This phenomenon results in the formation of an acoustic shadow behind the bone, that is, a black signal-free area appears on the ultrasound image, making it difficult to observe important anatomical structures such as the lung tissue, mediastinal region, and pleura behind the bone, seriously affecting the application of ultrasound in the detection of pulmonary tuberculosis.

[0004] In clinical practice, the ultrasonic probe can be tilted or rotated to make the ultrasonic waves propagate along the intercostal space, avoiding the high acoustic impedance interface of the rib, so as to enter the lung tissue for imaging. Or select a suitable detection area, such as windows in the intercostal space, subxiphoid or supraclavicular fossa, etc., to obtain better pulmonary ultrasound echo signals as much as possible.

[0005] However, the above methods highly depend on the operation experience and techniques of doctors. Different doctors have different masteries of probe angles, incident paths, and parameter adjustments, resulting in the lack of consistency in the quality of ultrasound images and detection results. In addition, there are individual differences in the thoracic anatomical structures of different patients, and the penetrability of ultrasonic waves in different individuals is different, further increasing the difficulty of ultrasonic detection of pulmonary tuberculosis. Therefore, relying solely on the operation experience of doctors to optimize the ultrasonic detection path and angle is difficult to achieve standardized, automated, and highly repeatable ultrasonic detection of tuberculosis in clinical practice. Summary of the Invention

[0006] In order to solve the problems in the prior art, the present invention provides a precise tuberculosis detection system based on ultrasound intervention, including the following modules:

[0007] An ultrasonic probe for acquiring ultrasonic images of a target area; the ultrasonic probe further includes an inertial measurement unit for measuring the spatial position information of the ultrasonic probe;

[0008] A three-dimensional modeling unit for constructing a three-dimensional model of the target area based on the ultrasonic image and the spatial position information of the ultrasonic probe, and the three-dimensional modeling unit includes:

[0009] A data acquisition unit for receiving multi-angle ultrasonic image data collected by the ultrasonic probe and synchronously recording the spatial position information of the ultrasonic probe;

[0010] A point cloud generation unit for calculating the point cloud data of each tissue layer based on the depth information of the ultrasonic image and generating a preliminary three-dimensional point cloud model of the target area through multi-frame image fusion;

[0011] A bone structure recognition unit for identifying the bone boundaries within the target area based on the point cloud model to determine the three-dimensional anatomical structures of the ribs, sternum, and hard tissues;

[0012] A soft tissue modeling unit for constructing a soft tissue model within the target area according to the ultrasonic echo characteristics;

[0013] An ultrasonic guidance unit connected to the three-dimensional modeling unit for calculating an optimal detection path based on the three-dimensional model and the real-time position of the ultrasonic probe, and guiding the operator to obtain a second ultrasonic image through the intercostal space. The ultrasonic guidance unit includes:

[0014] A path planning unit for calculating an optimal ultrasonic detection path based on the three-dimensional model and the anatomical structure of the target area to avoid the bone occlusion area;

[0015] A probe angle optimization unit for calculating a recommended probe tilt angle based on the current position of the ultrasonic probe and the positional relationship of the target area;

[0016] A force feedback unit for monitoring the pressure of the ultrasonic probe during operation and providing tactile feedback to determine that the ultrasonic probe reaches the optimal position and angle;

[0017] A detection module connected to the ultrasonic guidance unit for performing precise tuberculosis detection based on the second ultrasonic image.

[0018] The present invention provides a precise tuberculosis detection system based on ultrasonic intervention, which has the following beneficial effects compared with the prior art:

[0019] In the present invention, through intelligent ultrasonic guidance, optimized probe angle, and real-time force feedback mechanism, ultrasonic waves can effectively avoid the blocked areas of the ribs and sternum, optimize the ultrasonic propagation path, improve the penetration ability of ultrasonic signals and the imaging quality of the lesion area, reduce the detection errors caused by differences in doctors' operation experience, and thus improve the accuracy and consistency of ultrasonic detection of pulmonary tuberculosis. By adopting an automated ultrasonic detection path planning and intelligent probe angle recommendation algorithm, it can dynamically guide doctors to adjust the probe position and angle, reduce the high dependence of ultrasonic detection on doctors' experience, enable non-professional ultrasonic doctors to quickly master the best detection operations, improve the standardization degree of ultrasonic detection, reduce repeated scans at the same time, improve the detection efficiency, and optimize the clinical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0021] Figure 1 It is a system diagram of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, in combination with the drawings and the specific embodiments, a preferred description of the invention will be given.

[0023] This embodiment solves the above problems through the following steps:

[0024] In one embodiment, referring to Figure 1 , the present invention provides a precise tuberculosis detection system based on ultrasonic intervention. This system combines ultrasonic imaging technology, spatial positioning technology, and intelligent guidance algorithms. By real-time collecting ultrasonic data of the target area, constructing a three-dimensional anatomical model, and adopting an optimized ultrasonic detection path and force feedback mechanism, it guides the operator to accurately obtain high-quality ultrasonic images to improve the detection accuracy and diagnostic accuracy of tuberculosis lesions.

[0025] Next, each module of the system will be described in detail.

[0026] An ultrasonic probe is used to obtain ultrasonic images of the target area; the ultrasonic probe further includes an inertial measurement unit, and the inertial measurement unit measures the spatial position information of the ultrasonic probe.

[0027] The ultrasonic probe is used to obtain ultrasonic images of a target area. The ultrasonic probe is a medical ultrasonic device with high-resolution imaging capabilities, including an ultrasonic transducer unit and a signal processing unit. Among them, the ultrasonic transducer unit is used to transmit ultrasonic signals and receive echo signals from the target area, and the signal processing unit is used to perform real-time analysis on the echo signals to generate ultrasonic image data.

[0028] The ultrasonic probe further includes an inertial measurement unit, which is used to measure the spatial position information of the ultrasonic probe. The spatial position information includes the displacement, rotation angle, and movement trajectory of the ultrasonic probe. The inertial measurement unit consists of an accelerometer, a gyroscope, and a magnetometer. Through multi-sensor data fusion technology, it performs high-precision measurement of the motion state of the ultrasonic probe to ensure the accuracy of the position information of the probe during the scanning process.

[0029] By integrating an inertial measurement unit into the ultrasonic probe, this system can accurately record the spatial position information of the probe while performing ultrasonic imaging, enabling the ultrasonic image data to have high spatial traceability, thereby achieving precise matching of multi-angle ultrasonic images and improving the accuracy of 3D modeling. At the same time, the inertial measurement unit can real-time monitor the operating state of the ultrasonic probe, optimize the operator's operation path, reduce imaging errors, improve the stability and repeatability of detection, and provide more efficient image data support for the precise detection of tuberculosis.

[0030] A 3D modeling unit is used to construct a 3D model of the target area based on the ultrasonic image and the spatial position information of the ultrasonic probe.

[0031] The 3D modeling unit is a calculation module for processing ultrasonic data and generating a visual anatomical structure, including a data acquisition unit, a point cloud generation unit, a bone structure recognition unit, and a soft tissue modeling unit, to achieve precise reconstruction of the anatomical structure of the target area.

[0032] The 3D model refers to a three-dimensional visual structure generated based on ultrasonic image data and the spatial position information of the ultrasonic probe. This 3D model includes the tissue boundaries, anatomical structure features, and spatial distribution information of the lesion area of the target area, and can provide complete anatomical information outside the ultrasonic imaging plane, improving the comprehensiveness and accuracy of detection.

[0033] The 3D modeling unit generates a 3D model of the target area by acquiring multi-angle ultrasonic image data, combining the spatial position information of the ultrasonic probe, and using point cloud computing, depth information fusion, and image registration algorithms. The 3D model can truly reflect the anatomical morphology of the target area and be dynamically updated to adapt to real-time changes during the movement of the probe.

[0034] Through the construction of the three-dimensional modeling unit, the system can overcome the limitations of traditional two-dimensional ultrasound imaging, achieve multi-angle and multi-level information fusion, and improve the accuracy of the lesion location. At the same time, the three-dimensional model can be used for the navigation of the ultrasound guidance unit to assist the operator in optimizing the detection path and improving the repeatability and consistency of detection. In addition, this technology can reduce the influence of the operator's experience on the detection results, making ultrasound intervention detection more intelligent, precise, and standardized, and enhancing the ability of early screening and precise diagnosis of tuberculosis.

[0035] The data acquisition unit is used to receive the multi-angle ultrasound image data collected by the ultrasound probe and synchronously record the spatial position information of the ultrasound probe.

[0036] The data acquisition unit is used to receive the multi-angle ultrasound image data collected by the ultrasound probe and synchronously record the spatial position information of the ultrasound probe. Among them, the data acquisition unit is the core module that performs ultrasound image data reception, position information storage, and synchronous processing, including an image signal reception module, a position information storage module, and a data synchronous processing module, which are used to ensure the integrity and spatial consistency of ultrasound data.

[0037] The multi-angle ultrasound image data refers to the ultrasound imaging data collected by the ultrasound probe at different spatial positions and angles. This data reflects the tissue characteristics and lesion information of the target area at different imaging angles and can be used for subsequent three-dimensional reconstruction and lesion analysis.

[0038] The spatial position information refers to the real-time displacement, rotation angle, and trajectory information of the ultrasound probe in the three-dimensional space during the scanning process. This information is obtained by an inertial measurement unit (IMU), an optical tracking system, or a magnetic positioning system and is used to map the real position of the ultrasound image data to ensure the spatial consistency of the imaging data at different scanning angles.

[0039] The data acquisition unit makes the image data and the probe position correspond one by one by receiving the ultrasound image data in real time and synchronously storing the spatial motion information of the probe, and adopts a high-precision time synchronization algorithm to ensure the traceability of the image data.

[0040] The setting of this unit can effectively improve the accuracy and spatial matching degree of ultrasound image data, enabling multi-frame fusion, depth calculation, and three-dimensional reconstruction of the images during the ultrasound detection process, thereby improving the imaging quality of the target area. In addition, the data acquisition unit reduces the image deviation caused by the probe movement, making the lesion location more accurate, providing high-precision and structured image data for subsequent ultrasound guidance and lesion analysis, and enhancing the intelligent and standardized level of tuberculosis detection.

[0041] A point cloud generation unit, which is used to calculate the point cloud data of each tissue layer based on the depth information of the ultrasound image, and generate a preliminary three-dimensional point cloud model of the target area through multi-frame image fusion.

[0042] The point cloud generation unit is used to calculate the point cloud data of each tissue layer based on the depth information of the ultrasound image, and generate a preliminary three-dimensional point cloud model of the target area through multi-frame image fusion. Among them, the point cloud generation unit includes a depth information calculation module, a point cloud data construction module, and a multi-frame fusion module to achieve high-precision three-dimensional modeling of the target area.

[0043] The depth information refers to the time difference, attenuation characteristics, and sound velocity propagation path of the echo signals of each tissue structure in the target area obtained by the ultrasound probe at different scanning angles. This information can be used to calculate the relative depth of the tissue structure in the ultrasound imaging plane to establish the position relationship in the three-dimensional space.

[0044] The point cloud data refers to a spatial data set composed of multiple three-dimensional coordinate points. Among them, each point is determined by the reflection signal intensity and position information of the ultrasound imaging. This point cloud data can reflect the morphological characteristics of the tissue structure and provide a basis for subsequent tissue recognition and model reconstruction.

[0045] The multi-frame image fusion refers to registering, matching, and fusing the ultrasound image data obtained by the ultrasound probe at different angles and different times to enhance the stability of the ultrasound imaging, reduce the noise or artifacts that may exist in a single-frame image, and improve the integrity and accuracy of the three-dimensional point cloud model.

[0046] The point cloud generation unit can establish a three-dimensional point cloud model through the following methods:

[0047] Calculate the depth information of the target tissue using the propagation time of ultrasonic waves and map it to the three-dimensional coordinate space to construct the initial point cloud data.

[0048] Combined with the phase characteristics of ultrasonic waves, by calculating the phase difference of different ultrasonic beams, infer the position of the tissue boundary points to improve the accuracy of the point cloud data.

[0049] Based on the movement trajectory of the ultrasound probe, calculate the propagation path of ultrasonic waves between tissues, and generate point cloud data using the change in echo intensity.

[0050] Through the point cloud generation unit, this system can effectively improve the three-dimensional visualization ability of ultrasound image data, enhance the spatial analysis ability of the lesion area, provide high-precision structural information support for ultrasound intervention detection, and make the screening and diagnosis of tuberculosis more intelligent and accurate.

[0051] The bone structure recognition unit is used to recognize the bone boundaries within the target area based on the point cloud model to determine the three-dimensional anatomical structures of the ribs, sternum, and hard tissues.

[0052] The bone structure recognition unit is used to recognize the bone boundaries within the target area based on the point cloud model to determine the three-dimensional anatomical structures of the ribs, sternum, and hard tissues. Among them, the bone structure recognition unit includes a bone boundary detection module, a bone point cloud extraction module, and a three-dimensional anatomical modeling module, which are used to accurately construct the spatial distribution model of the bones and provide stable anatomical reference information for ultrasonic intervention detection.

[0053] The bone boundary refers to the reflection interface formed due to the high acoustic impedance characteristics of bone tissue in ultrasonic images. This boundary can be used to distinguish bones from soft tissues and serve as a spatial reference for ultrasonic guidance.

[0054] The three-dimensional anatomical structure refers to the spatial model of the bones within the target area reconstructed based on point cloud data, including the spatial arrangement information of the ribs, sternum, and other hard tissues. This structure can be used to optimize the imaging path of the ultrasonic probe and improve the accuracy of intervention detection.

[0055] The bone boundary detection can adopt the ultrasonic echo signal feature analysis method to detect the regions of sudden change in acoustic impedance between tissues to extract the bone contour. Further, it can be combined with gradient-enhanced edge detection algorithms (such as the Sobel operator or Canny operator) to accurately locate the bone boundary and improve the recognition accuracy.

[0056] Hard tissues such as ribs and sternum will block the propagation of ultrasonic waves, resulting in limited imaging in some areas and affecting the integrity of ultrasonic detection. By establishing an accurate bone structure model, the optimal ultrasonic incident angle can be determined, the propagation path of ultrasonic waves can be optimized, and artifact interference can be reduced.

[0057] The bone structure recognition unit combines point cloud data analysis, ultrasonic boundary detection, and three-dimensional modeling algorithms, and can accurately recognize the three-dimensional anatomical structures of the ribs, sternum, and other hard tissues, improve the ultrasonic imaging quality, optimize the ultrasonic guidance path, enhance the accurate detection ability of tuberculosis, and provide key technical support for intelligent ultrasonic navigation.

[0058] The soft tissue modeling unit is used to construct a soft tissue model within the target area according to the ultrasonic echo characteristics.

[0059] The soft tissue modeling unit is used to construct a soft tissue model within the target area according to the ultrasonic echo characteristics. Among them, the soft tissue modeling unit includes an echo feature analysis module, a soft tissue point cloud generation module, and a three-dimensional reconstruction module, which are used to accurately extract the echo information of the soft tissues and reconstruct the soft tissue anatomical structure of the target area to improve the accuracy and visualization effect of ultrasonic detection.

[0060] A three-dimensional representation of the organizational structure within the target area reconstructed from ultrasonic echo data, including morphological information of lung tissue, pleura, lymph nodes, muscle tissue, and other non-bony tissues, can be used for lesion detection, tissue segmentation, and surgical planning. The soft tissue modeling unit analyzes ultrasonic echo features. For example, by using time gain compensation technology, it corrects the attenuation effect of ultrasonic waves at different depths, improving image contrast. Then, it uses the echo time calculation method to calculate the relative depth information of soft tissue layers based on the round-trip time of ultrasonic waves. Finally, the iterative closest point algorithm is used for multi-frame data registration to improve the spatial stability of the soft tissue point cloud.

[0061] During the precise detection of tuberculosis under ultrasonic guidance, an accurate soft tissue model helps doctors optimize the puncture path, improving the safety and precision of interventional surgery. Through intelligent modeling, noise interference is reduced, the clarity of the soft tissue boundary is improved, the lesion area becomes more obvious, and the readability of ultrasonic images is enhanced.

[0062] The ultrasonic guidance unit, connected to the three-dimensional modeling unit, is used to calculate the optimal detection path based on the three-dimensional model and the real-time position of the ultrasonic probe, and guide the operator to obtain a second ultrasonic image through the intercostal space.

[0063] Among them, the ultrasonic guidance unit includes a path planning unit, a probe angle optimization unit, and a force feedback unit, which are used to optimize the ultrasonic imaging process and improve the precision and repeatability of detection.

[0064] The path planning unit is used to calculate the optimal ultrasonic detection path based on the three-dimensional model and the anatomical structure of the target area to avoid the bone occlusion area. Among them, the path planning unit includes an anatomical information analysis module, a path optimization calculation module, and a dynamic adjustment module, which are used to ensure the smooth propagation of ultrasonic signals, improve the quality of ultrasonic imaging, and optimize the operation process of ultrasonic detection.

[0065] The anatomical information analysis module is used to analyze the three-dimensional anatomical structure of the target area, extract key anatomical features, and establish an anatomical data set available for path planning. Further, this module includes:

[0066] The ultrasonic image segmentation unit uses an image segmentation algorithm based on deep learning (such as U-Net or DeepLabV3+) to automatically identify bones, blood vessels, soft tissues, and lesion areas in ultrasonic images. Combining with the adaptive region growing algorithm, it refines tissues with blurred boundaries to improve the segmentation accuracy.

[0067] The bone shielding area recognition unit detects the rib boundaries in ultrasonic images through the Hough transform algorithm and establishes a bone shielding area model. Combining with bone point cloud data, it calculates the position of the intercostal space and determines the best area where ultrasonic waves can penetrate.

[0068] The target tissue modeling unit uses a voxel reconstruction algorithm to convert ultrasonic images into three-dimensional anatomical models. Combining Bayesian inference, it optimizes the prediction of anatomical structures and reduces errors caused by data loss.

[0069] The path optimization calculation module is used to calculate the optimal ultrasonic detection path based on anatomical information, ensure the smooth propagation of ultrasonic signals, and improve the image quality. The following algorithm is used by this module for path optimization:

[0070] The goal of this algorithm is to find a suitable starting point for ultrasonic detection, enabling ultrasonic waves to propagate in a straight line to the target area while avoiding bone occlusion areas, ensuring the imaging quality and effectiveness of ultrasonic detection.

[0071] During the path planning process, the following constraints must be followed:

[0072] The target point is fixed and cannot be changed, that is, the target detection position.

[0073] The detection starting point is adjustable, and the best detection position needs to be found so that ultrasonic signals can propagate in a straight line to the target point.

[0074] The detection path must be a straight line, and ultrasonic waves cannot turn.

[0075] The path cannot pass through the bone area and must propagate within the soft tissue area.

[0076] The model is divided into regular grids, and each grid represents an optional detection starting point.

[0077] Assign characteristics to each grid cell:

[0078] Whether it can be used as the starting point for ultrasonic detection;

[0079] Whether it is a soft tissue area allowing ultrasonic waves to penetrate;

[0080] Whether it belongs to the bone occlusion area where ultrasonic waves are not allowed to pass.

[0081] Select the current ultrasonic probe position as the starting point. If this point does not meet the path requirements, the optimal detection starting point is found through the algorithm.

[0082] According to the positions of the current detection starting point and the target point, calculate the straight-line path between them. Discretize this straight line into multiple discrete points for path feasibility detection in the grid.

[0083] Check all grids on the straight-line path one by one to determine whether they pass through the bone area: If all path points are in the soft tissue area, this detection starting point is available and the search is terminated. If there is a bone area on the path, the current detection starting point is not feasible and the detection starting point needs to be adjusted.

[0084] During adjustment, search for a new detection starting point within the candidate area of the detection starting point. Taking the target point as a reference, expand outward to search for possible detection starting points. The search range is set by the doctor and usually includes a certain range in front of the target point to cover all possible ultrasonic incident angles.

[0085] Calculate the straight-line path from the candidate detection starting point to the target point and check whether it completely avoids the bone area. If this path is feasible, set this detection starting point as the final detection starting point and terminate the search. If the path is still not feasible, continue to search for other candidate points until the best detection starting point is found.

[0086] Prioritize the feasible detection starting point closest to the target point to ensure the shortest ultrasonic detection path and improve the signal quality. If there are multiple feasible detection starting points, select the detection starting point with the optimal ultrasonic angle, that is, the point where the ultrasonic incident angle is close to perpendicular to the lesion area, to obtain the best echo signal.

[0087] The dynamic adjustment module is used to adjust the path according to real-time feedback during the detection process to improve the detection accuracy. This module includes:

[0088] The real-time feedback adjustment unit combines ultrasonic echo quality analysis to monitor the intensity and distribution of ultrasonic signals and judge the current imaging quality. Further, fuzzy logic control can also be used to adjust the probe position according to the signal quality and optimize the path.

[0089] The target area tracking unit uses an optical flow tracking algorithm to monitor the movement of the target tissue in the ultrasonic image to ensure that the lesion does not shift out of the field of view during the scanning process. Further, particle filtering can also be combined to improve the tracking stability and reduce errors.

[0090] The intelligent path adaptive unit optimizes through a neural network to dynamically adjust the path during the scanning process to improve adaptability. Further, a reinforcement learning algorithm can also be combined to continuously optimize the probe path and improve the long-term detection effect.

[0091] Through path optimization, the ultrasonic probe can avoid the rib area, minimize the bone shielding effect to the greatest extent, improve the imaging ability of deep tissues, ensure that the ultrasonic signal evenly covers the target area, and improve the accuracy of lesion recognition.

[0092] The probe angle optimization unit is used to calculate the recommended probe tilt angle based on the position relationship between the current position of the ultrasonic probe and the target area.

[0093] The probe angle optimization unit is used to comprehensively analyze the ultrasonic wave propagation path, tissue acoustic characteristics, and imaging requirements, calculate the best probe angle, and provide dynamic adjustment suggestions to improve the detection accuracy and operation consistency.

[0094] When ultrasonic waves propagate between different tissues, they are affected by reflection, refraction, scattering, and absorption. When the incident angle of the ultrasonic waves is different, the intensity and penetration depth of the tissue echoes will also change. A better probe angle can effectively reduce the loss of ultrasonic signals and improve the imaging contrast.

[0095] According to the depth of the target area and the current position of the ultrasonic probe, calculate the optimal incident angle of the ultrasonic waves to maximize the signal penetration rate and reduce the reflection interference on the tissue interface. Use an ultrasonic acoustic model to analyze the propagation path of the ultrasonic waves between different tissues, and combine the oblique incident wave propagation theory to determine the optimal detection angle.

[0096] Calculate the normal direction from the ultrasonic probe to the target area, and adjust the probe angle based on the law of acoustic wave incidence to make the incident angle as close as possible to perpendicular to the tissue surface of the lesion area, so as to reduce the reflection loss of the ultrasonic signal.

[0097] A force feedback unit is used to monitor the pressure, position, and angle of the ultrasonic probe during operation and provide tactile feedback to determine that the ultrasonic probe reaches the optimal position and angle.

[0098] The force feedback unit includes a pressure sensing module, a position detection module, an angle calculation module, a feedback control module, and a real-time adjustment module. Each module works together to ensure that the ultrasonic probe is in an optimal operating state and improve the stability and accuracy of ultrasonic imaging.

[0099] The pressure sensing module is arranged at the bottom of the ultrasonic probe and uses a piezoresistive sensor, a strain gauge sensor, or a capacitive sensor to monitor the pressure of the probe in contact with the skin in real time and transmit the pressure data to the feedback control module to prevent tissue deformation caused by excessive pressure or ultrasonic signal attenuation caused by insufficient pressure. The position detection module is based on an inertial measurement unit (IMU), a magnetic positioning system, or an optical tracking system to obtain the spatial coordinates of the ultrasonic probe in real time, and combine the preset position of the target area to calculate the relative position deviation between the probe and the target area to ensure that the probe is always on the best detection path. The angle calculation module combines a gyroscope, an accelerometer, and a magnetometer to measure the tilt angle of the ultrasonic probe and combines the anatomical features of the target area to calculate the optimal incident angle of the ultrasonic waves to reduce the reflection loss and improve the quality of the echo signal.

[0100] The feedback control module receives pressure, position, and angle data and analyzes the operating state of the probe. When the probe pressure exceeds the preset range, the position deviates from the target area, or the angle does not reach the optimal incident angle, the feedback control module provides adjustment suggestions to the operator through haptic feedback. The haptic feedback can be provided by a vibration motor built into the probe handle, and the operator can perceive the probe adjustment requirements through changes in the vibration intensity during the detection process. The real-time adjustment module dynamically optimizes the operating strategy of the probe based on the instructions of the feedback control module, enabling the probe to automatically adapt to the individual differences of different patients during the detection process and improving the stability and consistency of the detection.

[0101] The detection module is connected to the ultrasound guiding unit and is used for accurately detecting tuberculosis based on the second ultrasound image.

[0102] The detection module includes an ultrasound image preprocessing unit, a feature extraction unit, a lesion recognition unit, and a classification and diagnosis unit to analyze and process the ultrasound image data of the target area and automatically identify tuberculosis-related lesions, improving the accuracy and reliability of the detection.

[0103] The ultrasound image preprocessing unit is used to receive the second ultrasound image collected by the ultrasound guiding unit and perform noise removal, contrast enhancement, and edge optimization on the image to ensure that the image quality reaches the best analysis conditions. This unit uses an adaptive filtering algorithm to remove high-frequency noise in the ultrasound image, combines histogram equalization to improve the visualization of the lesion area, and extracts possible lesion areas through an image segmentation algorithm to reduce background interference and improve the subsequent detection accuracy.

[0104] The feature extraction unit extracts tuberculosis-related image features based on the texture, morphology, and echo characteristics of the ultrasound image. This unit uses methods such as gray-level co-occurrence matrix analysis (GLCM), local binary pattern (LBP), and wavelet transform to perform multi-scale feature extraction on the lesion area in the ultrasound image and combines a deep learning feature extraction network to further enhance the discrimination ability between the lesion area and normal tissues.

[0105] Based on the feature extraction results, the lesion recognition unit uses an improved U-Net deep learning network to perform semantic segmentation on the target area, accurately delineate the tuberculosis lesion area, and combines a classification model based on the ultrasound echo intensity to determine the scope, position, and type of the lesion. This unit also combines the fusion of multi-frame ultrasound images to perform time series analysis on the ultrasound images of the target area to improve the stability and accuracy of lesion detection.

[0106] Based on the lesion recognition results, the classification and diagnosis unit uses machine learning algorithms such as support vector machine (SVM), random forest (RF), or deep neural network (DNN) to classify the lesion area, and combines clinical tuberculosis cases in the image database to evaluate the malignancy probability, development trend, and pathological characteristics of the lesion. This unit can also combine with an expert system or a telemedicine platform to provide automated tuberculosis diagnosis assistance suggestions and improve the diagnosis efficiency.

[0107] In summary, through ultrasonic image preprocessing, feature extraction, lesion recognition, and intelligent classification, the detection module can accurately analyze the second ultrasonic image, realize the automatic detection and classification of tuberculosis lesion areas, improve the intelligent level of detection, reduce human errors, and provide efficient and stable technical support for clinical diagnosis.

[0108] For the module structures not specifically defined in the present invention, the content recorded in the prior art shall prevail. The prior art mentioned in the foregoing background art part and specific embodiment part of the present invention can be used as a part of the present invention to understand the meaning of some technical features or parameters.

Claims

1. A precise tuberculosis detection system based on ultrasound intervention, characterized in that, The system includes: An ultrasound probe for acquiring ultrasound images of a target area; the ultrasound probe further includes an inertial measurement unit that measures the spatial position information of the ultrasound probe. A three-dimensional modeling unit for constructing a three-dimensional model of the target area based on the ultrasound images and the spatial position information of the ultrasound probe. The three-dimensional modeling unit includes: A data acquisition unit for receiving multi-angle ultrasound image data collected by the ultrasound probe and synchronously recording the spatial position information of the ultrasound probe. A point cloud generation unit for calculating point cloud data of each tissue layer based on the depth information of the ultrasound images and generating a preliminary three-dimensional point cloud model of the target area through multi-frame image fusion. A bone structure recognition unit for identifying the bone boundaries within the target area based on the point cloud model to determine the three-dimensional anatomical structures of the ribs, sternum, and hard tissues. A soft tissue modeling unit for constructing a soft tissue model within the target area according to the ultrasound echo characteristics. An ultrasound guidance unit connected to the three-dimensional modeling unit for calculating an optimal detection path based on the three-dimensional model and the real-time position of the ultrasound probe and guiding the operator to obtain a second ultrasound image through the intercostal space. The ultrasound guidance unit includes: A path planning unit for calculating an optimal ultrasound detection path based on the three-dimensional model and the anatomical structure of the target area to avoid the bone occlusion area. A probe angle optimization unit for calculating a recommended probe tilt angle based on the current position of the ultrasound probe and the position relationship of the target area. A force feedback unit for monitoring the pressure of the ultrasound probe during operation and providing tactile feedback to determine that the ultrasound probe reaches the optimal position and angle. A detection module connected to the ultrasound guidance unit for performing precise tuberculosis detection based on the second ultrasound image.

2. The tuberculosis precise detection system based on ultrasonic intervention according to claim 1, wherein The point cloud generation unit establishes a three-dimensional point cloud model by the following method: Calculating the depth information of the target tissue using the propagation time of ultrasonic waves and mapping it to a three-dimensional coordinate space to construct initial point cloud data. Combining the phase characteristics of ultrasonic waves, calculating the phase differences of different ultrasonic beams to infer the positions of tissue boundary points to improve the accuracy of the point cloud data. Calculating the propagation path of ultrasonic waves between tissues based on the movement trajectory of the ultrasound probe and generating point cloud data using the change in echo intensity.

3. The tuberculosis precise detection system based on ultrasound intervention according to claim 1, characterized in that, The bone structure recognition unit uses the ultrasonic echo signal feature analysis method to detect the regions of sudden change in acoustic impedance between tissues to extract the bone contour.

4. The tuberculosis precise detection system based on ultrasound intervention according to claim 1, characterized in that, The soft tissue modeling unit uses time gain compensation technology to correct the attenuation effect of ultrasonic waves at different depths to improve the image contrast; then uses the echo time calculation method to calculate the relative depth information of the soft tissue layer based on the round-trip time of ultrasonic waves; finally, uses the iterative closest point algorithm for multi-frame data registration.

5. The tuberculosis precise detection system based on ultrasonic intervention according to claim 1, wherein The path planning unit includes an anatomical information analysis module, a path optimization calculation module, and a dynamic adjustment module.

6. The tuberculosis precise detection system based on ultrasonic intervention according to claim 5, wherein The anatomical information analysis module includes: An ultrasound image segmentation unit that uses an image segmentation algorithm based on deep learning to automatically identify the bones, blood vessels, soft tissues, and lesion regions in the ultrasound images. The bone shielding area recognition unit detects the rib boundaries in the ultrasonic image through the Hough transform algorithm and establishes a bone shielding area model; The target tissue modeling unit uses the voxel reconstruction algorithm to convert the ultrasonic image into a three-dimensional anatomical model.

7. The tuberculosis precise detection system based on ultrasonic intervention according to claim 6, characterized in that, The path optimization calculation module uses the following algorithm for path optimization: Divide the model into regular grids, and each grid represents an optional detection starting point; Assign characteristics to each grid cell: whether it can be used as an ultrasonic detection starting point, whether it is a soft tissue area, and whether it belongs to the bone occlusion area; Select the current ultrasonic probe position as the starting point. If the starting point does not meet the path requirements, find the optimal detection starting point through the algorithm; Calculate the straight-line path between the current detection starting point and the target point according to their positions; Check all the grids on the straight-line path one by one to determine whether the bone area is passed through: if all the path points are in the soft tissue area, the detection starting point is available and the search is terminated; If there is a bone area on the path, the current detection starting point is not feasible and the detection starting point needs to be adjusted; During adjustment, search for a new detection starting point within the candidate area of the detection starting point, expand outward with the target point as the reference, and search for possible detection starting points; Calculate the straight-line path from the candidate detection starting point to the target point, check whether the bone area is completely avoided. If the path is feasible, set the detection starting point as the final detection starting point and terminate the search. If the path is still not feasible, continue to search for other candidate points until the best detection starting point is found.

8. The tuberculosis precise detection system based on ultrasonic intervention according to claim 7, characterized in that, The path optimization includes: Prioritize selecting the feasible detection starting point closest to the target point to ensure the shortest ultrasonic detection path; If there are multiple feasible detection starting points, select the detection starting point with the optimal ultrasonic angle, that is, the point where the ultrasonic incident angle is close to perpendicular to the lesion area, to obtain the best echo signal.

9. The tuberculosis precise detection system based on ultrasound intervention according to claim 1, characterized in that, The force feedback unit includes a pressure sensing module, a position detection module, an angle calculation module, a feedback control module, and a real-time adjustment module.

10. The tuberculosis precise detection system based on ultrasonic intervention according to claim 1, characterized in that, The detection module includes an ultrasonic image preprocessing unit, a feature extraction unit, a lesion recognition unit, and a classification diagnosis unit.

Images