Coprocessing system for ultrasonic and biomarker detection
By designing a collaborative processing system for ultrasound and biomarker detection, and using ultrasound imaging automatic analysis and test result marking, the problem of difficulty in diagnosing local health conditions in the prior art is solved, and the efficiency of local sclerosis diagnosis of liver is improved.
Patent Information
- Application Number
- CN202411079960.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-15
AI Technical Summary
In the prior art, ultrasound examination and biomarker examination are performed separately, making it difficult to achieve effective diagnosis of local health conditions.
Design a collaborative processing system for ultrasound and biomarker detection, including ultrasound positioning module, sampling and assay module and analysis module. Through automatic analysis of ultrasound images and labeling of test results, doctors are guided to conduct targeted sampling and diagnosis.
It realizes automatic analysis and diagnosis of local liver sclerosis, improves diagnostic efficiency, and provides doctors with an effective diagnostic basis.
Smart Images

Figure CN118948333A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical image processing, and in particular to a collaborative processing system for ultrasound and biomarker detection. Background Art
[0002] Ultrasound scanning, or medical ultrasound examination, is a medical imaging diagnostic technology based on ultrasound. This technology can visualize the patient's muscle tissue and internal organs, including size, structure and pathological lesions, outside the patient's body based on ultrasound, to assist doctors in making effective diagnosis of the patient's disease. Ultrasound scanning equipment refers to medical instruments that apply the above-mentioned ultrasound scanning technology, which uses ultrasound to image the various tissue parts of the patient to assist medical diagnosis. In order to achieve a better diagnosis effect on the disease, it is usually necessary to compile a corresponding ultrasound scanning diagnosis process and perform the scanning process according to a specific process. For example, for thyroid scanning, it is usually necessary to design the corresponding scanning direction, sequence, and judgment branches, such as how to deal with the nodule site when scanning. Biomarkers refer to biochemical indicators that can mark changes or possible changes in the structure or function of systems, organs, tissues, cells and subcellular structures, and have a very wide range of uses. Biomarkers can be used to diagnose diseases, determine disease stages, or evaluate the safety and effectiveness of new drugs or new therapies in target populations.
[0003] In the prior art, there are diagnostic processes that use ultrasound and biomarker examinations. For example, Chinese patent CN202010903937.5 provides an ultrasonic examination method that can examine the subject even if, in addition to the ultrasonic waves propagated from the subject, ultrasonic waves that directly arrive through the medium outside the subject are received. An ultrasonic examination method for examining a subject, wherein an ultrasonic transmitting element and an ultrasonic receiving element are arranged opposite to each other, an ultrasonic wave is transmitted from the ultrasonic transmitting element, and the transmitted ultrasonic wave is received by the ultrasonic receiving element via the subject, and the received ultrasonic wave is temporally divided into a first ultrasonic signal, which is a transmission wave of the subject, and a second ultrasonic signal caused by a diffraction wave propagating in the air, and the subject is examined based on the first ultrasonic signal.
[0004] For another example, Chinese patent CN201180027158.2 provides biomarkers and determination methods for predicting the therapeutic effect of chemoradiotherapy on cancer and the prognosis of cancer patients. By measuring the concentrations of soluble interleukin-6 receptor, MIP-1β and activated plasminogen activator inhibitor in the blood collected from a vertebrate suffering from cancer before chemoradiotherapy, the chemoradiotherapy therapeutic effect on cancer of the individual can be predicted, and by measuring the concentration of soluble interleukin-6 receptor, the prognosis of the vertebrate can be determined.
[0005] However, in actual implementation, the inventors found that the above scheme usually involves separate ultrasound examinations and tests, which are then summarized by doctors to diagnose the patient's overall health status, making it difficult to diagnose local health conditions. Summary of the invention
[0006] In view of the above problems existing in the prior art, a collaborative processing system for ultrasound and biomarker detection is now provided.
[0007] The specific technical solutions are as follows:
[0008] A collaborative processing system for ultrasound and biomarker detection, comprising:
[0009] An ultrasound positioning module, which collects ultrasound images of the patient and determines a location to be sampled according to the ultrasound images;
[0010] A sampling and testing module, the sampling and testing module is connected to the ultrasonic positioning module, and the sampling and testing module takes samples according to the part to be sampled and tests to obtain test results;
[0011] An analysis module, wherein the analysis module is connected to the ultrasound positioning module and the sampling and testing module respectively, and the analysis module marks the ultrasound image according to the test result.
[0012] On the other hand, the ultrasound positioning module includes:
[0013] A scanning module, wherein the scanning module controls the ultrasound probe to collect an echo sequence from the patient and to image the patient to obtain the ultrasound image;
[0014] A segmentation module, the segmentation module is connected to the ultrasound module, and the segmentation module segments the liver fibrosis tissue from the ultrasound image according to the grayscale threshold;
[0015] A pre-labeling module is connected to the segmentation module, and the pre-labeling module predicts a nodule portion of the liver fibrous tissue as the portion to be sampled.
[0016] On the other hand, the ultrasonic positioning module further includes:
[0017] A background echo measurement module, the background echo measurement module is connected to the scanning module, and the background echo measurement module measures and obtains background echo parameters during the acquisition process;
[0018] An adaptive scanning module, wherein the adaptive scanning module is connected to the background echo measurement module and the scanning module, and the adaptive scanning module adjusts the ultrasonic scanning parameters of the scanning module according to the background echo parameters to separate the nodule area and the background image.
[0019] On the other hand, the pre-marking module includes:
[0020] A connected domain detection module, wherein the connected domain detection module performs connected domain detection on the separated liver fibrous tissue to separate and obtain a plurality of connected domains;
[0021] A classification module, the classification module is connected to the connected domain detection module, the classification module performs edge detection on the connected domain to classify it into a circular connected domain and a branch-shaped connected domain, and marks the circular connected domain as the part to be sampled;
[0022] A width measurement module, the width measurement module is connected to the classification module, the width measurement module constructs width detection vectors for multiple external endpoints of the branch-shaped communication domain respectively, and moves the width detection vectors along the branch-shaped communication domain;
[0023] When the length of the width detection vector changes suddenly, the width measurement module marks the corresponding position as the part to be sampled.
[0024] On the other hand, the sampling and testing module comprises:
[0025] A sequence positioning module, wherein the sequence positioning module obtains the part to be sampled and determines a corresponding echo sequence segment according to the position of the part to be sampled in the ultrasound image;
[0026] A position information extraction module, wherein the position information extraction module is connected to the sequence positioning module, and the position information extraction module extracts the position information of the ultrasound probe according to the echo sequence segment to obtain the corresponding probe position and output it.
[0027] On the other hand, the sampling and testing module also includes:
[0028] A projection module is connected to the position information extraction module and an external laser projector, and the projection module controls the laser projector to generate laser projection according to the probe position.
[0029] On the other hand, the analysis module comprises:
[0030] A point screening module, wherein the point screening module screens the lesion site from the site to be sampled according to the test result;
[0031] A marking module, wherein the marking module is connected to the point screening module, and the marking module marks the lesion site in the ultrasound image.
[0032] On the other hand, the analysis module further includes:
[0033] A fitting module is used to fit the lesion site according to the test result, and the labeling module labels the lesion site output by the fitting module.
[0034] The above technical solution has the following advantages or beneficial effects:
[0035] In order to solve the problem that ultrasound examination and biomarker examination in the prior art are performed separately and cannot determine the local health status, in this solution, the above-mentioned system is designed for liver examination, which can automatically analyze ultrasound images and guide doctors to conduct targeted sampling and testing, thereby comprehensively annotating ultrasound images, which can provide effective basis for doctors to diagnose local liver sclerosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The embodiments of the present invention will be described more fully with reference to the attached drawings, which are provided for illustration and description only and are not intended to limit the scope of the present invention.
[0037] Figure 1 It is an overall schematic diagram of an embodiment of the present invention;
[0038] Figure 2 This is a schematic diagram of an ultrasonic positioning module in an embodiment of the present invention;
[0039] Figure 3 Schematic diagram of a background echo measurement module in an embodiment of the present invention;
[0040] Figure 4 This is a schematic diagram of a pre-marking module in an embodiment of the present invention;
[0041] Figure 5 This is a schematic diagram of a sampling and testing module in an embodiment of the present invention;
[0042] Figure 6 This is a schematic diagram of a projection module in an embodiment of the present invention;
[0043] Figure 7 This is a schematic diagram of an analysis module in an embodiment of the present invention;
[0044] Figure 8Schematic diagram of a fitting module in an embodiment of the present invention. DETAILED DESCRIPTION
[0045] 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.
[0046] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.
[0047] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.
[0048] The present invention comprises:
[0049] A collaborative processing system for ultrasound and biomarker detection, such as Figure 1 As shown, including:
[0050] Ultrasound positioning module 1, which collects ultrasound images of the patient and determines the part to be sampled according to the ultrasound images;
[0051] The sampling and testing module 2 is connected to the ultrasonic positioning module 1, and the sampling and testing module 2 takes samples according to the part to be sampled and tests to obtain the test results;
[0052] The analysis module 3 is connected to the ultrasound positioning module 1 and the sampling and testing module 2 respectively, and the analysis module 3 marks the ultrasound image according to the test results.
[0053] Specifically, in response to the problem that ultrasound examination and biomarker examination in the prior art are performed separately and cannot determine the local health status, in this solution, the above-mentioned system is designed for liver examination, which can automatically analyze ultrasound images and guide doctors to conduct targeted sampling and testing, thereby comprehensively annotating ultrasound images, which can provide effective basis for doctors to diagnose local liver sclerosis.
[0054] During the implementation process, the above-mentioned collaborative processing system is mainly configured as a software embodiment in a specific computer device for processing ultrasound images and test data. Ultrasound images are mainly obtained by scanning the liver, and the ultrasound positioning module 1 is used to identify and mark through a specific algorithm. In terms of biomarkers, the process of sampling and testing AFP (alpha-fetoprotein) based on trace blood is mainly selected, which can provide a diagnostic basis for liver cirrhosis. Pre-identification through ultrasound images can achieve faster selection of sampling sites. The sampling and testing module 2 guides doctors to take samples according to the site to be sampled and connects to external testing equipment to obtain test results. According to the test results, the analysis module 3 can determine the site where the lesion may exist, mark it on the ultrasound image, and provide it to the doctor, so that the doctor can obtain the ultrasound image of the suspected nodule and the corresponding test parameters, thereby improving the diagnostic efficiency.
[0055] In one embodiment, Figure 2 As shown, the ultrasonic positioning module 1 includes:
[0056] A scanning module 11, the scanning module 11 controls the ultrasound probe to collect echo sequences from the patient and to image and obtain ultrasound images;
[0057] The segmentation module 12 is connected to the scanning module 11, and the segmentation module 12 segments the liver fibrosis tissue from the ultrasound image according to the grayscale threshold;
[0058] The pre-labeling module 13 is connected to the segmentation module 12. The pre-labeling module 13 predicts the nodule part of the liver fibrous tissue and uses it as the part to be sampled.
[0059] Specifically, in order to achieve a better determination effect on the parts that need to be tested and sampled, in this embodiment, the scanning module 11 is first used to control the ultrasound probe to collect echo sequences from the patient and to image an ultrasound image. Since different tissues have different intensities of reflected echoes in ultrasound images, the grayscale value corresponding to the reflection intensity of liver fibrosis tissue after liver cirrhosis under specific ultrasound parameters can be determined through preliminary experimental measurements.
[0060] A grayscale threshold is designed according to the grayscale value, and the segmentation module 12 segments the liver fibrous tissue from the ultrasound image according to the grayscale threshold. Finally, the pre-labeling module 13 is used to identify the nodule part in the liver fibrous tissue, so as to predict the part corresponding to the nodule as the part to be sampled.
[0061] In one embodiment, Figure 3 As shown, the ultrasonic positioning module 1 also includes:
[0062] A background echo measurement module 14, the background echo measurement module 14 is connected to the scanning module 11, and the background echo measurement module 14 measures and obtains background echo parameters during the acquisition process;
[0063] The adaptive scanning module 15 is connected to the background echo measurement module 14 and the scanning module 11. The adaptive scanning module 15 adjusts the ultrasonic scanning parameters of the scanning module 11 according to the background echo parameters to separate the nodule area and the background image.
[0064] Specifically, in view of the problem that the imaging effect of fixed ultrasound scanning parameters in the prior art is poor and difficult to identify, in this embodiment, for the liver fibrosis tissue part to be scanned, when the scanning module 11 starts scanning, that is, when the ultrasound probe just contacts the patient's body surface and mainly points to other background tissues, the background echo measurement module 14 measures the echo sequence of this part to obtain the background echo parameters.
[0065] Then, the adaptive scanning module 15 adjusts the ultrasonic scanning parameters of the scanning module 11 according to the echo intensity of irrelevant tissue on the background, thereby highlighting the brightness of the liver fibrosis tissue area in the image, making it easier to separate the nodule area from the background image.
[0066] In one embodiment, Figure 4 As shown, the pre-marking module 13 includes:
[0067] A connected domain detection module 131, the connected domain detection module 131 performs connected domain detection on the separated liver fibrosis tissue to separate and obtain a plurality of connected domains;
[0068] The classification module 132 is connected to the connected domain detection module 131. The classification module 132 performs edge detection on the connected domains to classify them into circular connected domains and branch-shaped connected domains, and marks the circular connected domains as the parts to be sampled.
[0069] A width measurement module 133, the width measurement module 133 is connected to the classification module 132, and the width measurement module 133 constructs width detection vectors for multiple external endpoints of the branch-shaped communication domain respectively, and moves the width detection vectors along the branch-shaped communication domain;
[0070] When the length of the width detection vector changes suddenly, the width measurement module 133 marks the corresponding position as a portion to be sampled.
[0071] Specifically, in order to achieve better labeling efficiency, in this embodiment, after the liver fibrosis tissue is obtained by threshold separation, the separated liver fibrosis tissue is firstly detected by the connected domain detection module 131 to separate and obtain multiple connected domains. The multiple connected domains mainly correspond to the image areas with more significant fibrosis on the full-frame ultrasound image, and may correspond to the main areas of liver fibrosis or local liver cirrhosis areas in anatomy.
[0072] Then, the classification module 132 performs edge detection on the connected domains, extracts the edge portion of each connected domain, traverses the curvature of each point on the edge according to the edge portion, obtains a curvature sequence, and then derives the curvature sequence, and determines whether the connected domain is a circular connected domain with continuously changing curvature or a branch-shaped connected domain with sudden changes according to the change of its derivative. Among them, the circular connected domain usually corresponds to a local liver cirrhosis area and can be directly marked as the part to be sampled.
[0073] Subsequently, for the branch-shaped connected domain, the width measurement module 133 determines the multiple external endpoints of the branch-shaped connected domain according to the derivative change of the curvature sequence, and then segments the edge of the branch-shaped connected domain according to the external endpoints. Each segment constructs a set of sampling points extending from the external endpoints to both sides, which are connected on the ultrasound image to form a width detection vector. Subsequently, the sampling points are moved to both sides according to the same length, and the modulus of the width detection vector is continuously calculated to form a modulus length sequence. Normally, the length of the modulus length sequence will gradually increase to a fixed value. When the length mutates, the corresponding mutation area is the nodule on the branch, and the front and rear coordinates of the sampling point are obtained and intercepted as the sampling site.
[0074] For example, the modulus length sequence includes multiple modulus length values, each modulus length value has a corresponding width detection vector, and each width detection vector has a first coordinate and a last coordinate corresponding to a sampling point.
[0075] First, the module length values of the module length sequence are compared to extract the interval with large module length changes, and the module length values of this part usually have the characteristics of increasing-decreasing. Then, the width detection vector is searched for this interval to obtain the front-end width detection vector and the rear-end width detection vector. Finally, the first coordinate and the tail coordinate of the front-end width detection vector and the rear-end width detection vector are connected to obtain a rectangular sampling area as the output of the sampling part.
[0076] In one embodiment, Figure 5 As shown, the sampling and testing module 2 includes:
[0077] A sequence positioning module 21, the sequence positioning module 21 obtains the part to be sampled, and determines the corresponding echo sequence segment according to the position of the part to be sampled in the ultrasound image;
[0078] The position information extraction module 22 is connected to the sequence positioning module 21. The position information extraction module 22 extracts the position information of the ultrasound probe according to the echo sequence segment to obtain the corresponding probe position and output it.
[0079] Specifically, to achieve a better sampling effect, in this embodiment, after the part to be sampled is determined, the sequence positioning module 21 obtains the part to be sampled, and determines to reconstruct the corresponding echo sequence segment of the part according to the position of the part to be sampled in the ultrasound image.
[0080] Then, the position information extraction module 22 extracts the sequence of the ultrasound probe's posture information according to the time points of the echo sequence segments during the overall scanning process, and determines the corresponding posture information. Since the scanning start point, end point and orientation of the ultrasound probe can be determined, on this basis, combined with the posture information, the azimuth and distance information of each part to be sampled relative to the actual patient's body surface can be determined and output as the probe position, thereby indicating the sampling part.
[0081] In one embodiment, Figure 6 As shown, the sampling and testing module 2 also includes:
[0082] The projection module 23 is connected to the position information extraction module 22 and an external laser projector. The projection module 23 controls the laser projector to generate laser projection according to the probe position.
[0083] Specifically, to achieve a better indication effect, in this embodiment, after the probe position is calculated, the laser projector is controlled to generate laser projection according to the scanning start and end points of the ultrasound probe marked on the patient's body surface to facilitate puncture sampling.
[0084] In one embodiment, Figure 7 As shown, the analysis module 3 includes:
[0085] A point screening module 31, which screens the lesion site from the site to be sampled according to the test results;
[0086] The marking module 32 is connected to the point selection module 31 , and the marking module 32 marks the lesion site in the ultrasound image.
[0087] Specifically, in order to achieve better analysis results, in this embodiment, after obtaining the test results, the point screening module 31 is used to screen the lesion sites where liver fibrosis and cirrhosis actually exist from the sampled sites according to the test results, and then the marking module 32 marks the lesion sites in the ultrasound image to facilitate subsequent doctor reading and diagnosis.
[0088] In one embodiment, Figure 8 As shown, the analysis module 3 also includes:
[0089] The fitting module 33 obtains the lesion site by fitting according to the test results, and the marking module 32 marks the lesion site output by the fitting module.
[0090] Specifically, since the present scheme selects a scheme of micro-blood sampling and alpha-fetoprotein detection through multiple sampling points for testing, after obtaining the test results, the fitting module 33 can be used to fit the distribution according to the alpha-fetoprotein content and the corresponding position, and the points where the peak concentration may exist can be fitted and marked as the lesion site.
[0091] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.
Claims
1. A collaborative processing system for ultrasound and biomarker detection, It is characterized in that include: An ultrasound positioning module, which collects ultrasound images of the patient and determines a location to be sampled according to the ultrasound images; A sampling and testing module, the sampling and testing module is connected to the ultrasonic positioning module, and the sampling and testing module takes samples according to the part to be sampled and tests to obtain test results; An analysis module, wherein the analysis module is connected to the ultrasound positioning module and the sampling and testing module respectively, and the analysis module marks the ultrasound image according to the test result.
2. The collaborative processing system according to claim 1, It is characterized in that The ultrasonic positioning module comprises: A scanning module, wherein the scanning module controls the ultrasound probe to collect an echo sequence from the patient and to image the patient to obtain the ultrasound image; A segmentation module, the segmentation module is connected to the scanning module, and the segmentation module segments the liver fibrosis tissue from the ultrasound image according to the grayscale threshold; A pre-labeling module is connected to the segmentation module, and the pre-labeling module predicts a nodule portion of the liver fibrous tissue as the portion to be sampled.
3. The collaborative processing system according to claim 2, It is characterized in that The ultrasonic positioning module also includes: A background echo measurement module, the background echo measurement module is connected to the scanning module, and the background echo measurement module measures and obtains background echo parameters during the acquisition process; An adaptive scanning module, wherein the adaptive scanning module is connected to the background echo measurement module and the scanning module, and the adaptive scanning module adjusts the ultrasonic scanning parameters of the scanning module according to the background echo parameters to separate the nodule area and the background image.
4. The collaborative processing system according to claim 2, It is characterized in that The pre-marking module comprises: A connected domain detection module, wherein the connected domain detection module performs connected domain detection on the separated liver fibrous tissue to separate and obtain a plurality of connected domains; A classification module, the classification module is connected to the connected domain detection module, the classification module performs edge detection on the connected domain to classify it into a circular connected domain and a branch-shaped connected domain, and marks the circular connected domain as the part to be sampled; A width measurement module, the width measurement module is connected to the classification module, the width measurement module constructs width detection vectors for multiple external endpoints of the branch-shaped communication domain respectively, and moves the width detection vectors along the branch-shaped communication domain; When the length of the width detection vector changes suddenly, the width measurement module marks the corresponding position as the part to be sampled.
5. The collaborative processing system according to claim 2, It is characterized in that The sampling and testing module comprises: A sequence positioning module, wherein the sequence positioning module obtains the part to be sampled and determines a corresponding echo sequence segment according to the position of the part to be sampled in the ultrasound image; A position information extraction module, wherein the position information extraction module is connected to the sequence positioning module, and the position information extraction module extracts the position information of the ultrasound probe according to the echo sequence segment to obtain the corresponding probe position and output it.
6. The collaborative processing system according to claim 5, It is characterized in that The sampling and testing module also includes: A projection module is connected to the position information extraction module and an external laser projector, and the projection module controls the laser projector to generate laser projection according to the probe position.
7. The collaborative processing system according to claim 1, It is characterized in that The analysis module comprises: A point screening module, wherein the point screening module screens the lesion site from the site to be sampled according to the test result; A marking module, wherein the marking module is connected to the point screening module, and the marking module marks the lesion site in the ultrasound image.
8. The collaborative processing system according to claim 7, It is characterized in that The analysis module also includes: A fitting module is used to fit the lesion site according to the test result, and the labeling module labels the lesion site output by the fitting module.
