CN111933279A - Intelligent disease diagnosis and treatment system - Google Patents
Intelligent disease diagnosis and treatment system Download PDFInfo
- Publication number
- CN111933279A CN111933279A CN202010958768.5A CN202010958768A CN111933279A CN 111933279 A CN111933279 A CN 111933279A CN 202010958768 A CN202010958768 A CN 202010958768A CN 111933279 A CN111933279 A CN 111933279A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- information
- medical
- treatment
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/02—Measuring pulse or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0883—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the heart
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/48—Diagnostic techniques
- A61B8/488—Diagnostic techniques involving Doppler signals
Abstract
The invention discloses an intelligent disease diagnosis and treatment system, which comprises more than two medical examination instruments in a medical workstation, a database system connected with the medical examination instruments in a data transmission mode, a diagnosis and analysis system connected with the database system, and an information feedback system connected with the diagnosis and analysis system; the medical examination instrument carries out medical examination on a human body, acquires medical image information of the human body and corresponding medical diagnosis and treatment information, and then transmits the acquired information to the database system; the database system processes the collected medical image information and the corresponding medical diagnosis and treatment information, and a multi-mode information model is established by using an artificial intelligence module to form a model database; the diagnosis and analysis system calls an existing model database to study and judge the clinically acquired medical image information, and a medical diagnosis and treatment report is output through the information feedback system. And the diagnosis and treatment results in multiple directions are researched and judged through artificial intelligence, so that the manual operation content is saved, and the method is more accurate and efficient.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to an intelligent disease diagnosis and treatment system.
Background
Modern medicine is syndrome-based medicine, and medical imaging includes various image examination and treatment methods, and has become the largest source of clinical evidence at present. The trend in medical imaging is the convergence and optimization of multiple imaging modalities, and in addition, the need for the communication and mutual convergence of professional information. With the gradual normalization of imaging examinations, the large shortage of personnel and the large amount of imaging data put a great deal of pressure and challenge on imaging department doctors today. For example, echocardiography measurements and results analysis rely on the practical and theoretical basis of the examiner, often requiring long-term, specialized training of the examiner, and not only is the entire echocardiography workflow, including patient preparation, sonographer acquisition of images, integration of measurement data, analysis of images and final results, and presentation of reports for shaping, a very time consuming and inefficient process. Many non-sonographers are unable to use ultrasound freely due to lack of standard image acquisition and analysis skills, which is also problematic in other imaging modalities. Moreover, the existing image examination is independent, single in information, less in function, and incapable of completing comprehensive and interactive diagnosis and treatment evaluation. The current ultrasound diagnostic report contains a large amount of medical information reflecting the characteristics of the patient's disease, but is mostly described by physicians using their own language, is unstructured, and the content reflected therein is not sufficient and comprehensive. The inaccuracy of the language description makes it difficult for the clinician to analyze, study, summarize, and extract, which is not conducive to scientific data analysis, sharing, and quality assessment management.
Disclosure of Invention
The applicant aims at the defects that the image examination efficiency is low, the instrument diagnosis and treatment information is single, the diagnosis and treatment functions are few, the manual diagnosis and treatment report is unstructured and difficult to analyze and is not comprehensive in the existing medical image diagnosis and treatment technology, an intelligent disease diagnosis and treatment system with a reasonable structure is provided, images from different equipment sources can be collected to form an intelligent model, diversified diagnosis and treatment results are output through artificial intelligence research and judgment, the manual operation content is saved, diagnosis and treatment can be more accurate and efficient, and the output medical diagnosis and treatment report is standard and comprehensive.
The technical scheme adopted by the invention is as follows:
an intelligent disease diagnosis and treatment system comprises more than two medical examination instruments in a medical workstation, a database system connected with the medical examination instruments in a data transmission mode, a diagnosis and analysis system connected with the database system, and an information feedback system connected with the diagnosis and analysis system; the medical examination instrument carries out medical examination on a human body, acquires medical image information of the human body and corresponding medical diagnosis and treatment information, and then transmits the acquired information to the database system; the database system processes the collected medical image information and the corresponding medical diagnosis and treatment information, and a multi-mode information model is established by using an artificial intelligence module to form a model database; the diagnosis and analysis system calls an existing model database to study and judge the clinically acquired medical image information, a medical diagnosis and treatment report is output through the information feedback system, meanwhile, the data of the diagnosis and treatment is stored in the database system, and the model database in the database system is updated.
As a further improvement of the above technical solution:
the medical image information is one or more of a three-dimensional image, a two-dimensional image, sound, a motion state, and the flow speed and the flow quantity of blood; the medical diagnosis and treatment information is one or two of an instrument diagnosis and treatment conclusion and a doctor diagnosis and treatment conclusion.
The medical image information comprises disease characteristic information of different internal organs, and the artificial intelligence module establishes a multi-modal information model comprising a plurality of internal organs in linkage.
The multi-mode information model comprises information including a three-dimensional reconstruction model, image information and character information.
The database system at least comprises a feature index table, a feature library and an experience image database.
The database system decomposes a source image into a smooth image in a GIF mode for image decomposition; constructing a smooth image fusion rule capable of distinguishing important information and redundant information by using a frequency spectrum residual method; and adopting an image-based visual saliency detection algorithm to construct a fusion rule of the detailed images.
The database system tags and classifies the collected echocardiograms of different sections.
The database system adopts an end-to-end target detection neural network to detect each valve and chamber of the classified echocardiogram in real time, and medical diagnosis and treatment information is formed.
The database system adopts an improved MC algorithm to carry out three-dimensional reconstruction on the medical image, the improved MC algorithm expands the topology configurations to 24 types, a midpoint selection method is adopted to replace a linear interpolation method, the 24 topology configurations are divided into three types, each type corresponds to a macro, a processing function is called through a macro trigger function pointer, the three types of configurations respectively correspond to three threads, and the threads are synchronized in a critical zone mode.
The database system carries out structural division and characteristic point subdivision on different disease diagnosis and diagnosis branches by using a decision tree model.
The invention has the following beneficial effects:
according to the invention, the artificial intelligence technology is adopted to collect, intelligently analyze and process images from different equipment sources, different types of image data are integrated, diagnosis results of different diseases are fused, diagnosis cases of different doctors are combined, a multi-mode information model is formed through processing, and multi-directional diagnosis and treatment results are output through artificial intelligence study and judgment, so that the content of manual operation is greatly saved, manual labor force is liberated, cost and resource consumption are reduced, intelligent analysis and diagnosis and treatment break through the capacity limitation of the existing human medicine, and the method is more accurate and efficient. Compared with the prior art, the method has the advantages of strong compatibility, wide application range, intelligent analysis and processing and the like. The invention can realize the purpose of the invention by adopting an external system without modifying or replacing the existing medical examination instrument, and has the characteristics of good applicability and practicability.
The invention utilizes artificial intelligence and the advantage of big data to continuously update and optimize the intelligent model and continuously improve the accuracy and the accuracy of diagnosis and treatment. The invention can not only replace the artificial diagnosis and treatment link, but also be used as auxiliary equipment to provide experience reference for new doctors, accelerate the growth of the new doctors and ensure the accuracy of diagnosis and treatment. The normalized medical diagnosis and treatment report output by the invention has the characteristic of structuralization, can use normalized formats and phrases, and has superiority compared with the existing manual report. The invention effectively solves the problems of increased medical examination quantity and shortage of doctors, particularly has unique advantages on the image processing of the echocardiogram, and effectively solves the current situation of unbalanced supply and demand of the doctors.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
FIG. 2 is a schematic illustration of echocardiography tagging of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings.
As shown in fig. 1, the intelligent disease diagnosis and treatment system of the present invention includes a medical examination apparatus of a medical workstation, a database system connected to the medical examination apparatus through a data transmission manner, a diagnosis and analysis system connected to the database system, and an information feedback system connected to the diagnosis and analysis system. The medical workstation is a place where medical image examination is performed on a human body by using professional medical equipment and medical examination equipment is provided, and can be a medical institution or a department unit with medical examination equipment in the medical institution, such as an image center. The types of the medical examination instruments include but are not limited to ECG machines, X-ray machines, CT machines, MRI machines, ultrasonic machines and the like, more than two or all the medical examination instruments in the medical workstation can be selected to be simultaneously connected with the database system, and information is jointly acquired through a plurality of the medical examination instruments. The medical examination instrument carries out medical examination on a human body, collects medical image information of the human body and corresponding medical diagnosis and treatment information, and then transmits the collected information to the database system. The database system processes the collected medical image information and the corresponding medical diagnosis and treatment information, and a multi-mode information model is established by utilizing the artificial intelligence module to form a model database. The diagnosis and analysis system calls an existing model database to study and judge the clinically acquired medical image information, outputs a standardized medical diagnosis and treatment report through the information feedback system, simultaneously stores the data of the diagnosis and treatment in the database system, and updates the model database in the database system. The standardized medical diagnosis and treatment report can be unified in format and terms, and recorded information is more accurate and comprehensive. The report output by the information feedback system can be presented on a computer terminal or other terminals, and has the functions of doctor intervening in the diagnosis result and increasing database data, the diagnosis result needs the doctor to correct, and the correct diagnosis and treatment data is used as the source of machine learning and system application. The database system is the basis of the whole system and at least comprises a feature index table, a feature library, an experience image database and the like.
Depending on the instrument, the type of medical image information includes, but is not limited to, a three-dimensional image, a two-dimensional image, a sound, a motion state, a blood flow velocity and a blood flow rate, and the like, wherein the three-dimensional image and the two-dimensional image include information such as the shape, structure, color, and the like of an organ. The types of the medical diagnosis and treatment information include but are not limited to an instrument diagnosis and treatment conclusion, a doctor diagnosis and treatment conclusion and the like, and the instrument diagnosis and treatment conclusion and the doctor diagnosis and treatment conclusion are preferably combined and verified, so that the accuracy and the accuracy are improved. The multi-modal information model contains information including, but not limited to, a three-dimensional reconstruction model, visual information, and textual information.
The implementation process of the intelligent disease diagnosis and treatment system comprises a database building process and an application learning process. Taking cardiac diagnosis and treatment as an example, the database system utilizes an artificial intelligence module to establish a multi-modal information model by the following steps:
firstly, dynamic modal decomposition and fusion are carried out on a source image. The images acquired by the medical examination apparatus may include cardiac gray scale echocardiography, multi-slice echocardiography, and color doppler flow visualization, as well as other related different types of images. To perform multi-scale decomposition and reconstruction of images and to construct a fusion rule, in an image decomposition step, a GIF (Graphics Interchange Format) method is used to decompose a source image into smooth images, i.e., various scale images having the same resolution as an input image in a spatial domain. In the fusion rule construction step, a spatial residual importance detection algorithm spectrum residual method (SR) is used to construct a smooth image fusion rule that can distinguish important information from redundant information. And constructing a fusion rule of the detailed image by adopting an image-based visual saliency detection algorithm so as to generate a more compact and consistent fusion result and a visual system, and obtaining the fusion image by utilizing the fusion rule.
Second, labels and classifications are added to the echocardiograms collected for a large number of different slices. And adding labels to all the pictures according to the section types to serve as a section classification training data set. For example, the multi-section echocardiogram comprises different valves and chambers, and whether the valves and the chambers are normal or not is detected according to different section targets (see fig. 2). And manually or automatically adding a target detection frame and corresponding labels to the echocardiograms with different section types by using a data set label function, and constructing a training data set of a target detection algorithm. The ResNet neural network is adopted to automatically classify the stored pictures, the structure of the ResNet neural network can accelerate the training of the ultra-deep neural network very quickly, and the accuracy of the model is greatly improved.
In the image processing process, the classified echocardiograms are subjected to real-time target detection on each valve and chamber by adopting an end-to-end target detection neural network, so that medical diagnosis is realized. As an improvement, a target detection neural network and an exclusive-or network are combined to form a mixed precision neural network, and the target detection precision of the high-precision ultrasonic image and the operation efficiency of the neural network are balanced.
The dynamic image is then combined with the static image and its representation is identified. Taking the heart as an example, the motion of the target is observed clinically according to an echocardiogram, and the state of the heart is judged by combining other data. Such as acoustic quantification and dynamic color chamber walls, can reflect the index features of the heart, and optical flow and speckle tracking can reflect the motion state of the heart.
Then, the medical image is three-dimensionally reconstructed, a complete three-dimensional model is reconstructed by adopting an improved MC Algorithm (Marching Cubes Algorithm), and the model is stored or updated through subsequent processing. The improved MC algorithm is expanded from the original 15 topological configurations to 24 topological configurations, the problem of cavities on the surface of a model is solved, a midpoint selection method is adopted to replace a linear interpolation method, the calculated amount is simplified on the formula, the 24 topological configurations are divided into three types, each type corresponds to a macro, a processing function is called by a macro trigger function pointer, the opening and closing principle and the expansibility of the types are effectively maintained, the three types of configurations respectively correspond to three threads, the threads are synchronized in a critical zone mode, and the safety of a program is guaranteed.
Furthermore, the electrocardiogram waveform and the image data are synchronously processed and analyzed, and diversified data are recorded.
Then, images from different imaging devices, which are referred to as multi-modality images, are subjected to registration processing by multi-modality machine learning. For image registration, various index results can be obtained according to actual image characteristics and a registration algorithm. Therefore, the multi-modal information model formed by the invention can be flexibly changed according to the actual situation, and has very wide application modes.
And finally, carrying out structural division and feature point subdivision on different disease diagnosis and diagnosis branches by using a decision tree model. The decision tree is a process for carrying out tree classification on sample data from top to bottom, and comprises nodes and directed edges, node atmosphere internal nodes and leaf nodes, wherein each internal node represents a feature or a tree shape, and the leaf nodes represent categories. All samples are gathered together from the top root node and are divided into different sub-nodes, and all samples are classified into one leaf node through further division of the characteristics of the sub-nodes. The decision tree model is beneficial to improving the diagnosis and treatment accuracy and the diagnosis and treatment efficiency.
In the process of establishing or updating the multi-mode information model, manual intervention can be performed in real time, the completeness and the accuracy of diagnosis and treatment information are achieved, the added medical diagnosis and treatment information such as diagnosis and treatment conclusions of doctors can be input into diagnosis and treatment cases of some specialist doctors, and the guidance value of the model database is improved.
In the implementation application, for the medical examination of a new patient, a plurality of medical examination instruments acquire a plurality of different medical images, the data of the medical images are transmitted to a diagnosis and analysis system, the diagnosis and analysis system calls an existing model database to study and judge the clinically acquired medical image information, a normalized medical diagnosis and treatment report is output through an information feedback system, meanwhile, the data of the diagnosis and treatment is stored in the database system, and the model database in the database system is updated. The invention has the characteristics of continuous learning and intellectualization, and can learn from expert cases, historical data and clinical application, and continuously update learning, thereby being far beyond the artificial learning ability.
In practical application, the invention can simultaneously carry out linkage examination and diagnosis and treatment on a plurality of visceral organs to form an all-around comprehensive diagnosis and treatment result, breaks through the limitation of independent diagnosis and treatment and limited range of each department in the existing medicine, reduces the probability of repeated inquiry and examination, and has more accurate and comprehensive diagnosis and treatment.
The foregoing description is illustrative of the present invention and is not to be construed as limiting thereof, as the invention may be modified in any manner without departing from the spirit thereof.
Claims (10)
1. The utility model provides an intelligent disease diagnosis and treatment system which characterized in that: the medical examination system comprises more than two medical examination instruments in a medical workstation, a database system connected with the medical examination instruments in a data transmission mode, a diagnosis and analysis system connected with the database system, and an information feedback system connected with the diagnosis and analysis system; the medical examination instrument carries out medical examination on a human body, acquires medical image information of the human body and corresponding medical diagnosis and treatment information, and then transmits the acquired information to the database system; the database system processes the collected medical image information and the corresponding medical diagnosis and treatment information, and a multi-mode information model is established by using an artificial intelligence module to form a model database; the diagnosis and analysis system calls an existing model database to study and judge the clinically acquired medical image information, a medical diagnosis and treatment report is output through the information feedback system, meanwhile, the data of the diagnosis and treatment is stored in the database system, and the model database in the database system is updated.
2. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the medical image information is one or more of a three-dimensional image, a two-dimensional image, sound, a motion state, and the flow speed and the flow quantity of blood; the medical diagnosis and treatment information is one or two of an instrument diagnosis and treatment conclusion and a doctor diagnosis and treatment conclusion.
3. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the medical image information comprises disease characteristic information of different internal organs, and the artificial intelligence module establishes a multi-modal information model comprising a plurality of internal organs in linkage.
4. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the multi-mode information model comprises information including a three-dimensional reconstruction model, image information and character information.
5. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system at least comprises a feature index table, a feature library and an experience image database.
6. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system decomposes a source image into a smooth image in a GIF mode for image decomposition; constructing a smooth image fusion rule capable of distinguishing important information and redundant information by using a frequency spectrum residual method; and adopting an image-based visual saliency detection algorithm to construct a fusion rule of the detailed images.
7. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system tags and classifies the collected echocardiograms of different sections.
8. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system adopts an end-to-end target detection neural network to detect each valve and chamber of the classified echocardiogram in real time, and medical diagnosis and treatment information is formed.
9. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system adopts an improved MC algorithm to carry out three-dimensional reconstruction on the medical image, the improved MC algorithm expands the topology configurations to 24 types, a midpoint selection method is adopted to replace a linear interpolation method, the 24 topology configurations are divided into three types, each type corresponds to a macro, a processing function is called through a macro trigger function pointer, the three types of configurations respectively correspond to three threads, and the threads are synchronized in a critical zone mode.
10. The intelligent disease diagnosis and treatment system according to claim 1, wherein: the database system carries out structural division and characteristic point subdivision on different disease diagnosis and diagnosis branches by using a decision tree model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010958768.5A CN111933279A (en) | 2020-09-14 | 2020-09-14 | Intelligent disease diagnosis and treatment system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010958768.5A CN111933279A (en) | 2020-09-14 | 2020-09-14 | Intelligent disease diagnosis and treatment system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111933279A true CN111933279A (en) | 2020-11-13 |
Family
ID=73333423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010958768.5A Pending CN111933279A (en) | 2020-09-14 | 2020-09-14 | Intelligent disease diagnosis and treatment system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111933279A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112735590A (en) * | 2021-01-14 | 2021-04-30 | 上海交通大学 | Lumbar vertebra herniation curative effect evaluation expert system based on traditional Chinese medicine big data analysis |
| CN112802000A (en) * | 2021-02-06 | 2021-05-14 | 上海集迈实业有限公司 | Intelligent auxiliary diagnosis and treatment system for multi-modal medical images |
| CN113053523A (en) * | 2021-04-23 | 2021-06-29 | 广州易睿智影科技有限公司 | Continuous self-learning multi-model fusion ultrasonic breast tumor precise identification system |
| WO2022126800A1 (en) * | 2020-12-17 | 2022-06-23 | 谈斯聪 | Symptom, blood data and medical image fused method for comprehensively recognizing various suspected diseases |
| WO2023109283A1 (en) * | 2021-12-16 | 2023-06-22 | 华为云计算技术有限公司 | Method and apparatus for interpreting medical test data |
| CN116522248A (en) * | 2023-03-22 | 2023-08-01 | 新疆维吾尔自治区疾病预防控制中心 | Nucleic acid abnormal data intelligent research and judgment system based on machine learning |
| CN116665889A (en) * | 2023-07-28 | 2023-08-29 | 长春中医药大学 | Intelligent auxiliary diagnosis and treatment system applied to gynecological outpatient service |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247881A (en) * | 2017-06-20 | 2017-10-13 | 北京大数医达科技有限公司 | A kind of multi-modal intelligent analysis method and system |
| CN109378054A (en) * | 2018-12-13 | 2019-02-22 | 山西医科大学第医院 | A kind of multi-modality images assistant diagnosis system and its building method |
| CN109934922A (en) * | 2019-03-14 | 2019-06-25 | 哈尔滨理工大学 | A kind of three-dimensional rebuilding method based on improvement MC algorithm |
-
2020
- 2020-09-14 CN CN202010958768.5A patent/CN111933279A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247881A (en) * | 2017-06-20 | 2017-10-13 | 北京大数医达科技有限公司 | A kind of multi-modal intelligent analysis method and system |
| CN109378054A (en) * | 2018-12-13 | 2019-02-22 | 山西医科大学第医院 | A kind of multi-modality images assistant diagnosis system and its building method |
| CN109934922A (en) * | 2019-03-14 | 2019-06-25 | 哈尔滨理工大学 | A kind of three-dimensional rebuilding method based on improvement MC algorithm |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022126800A1 (en) * | 2020-12-17 | 2022-06-23 | 谈斯聪 | Symptom, blood data and medical image fused method for comprehensively recognizing various suspected diseases |
| CN112735590A (en) * | 2021-01-14 | 2021-04-30 | 上海交通大学 | Lumbar vertebra herniation curative effect evaluation expert system based on traditional Chinese medicine big data analysis |
| CN112802000A (en) * | 2021-02-06 | 2021-05-14 | 上海集迈实业有限公司 | Intelligent auxiliary diagnosis and treatment system for multi-modal medical images |
| CN113053523A (en) * | 2021-04-23 | 2021-06-29 | 广州易睿智影科技有限公司 | Continuous self-learning multi-model fusion ultrasonic breast tumor precise identification system |
| WO2023109283A1 (en) * | 2021-12-16 | 2023-06-22 | 华为云计算技术有限公司 | Method and apparatus for interpreting medical test data |
| CN116522248A (en) * | 2023-03-22 | 2023-08-01 | 新疆维吾尔自治区疾病预防控制中心 | Nucleic acid abnormal data intelligent research and judgment system based on machine learning |
| CN116522248B (en) * | 2023-03-22 | 2023-12-15 | 新疆维吾尔自治区疾病预防控制中心 | Nucleic acid abnormal data intelligent research and judgment system based on machine learning |
| CN116665889A (en) * | 2023-07-28 | 2023-08-29 | 长春中医药大学 | Intelligent auxiliary diagnosis and treatment system applied to gynecological outpatient service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111933279A (en) | Intelligent disease diagnosis and treatment system | |
| CN103793611B (en) | Medical information visualization method and device | |
| CN110517238B (en) | AI three-dimensional reconstruction and human-computer interaction visualization network system for CT medical image | |
| JP5222082B2 (en) | Information processing apparatus, control method therefor, and data processing system | |
| JP2022529682A (en) | Medical video splitting methods, devices, computer devices and computer programs | |
| CN111429407B (en) | Chest X-ray disease detection device and method based on double-channel separation network | |
| EP1711908A2 (en) | Systems and methods for automated diagnosis and decision support for heart related diseases and conditions | |
| CA2530595A1 (en) | Automated regional myocardial assessment for cardiac imaging | |
| CN111739000B (en) | System and device for improving left ventricle segmentation accuracy of multiple cardiac views | |
| CN114052794B (en) | Carotid artery ultrasonic report generation system based on multi-mode information | |
| CN112270993B (en) | Ultrasonic robot online decision-making method and system taking diagnosis result as feedback | |
| CN112151169B (en) | Autonomous scanning method and system of humanoid-operation ultrasonic robot | |
| Sengupta | Intelligent platforms for disease assessment: novel approaches in functional echocardiography | |
| CN107665737A (en) | Vascular wall stress-strain state acquisition methods, computer-readable medium and system | |
| JP5539478B2 (en) | Information processing apparatus and information processing method | |
| CN105096227A (en) | Visualization processing method for health data | |
| CN112132805B (en) | Ultrasonic robot state normalization method and system based on human body characteristics | |
| KR101843928B1 (en) | Method and apparatus for displaying an analysis result of medical measured data | |
| CN112397178A (en) | Medical image classification processing system based on artificial intelligence | |
| CN111276218A (en) | Accurate diagnosis and treatment system, equipment and method | |
| CN109192308A (en) | A kind of early screening system of peripheral arteriosclerosis | |
| CN115719329A (en) | Method and system for fusing RA ultrasonic modal synovial membrane scores based on deep learning | |
| CN115132376A (en) | Cardiovascular and cerebrovascular disease collaborative diagnosis model system based on multivariate heterogeneous medical data | |
| Alghadier et al. | A study of various applications of artificial intelligence (AI) and machine learning (ML) for healthcare services | |
| Garg et al. | Role of Deep Learning in Computed Tomography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |