CN115458160A - Whole-course intelligent management system, method, equipment and medium for breast tumor patient - Google Patents

Whole-course intelligent management system, method, equipment and medium for breast tumor patient Download PDF

Info

Publication number
CN115458160A
CN115458160A CN202211248421.7A CN202211248421A CN115458160A CN 115458160 A CN115458160 A CN 115458160A CN 202211248421 A CN202211248421 A CN 202211248421A CN 115458160 A CN115458160 A CN 115458160A
Authority
CN
China
Prior art keywords
patient
follow
breast tumor
treatment
image
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.)
Granted
Application number
CN202211248421.7A
Other languages
Chinese (zh)
Other versions
CN115458160B (en
Inventor
何瀛
谢探
曹一佳
鲍晓仙
严林娟
张晴霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202211248421.7A priority Critical patent/CN115458160B/en
Publication of CN115458160A publication Critical patent/CN115458160A/en
Application granted granted Critical
Publication of CN115458160B publication Critical patent/CN115458160B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • 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
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention relates to a system, a method, equipment and a medium for the whole-course intelligent management of breast tumor patients, wherein the system comprises the following components: the system comprises a preliminary screening module capable of outputting the position and the risk score of a suspected area image, a first pathological diagnosis module capable of diagnosing the suspected area image of the breast tumor with the risk score smaller than a certain threshold value, a second pathological diagnosis module capable of diagnosing the suspected area image of the breast tumor with the risk score not smaller than the certain threshold value or an image pushed by the first pathological diagnosis module, a treatment scheme output module capable of outputting a treatment scheme and a follow-up interaction module capable of interacting with a patient and constructing a three-dimensional patient model. The invention not only improves the screening precision and the diagnosis and treatment efficiency, but also provides a corresponding treatment scheme for the patient in time and lightens the further deterioration possibility of the patient. Meanwhile, after intervention, the progress of the patient's condition and various indexes of the patient's body can be obtained in real time and displayed to the patient in a three-dimensional model, so that the follow-up visit of the patient can be reminded in time.

Description

Whole-course intelligent management system, method, equipment and medium for breast tumor patient
Technical Field
The invention relates to the technical field of medical data processing, in particular to a whole-course intelligent management system, method, equipment and medium for breast tumor patients.
Background
In recent years, the prevalence rate and the fatality rate of breast diseases in China are high, and breast malignant tumors become an unimportant topic for Chinese women. However, unlike other cancers, breast cancer is specific and can significantly improve patient survival rates through early screening and treatment.
Meanwhile, with the continuous updating and iteration of various screening modes and detection devices, a great deal of identification and processing work is brought to medical personnel while more accurate disease information is brought to the medical personnel by infinite detection images and data, which is a huge challenge to the existing medical personnel.
Therefore, in order to reduce the burden of medical staff and improve efficiency and identification accuracy, it is necessary to establish an intelligent management system which can automatically run in the whole course of breast tumor patients.
Disclosure of Invention
Technical problem to be solved
In view of the above disadvantages and shortcomings of the prior art, the present invention provides a system, a method, a device and a medium for whole-course intelligent management of breast tumor patients, which solves the technical problem that the existing medical treatment does not provide an intelligent management scheme capable of automatic operation in whole course.
(II) technical scheme
In order to achieve the purpose, the invention adopts the main technical scheme that:
in a first aspect, an embodiment of the present invention provides a system for intelligently managing a breast tumor patient in a whole course, including:
the primary screening module is used for traversing the imaging examination image of each patient in a preset database, and outputting the image position of a suspected area and a risk score determined by extracting the image characteristics when the suspected area of the breast tumor is identified;
the first pathological diagnosis module is used for outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to the next pathological diagnosis module for processing according to the palpation information of the patient and/or the auditing feedback information of medical staff, which are called from the database, aiming at the breast tumor suspected region image with the risk score smaller than a certain threshold;
the second pathological diagnosis module is used for outputting pathological results according to one or more data of palpation information of a patient, audit feedback information of medical staff, suspected region images, gene detection results and histopathological examination results, which are called from a preset database, aiming at the breast tumor suspected region images with the risk score not less than a certain threshold value or the images pushed by the first pathological diagnosis module;
a treatment plan output module for determining at least one disease category based on the pathological result and outputting a treatment plan by combining the patient information and the past related treatment cases called from the database;
and the follow-up visit interaction module is used for establishing a three-dimensional patient model according to the follow-up diagnosis suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
Optionally, the preliminary screening module comprises:
the tumor suspected region identification unit is used for traversing the imaging examination image of each patient and recording the position of the suspected region image when the breast tumor suspected region is identified;
the characteristic extraction unit is used for extracting key characteristics from the breast tumor suspected region image;
and the risk determining unit is used for obtaining a risk score through a pre-trained risk prediction model according to the key characteristics.
Alternatively, the first and second liquid crystal display panels may be,
the imaging examination image is image data acquired by CT, PET, magnetic resonance or ultrasonic imaging equipment;
the key features include: morphology, edges, maximum diameter, ratio of longitudinal to transverse diameters, drag index, peak systolic flow rate, parenchymal echo, cystic changes, calcific foci, and blood flow signals;
the risk prediction model is as follows: a support vector machine, a neural network, a Bayesian network, and a decision tree.
Optionally, the first pathological diagnosis module comprises:
the palpation information calling unit is used for calling the palpation information of the patient from a preset database;
the first pushing unit is used for pushing the breast tumor suspected region image with the risk score smaller than a certain threshold value to an operation end of medical personnel so as to obtain auditing feedback information of the medical personnel;
the report output unit is used for outputting a follow-up consultation suggestion report when the palpation information and the audit feedback information of the patient both indicate a benign conclusion;
and the second pushing unit is used for pushing the palpation information and the auditing feedback information of the patient to a next-stage pathological diagnosis module for processing when at least one of the palpation information and the auditing feedback information of the patient indicates a non-benign conclusion.
Optionally, the second pathological diagnosis module comprises:
the multi-information calling and processing unit is used for calling one or more data of the patient palpation information, the medical staff auditing feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result from a preset database and carrying out normalization processing;
the multi-factor regression analysis unit is used for obtaining a plurality of risk factors through Logistic regression analysis on the normalized patient palpation information, the medical staff audit feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result;
the pathological result output unit is used for comparing each risk factor with a preset threshold value to obtain a pathological result;
wherein the pathological result comprises one or more data of confirmed age, tumor type, tumor stage, tumor size, molecular typing, regional lymph node metastasis condition and distant metastasis condition.
Optionally, the treatment protocol output module comprises:
a disease classification unit for determining at least one disease category based on the pathology result;
a related treatment case calling unit for calling a related treatment case set S = { x } from the database according to the disease category 1 ,x 2 ,…,x n }; wherein x is n For the case of the n-th treatment,
Figure BDA0003887440310000031
Figure BDA0003887440310000032
for a plurality of characteristic data of each treatment case, i and n are positive integers;
a quantization processing unit for quantizing the current disease category and the patient information to form the current case
Figure BDA0003887440310000033
A treatment case screening unit for calculating the current case
Figure BDA0003887440310000034
And related treatment case set
Figure BDA0003887440310000035
Each treatment case in (1)
Figure BDA0003887440310000036
A distance value of (d);
the treatment plan output unit is used for taking the treatment case with the minimum distance value as the treatment plan;
the treatment cases are stored in a preset database in a set form through a clustering mode; and the plurality of feature data comprises: one or more of age, height, weight, comorbid disease, past medical history, family tumor history, adverse drug reactions, economic status, treatment waiting time, treatment effect, treatment side effects, length of treatment cost, and economic cost.
Optionally, the prognostic follow-up module comprises:
the follow-up visit unit is used for obtaining the prognostic sign indexes of the patients through follow-up visit;
the three-dimensional model building unit is used for building a three-dimensional patient model which can simulate the daily activities of a patient;
and the import display unit is used for importing data in the follow-up suggestion report or the prognostic sign index into the virtual module, and displaying abnormal labels at corresponding positions of the model.
In a second aspect, an embodiment of the present invention provides a method for intelligently managing a breast tumor patient in a whole course, including:
traversing the imaging examination image of each patient in a preset database, and outputting the image position of the suspected region and a risk score determined by extracting the image characteristics when the suspected region of the breast tumor is identified;
aiming at the breast tumor suspected region image with the risk score smaller than a certain threshold value, outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to a next-stage pathological diagnosis module for processing according to the palpation information of the patient and/or the audit feedback information of medical staff called from the database;
aiming at the breast tumor suspected region image with the risk score not less than a certain threshold value or the image pushed by the first pathological diagnosis module, outputting a pathological result according to one or more data of palpation information of a patient, audit feedback information of medical staff, the suspected region image, a gene detection result and a histopathological examination result called from a preset database;
determining at least one disease category based on the pathology results and outputting a treatment plan in conjunction with patient information and past related treatment cases recalled from a database;
and establishing a three-dimensional patient model according to the follow-up suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
In a third aspect, an embodiment of the present invention provides a breast tumor patient global intelligent management device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method for intelligent management of breast tumor patients throughout a course as described above.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer-executable instructions are stored, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method for full-scale intelligent management of breast tumor patients as described above.
(III) advantageous effects
The invention provides an intelligent management scheme for omnibearing automatic processing from the discovery of breast tumors to the intervention of the whole process, which not only improves the screening precision and the diagnosis and treatment efficiency, but also provides a treatment scheme for patients in time and lightens the further deterioration possibility of the disease conditions of the patients. Meanwhile, after intervention, the progress of the patient and various indexes of the body of the patient can be acquired in real time and displayed to the patient in a three-dimensional model, so that follow-up visit of the patient is prompted in time, and anxiety and bad mood of the patient are relieved.
Drawings
Fig. 1 is a schematic diagram illustrating a system for overall intelligent management of a breast tumor patient according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a whole-course intelligent management method for breast tumor patients according to an embodiment of the present invention.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.
As shown in fig. 1, an intelligent management system for a breast tumor patient in a whole course according to an embodiment of the present invention includes: and the primary screening module is used for traversing the imaging examination image of each patient in the preset database, and outputting the image position of the suspected area and the risk score determined by extracting the image characteristics when the suspected area of the breast tumor is identified. And the first pathological diagnosis module is used for outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to the next pathological diagnosis module for processing according to the palpation information of the patient and/or the auditing feedback information of the medical staff, which are called from the database, aiming at the breast tumor suspected region image with the risk score smaller than a certain threshold value. And the second pathological diagnosis module is used for outputting a pathological result according to one or more data of palpation information of the patient, audit feedback information of medical staff, suspected region image, gene detection result and histopathological examination result called from a preset database aiming at the breast tumor suspected region image with the risk score not less than a certain threshold value or the image pushed by the first pathological diagnosis module. And the treatment plan output module determines at least one disease category based on the pathological result and outputs a treatment plan by combining the patient information and the related treatment cases called from the database. And the follow-up visit interaction module is used for establishing a three-dimensional patient model according to the follow-up diagnosis suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
The invention provides an intelligent management scheme for omnibearing automatic processing from the discovery of breast tumors to the intervention of the whole process, which not only improves the screening precision and the diagnosis and treatment efficiency, but also provides a treatment scheme for patients in time and lightens the further deterioration possibility of the illness state of the patients. Meanwhile, after intervention, the progress of the patient and various indexes of the body of the patient can be acquired in real time and displayed to the patient in a three-dimensional model, so that follow-up visit of the patient is prompted in time, and anxiety and bad mood of the patient are relieved.
In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Further, the preliminary screening module includes:
and the suspected tumor area identification unit is used for traversing the imaging examination image of each patient and recording the image position of the suspected breast tumor area when the suspected breast tumor area is identified.
And the characteristic extraction unit is used for extracting key characteristics from the breast tumor suspected region image.
And the risk determining unit is used for obtaining a risk score through a pre-trained risk prediction model according to the key characteristics. Wherein, the imaging examination image is image data acquired by CT, PET, magnetic resonance or ultrasonic imaging equipment; the key features include: quantitative index: maximum diameter, longitudinal-transverse diameter ratio, resistance index and peak flow velocity in the contraction period, wherein qualitative indexes comprise morphology, edges, substantial echo, cystic changes, calcific foci and blood flow signals; the risk prediction model is as follows: a support vector machine, a neural network, a Bayesian network, and a decision tree.
The problems of large workload and inaccurate positioning in manual division of the breast tumor suspected area by doctors are considered, and different doctors have certain difference of delineated tumor boundaries due to experience difference, so that the accuracy of image identification is obviously influenced by subjectivity. Therefore, a segmentation result similar to the manual drawing can be obtained by adopting a segmentation algorithm such as a clustering-based segmentation method and combining with an expert prior rule. Then, the breast tumor image characteristics are quantified, and the breast tumor suspected area is described from multiple aspects of the breast tumor, such as morphology, edges, maximum diameter, ratio of longitudinal diameter to transverse diameter, resistance index, peak systolic flow rate, parenchymal echo, cystic change, calcific foci, blood flow signals and the like, so that a solid foundation is laid for subsequent diagnosis.
Next, the first pathological diagnosis module includes:
the palpation information calling unit is used for calling the palpation information of the patient from a preset database;
the first pushing unit is used for pushing the breast tumor suspected region image with the risk score smaller than a certain threshold value to an operation end of medical personnel so as to obtain auditing feedback information of the medical personnel;
the report output unit is used for outputting a follow-up consultation suggestion report when the palpation information and the audit feedback information of the patient both indicate a benign conclusion;
and the second pushing unit is used for pushing the palpation information and the auditing feedback information of the patient to a next-stage pathological diagnosis module for processing when at least one of the palpation information and the auditing feedback information of the patient indicates a non-benign conclusion.
Next, the second pathological diagnosis module includes:
the multi-information calling and processing unit is used for calling one or more data of the patient palpation information, the medical staff auditing feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result from a preset database and carrying out normalization processing;
the multi-factor regression analysis unit is used for obtaining a plurality of risk factors through Logistic regression analysis on the normalized patient palpation information, the medical staff audit feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result;
the pathological result output unit is used for comparing each risk factor with a preset threshold value to obtain a pathological result;
wherein the pathological result comprises one or more data of confirmed age, tumor type, tumor stage, tumor size, molecular typing, regional lymph node metastasis and distant metastasis.
In the embodiment of the invention, the breast tumor data with different risk degrees are processed in a grading manner by adopting two stages of pathological diagnosis modules, so that the processing efficiency and the processing flow are accelerated, the medical resources are saved, and meanwhile, the Logistic regression analysis is adopted to obtain main risk factors aiming at higher risk cases so as to carry out individualized intervention aiming at the main influence factors in the follow-up process.
Further, the treatment plan output module includes:
a disease classification unit for determining at least one disease category based on the pathology result;
a related treatment case calling unit for calling a related treatment case set s from the database according to the disease category t ＝{x 1 ,x 2 ,…,x n In which x n For the case of the n-th treatment,
Figure BDA0003887440310000081
Figure BDA0003887440310000082
for a plurality of characteristic data of each treatment case, i and n are positive integers; wherein the plurality of feature data includes: one or more of age, height, weight, comorbid disease, past medical history, family tumor history, adverse drug reactions, economic status, treatment waiting time, treatment effect, treatment side effects, length of treatment cost, and economic cost.
A quantization processing unit for quantizing the current disease category and the patient information to form a current case
Figure BDA0003887440310000083
A treatment case screening unit for calculating the current case
Figure BDA0003887440310000084
And associated treatment case set s t ＝{x 1 ,x 2 ,…,x n Each treatment case of
Figure BDA0003887440310000085
The distance value of (a);
and the treatment scheme output unit is used for taking the treatment case with the minimum distance value as the treatment scheme.
In the treatment scheme output module, firstly, treatment cases are stored in preset data in a set form in a clustering mode; secondly, the distance between the current case and each case in the called related treatment case set is calculated, so that the closest treatment case is judged, and the treatment scheme which is most suitable for the current situation of the patient is obtained.
Then, the prognostic follow-up module includes:
the follow-up visit unit is used for obtaining the prognostic sign indexes of the patients through follow-up visit;
the three-dimensional model building unit is used for building a three-dimensional patient model which can simulate the daily activities of a patient;
and the import display unit is used for importing data in the follow-up suggestion report or the prognostic sign index into the virtual module, and displaying abnormal labels at corresponding positions of the model.
In the embodiment of the invention, the current affected part condition of the patient is displayed by adopting the three-dimensional model, meanwhile, the affected part can be updated in real time and marked on the model in a conspicuous manner, so that the patient can conveniently know the condition in time and make a follow-up visit by holding the client, and meanwhile, medical staff can master the condition development condition at any time.
In addition, an embodiment of the present invention further provides a method for intelligently managing a breast tumor patient in a whole course, as shown in fig. 2, including:
s1, traversing the imaging examination image of each patient in a preset database, and outputting the image position of the suspected area and a risk score determined by extracting the image characteristics when the suspected area of the breast tumor is identified.
And S2, outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to a next-stage pathological diagnosis module for processing according to the palpation information of the patient and/or the auditing feedback information of medical staff called from the database aiming at the breast tumor suspected region image with the risk score smaller than a certain threshold value.
And S3, aiming at the breast tumor suspected region image with the risk score not less than a certain threshold or the image pushed by the first pathological diagnosis module, outputting a pathological result according to one or more data of palpation information of the patient, audit feedback information of medical staff, the suspected region image, a gene detection result and a histopathological examination result called from a preset database.
And S4, determining at least one disease category based on the pathological result, and outputting a treatment scheme by combining the patient information and the related treatment cases called from the database.
And S5, establishing a three-dimensional patient model according to the follow-up suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
Meanwhile, the invention provides a breast tumor patient whole-course intelligent management device, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of a method for intelligent management of breast tumor patients throughout a course as described above; and, a computer readable storage medium is also provided, on which computer executable instructions are stored, which when executed by a processor, implement the steps of a method for the whole-course intelligent management of breast tumor patients as described above.
In summary, the present invention provides a system, a method, a device, and a medium for overall intelligent management of a breast tumor patient, which are provided with a preliminary screening module capable of outputting a suspected area image position and a risk score, a first pathological diagnosis module capable of diagnosing a suspected area image of a breast tumor with a risk score smaller than a certain threshold, a second pathological diagnosis module capable of diagnosing a suspected area image of a breast tumor with a risk score not smaller than a certain threshold or an image pushed by the first pathological diagnosis module, a treatment scheme output module capable of outputting a treatment scheme, and a follow-up interaction module interacting with a patient and constructing a three-dimensional patient model. The invention provides a whole-course intelligent management scheme from discovery, diagnosis, intervention to follow-up visit aiming at the malignant tumor of the mammary gland, so that a patient can screen diseases in time, medical personnel can intervene in time, which has great significance for the life cycle of breast tumor patients, stabilizes the emotion of the patients, promotes the improvement of the disease conditions from the side and improves the cure rate.
Since the system/apparatus described in the above embodiments of the present invention is a system/apparatus used for implementing the method of the above embodiments of the present invention, a person skilled in the art can understand the specific structure and modification of the system/apparatus based on the method described in the above embodiments of the present invention, and thus the detailed description is omitted here. All systems/devices adopted by the methods of the above embodiments of the present invention are within the intended scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third and the like are for convenience only and do not denote any order. These words are to be understood as part of the name of the component.
Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all such variations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.

Claims (10)

1. A system for the whole-course intelligent management of breast tumor patients is characterized by comprising:
the primary screening module is used for traversing the imaging examination image of each patient in a preset database, and outputting the image position of a suspected area and a risk score determined by extracting the image characteristics when the suspected area of the breast tumor is identified;
the first pathological diagnosis module is used for outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to a next-stage pathological diagnosis module for processing according to the palpation information of the patient and/or the auditing feedback information of medical personnel called from the database aiming at the suspected area image of the breast tumor with the risk score smaller than a certain threshold value;
the second pathological diagnosis module is used for outputting pathological results according to one or more data of palpation information of a patient, audit feedback information of medical staff, suspected region images, gene detection results and histopathological examination results, which are called from a preset database, aiming at the breast tumor suspected region images with the risk score not less than a certain threshold value or the images pushed by the first pathological diagnosis module;
a treatment plan output module for determining at least one disease category based on the pathological result and outputting a treatment plan by combining the patient information and the past related treatment cases called from the database;
and the follow-up visit interaction module is used for establishing a three-dimensional patient model according to the follow-up diagnosis suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
2. The breast cancer postoperative global intelligent management system according to claim 1, wherein the primary screening module comprises:
the tumor suspected area identification unit is used for traversing the imaging examination image of each patient and recording the image position of the suspected area when the breast tumor suspected area is identified;
the characteristic extraction unit is used for extracting key characteristics from the breast tumor suspected region image;
and the risk determining unit is used for obtaining a risk score through a pre-trained risk prediction model according to the key characteristics.
3. The breast cancer postoperative global intelligent management system according to claim 2,
the imaging examination image is image data acquired by CT, PET, magnetic resonance or ultrasonic imaging equipment;
the key features include: morphology, edges, maximum diameter, ratio of longitudinal to transverse diameters, resistance index, peak systolic flow rate, parenchymal echo, cystic changes, calcific foci and blood flow signals;
the risk prediction model is as follows: a support vector machine, a neural network, a Bayesian network, and a decision tree.
4. The postoperative full-range intelligent breast cancer management system according to claim 1, wherein the first pathological diagnosis module comprises:
the palpation information calling unit is used for calling the palpation information of the patient from a preset database;
the first pushing unit is used for pushing the breast tumor suspected region image with the risk score smaller than a certain threshold value to an operation end of medical staff so as to obtain audit feedback information of the medical staff;
the report output unit is used for outputting a follow-up diagnosis suggestion report when the palpation information and the audit feedback information of the patient both indicate a benign conclusion;
and the second pushing unit is used for pushing the palpation information and the audit feedback information of the patient to a next-stage pathological diagnosis module for processing when at least one of the palpation information and the audit feedback information of the patient indicates a non-benign conclusion.
5. The breast cancer postoperative global intelligent management system of claim 1, wherein the second pathological diagnosis module comprises:
the multi-information calling and processing unit is used for calling one or more data of the patient palpation information, the medical staff auditing feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result from a preset database and carrying out normalization processing;
the multi-factor regression analysis unit is used for obtaining a plurality of risk factors through Logistic regression analysis on the normalized patient palpation information, the medical staff audit feedback information, the suspected tumor area image, the gene detection result and the histopathology examination result;
the pathological result output unit is used for comparing each risk factor with a preset threshold value to obtain a pathological result;
wherein the pathological result comprises one or more data of diagnosis age, tumor type, tumor stage, tumor size, molecular classification, regional lymph node metastasis condition and distant metastasis condition.
6. The postoperative full-range intelligent management system for breast cancer according to claim 1, wherein the treatment plan output module comprises:
a disease classification unit for determining at least one disease category based on the pathology result;
a related treatment case calling unit for calling a related treatment case set S = { x } from the database according to the disease category 1 ,x 2 ,…,x n }; wherein x is n For the case of the n-th treatment,
Figure FDA0003887440300000031
Figure FDA0003887440300000032
for a plurality of characteristic data of each treatment case, i and n are positive integers;
a quantization processing unit for quantizing the current disease category and the patient information to form the current case
Figure FDA0003887440300000033
A treatment case screening unit for calculating the current case
Figure FDA0003887440300000034
And associated treatment case set s t ＝{x 1 ,x 2 ,…,x n Each treatment case of
Figure FDA0003887440300000035
The distance value of (a);
the treatment scheme output unit is used for taking the treatment case with the minimum distance value as the treatment scheme;
the treatment cases are stored in a preset database in a set form through a clustering mode; and the plurality of feature data comprises: one or more of age, height, weight, comorbidities, past history, family tumor history, adverse drug reactions, economic status, treatment waiting time, treatment effect, treatment side effects, length of treatment spent, and economic cost.
7. The system for full-scale intelligent post-operative management of breast cancer according to any one of claims 1-6, wherein the prognostic follow-up module comprises:
the follow-up visit unit is used for obtaining the prognostic sign indexes of the patients through follow-up visit;
the three-dimensional model building unit is used for building a three-dimensional patient model which can simulate the daily activities of a patient;
and the import display unit is used for importing the data in the follow-up suggestion report or the prognostic sign index into the virtual module, and displaying the abnormal label at the corresponding position of the model.
8. A whole-course intelligent management method for breast tumor patients is characterized by comprising the following steps:
traversing the imaging examination image of each patient in a preset database, and outputting the image position of the suspected area and a risk score determined by extracting the image characteristics when the suspected area of the breast tumor is identified;
aiming at the breast tumor suspected region image with the risk score smaller than a certain threshold value, outputting a follow-up diagnosis suggestion report or pushing the follow-up diagnosis suggestion report to a next-stage pathological diagnosis module for processing according to the palpation information of the patient and/or the auditing feedback information of medical staff called from the database;
aiming at the breast tumor suspected region image with the risk score not less than a certain threshold value or the image pushed by the first pathological diagnosis module, outputting a pathological result according to one or more data of palpation information of a patient, audit feedback information of medical staff, the suspected region image, a gene detection result and a histopathological examination result called from a preset database;
determining at least one disease category based on the pathology results and outputting a treatment plan in conjunction with patient information and past related treatment cases recalled from a database;
and establishing a three-dimensional patient model according to the follow-up suggestion report or the prognostic sign indexes of the patient obtained through follow-up visit so that the patient can obtain the disease development condition at any time.
9. A breast tumor patient global intelligent management device is characterized by comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method steps of claim 8 for full-scale intelligent management of a breast tumor patient.
10. A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, implement the method steps of claim 8 for global intelligent management of a breast tumor patient.
CN202211248421.7A 2022-10-12 2022-10-12 Whole-course intelligent management system, method, equipment and medium for breast tumor patients Active CN115458160B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211248421.7A CN115458160B (en) 2022-10-12 2022-10-12 Whole-course intelligent management system, method, equipment and medium for breast tumor patients

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211248421.7A CN115458160B (en) 2022-10-12 2022-10-12 Whole-course intelligent management system, method, equipment and medium for breast tumor patients

Publications (2)

Publication Number Publication Date
CN115458160A true CN115458160A (en) 2022-12-09
CN115458160B CN115458160B (en) 2023-06-20

Family

ID=84308192

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211248421.7A Active CN115458160B (en) 2022-10-12 2022-10-12 Whole-course intelligent management system, method, equipment and medium for breast tumor patients

Country Status (1)

Country Link
CN (1) CN115458160B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109166105A (en) * 2018-08-01 2019-01-08 中国人民解放军***南京总医院 The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image
CN110584605A (en) * 2019-09-10 2019-12-20 贾英 Similarity-matched diagnosis and monitoring comprehensive medical system and matching method thereof
CN111279195A (en) * 2017-10-16 2020-06-12 生物预测公司 Method for prognosis and follow-up of primary liver cancer
CN111340770A (en) * 2020-02-22 2020-06-26 太原理工大学 Method for constructing cancer prognosis model by combining global weighted LBP (local binary pattern) and texture analysis
CN111657945A (en) * 2020-06-16 2020-09-15 中南大学湘雅医院 Nasopharyngeal carcinoma prognosis auxiliary evaluation method based on enhanced MRI (magnetic resonance imaging) imaging omics
CN112435743A (en) * 2020-12-09 2021-03-02 上海市第一人民医院 Bladder cancer pathological omics intelligent diagnosis method based on machine learning and prognosis model thereof
CN112802600A (en) * 2021-02-07 2021-05-14 山东第一医科大学附属省立医院(山东省立医院) Whole-course supervision system and method for soft tissue tumor informatization pathology auxiliary diagnosis
US11263749B1 (en) * 2021-06-04 2022-03-01 In-Med Prognostics Inc. Predictive prognosis based on multimodal analysis

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111279195A (en) * 2017-10-16 2020-06-12 生物预测公司 Method for prognosis and follow-up of primary liver cancer
CN109166105A (en) * 2018-08-01 2019-01-08 中国人民解放军***南京总医院 The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image
CN110584605A (en) * 2019-09-10 2019-12-20 贾英 Similarity-matched diagnosis and monitoring comprehensive medical system and matching method thereof
CN111340770A (en) * 2020-02-22 2020-06-26 太原理工大学 Method for constructing cancer prognosis model by combining global weighted LBP (local binary pattern) and texture analysis
CN111657945A (en) * 2020-06-16 2020-09-15 中南大学湘雅医院 Nasopharyngeal carcinoma prognosis auxiliary evaluation method based on enhanced MRI (magnetic resonance imaging) imaging omics
CN112435743A (en) * 2020-12-09 2021-03-02 上海市第一人民医院 Bladder cancer pathological omics intelligent diagnosis method based on machine learning and prognosis model thereof
CN112802600A (en) * 2021-02-07 2021-05-14 山东第一医科大学附属省立医院(山东省立医院) Whole-course supervision system and method for soft tissue tumor informatization pathology auxiliary diagnosis
US11263749B1 (en) * 2021-06-04 2022-03-01 In-Med Prognostics Inc. Predictive prognosis based on multimodal analysis

Also Published As

Publication number Publication date
CN115458160B (en) 2023-06-20

Similar Documents

Publication Publication Date Title
US11416716B2 (en) System and method for automatic assessment of cancer
US11462325B2 (en) Multimodal machine learning based clinical predictor
US10825167B2 (en) Rapid assessment and outcome analysis for medical patients
US11037070B2 (en) Diagnostic test planning using machine learning techniques
EP3404666A2 (en) Rapid assessment and outcome analysis for medical patients
Lee et al. Decomposing MRI phenotypic heterogeneity in epilepsy: a step towards personalized classification
WO2022060949A1 (en) Systems and methods for automatically identifying a candidate patient for enrollment in a clinical trial
Amarasinghe et al. A deep learning model to automate skeletal muscle area measurement on computed tomography images
Cretoiu et al. Simulation and modeling of telocytes behavior in signaling and intercellular communication processes
WO2022060948A1 (en) Systems and methods for automatically notifying a caregiver that a patient requires medical intervention
Trebeschi et al. Development of a prognostic AI-monitor for metastatic urothelial cancer patients receiving immunotherapy
Singh et al. Classification of first trimester ultrasound images using deep convolutional neural network
WO2022165433A1 (en) Systems and methods for classifying biomedical image data using a graph neural network
CN114300075A (en) Exercise medical health data management system based on big data
Wei et al. Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity
Mekov et al. Machine learning in lung transplantation: Where are we?
Shi et al. Radiomics for the prediction of pathological complete response to neoadjuvant chemoradiation in locally advanced rectal cancer: a prospective observational trial
Xiang et al. ADSeg: A flap-attention-based deep learning approach for aortic dissection segmentation
CN115458160A (en) Whole-course intelligent management system, method, equipment and medium for breast tumor patient
Olivetti et al. Fast clustering for interactive tractography segmentation
CN113220896B (en) Multi-source knowledge graph generation method, device and terminal equipment
CN113706541B (en) Image processing method and device
CN110570943B (en) Method and device for intelligently recommending MDT (minimization of drive test) grouping, electronic equipment and storage medium
CN114068004A (en) Colorectal cancer clinical decision, teaching and scientific research auxiliary support system and method
Kollmann et al. Cardiac function in a large animal model of myocardial infarction at 7 T: deep learning based automatic segmentation increases reproducibility

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
GR01 Patent grant
GR01 Patent grant